GPT-5 Nano

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  outputFormat: 'JSON',
  model: 'openai:gpt@5-nano',
  settings: {
    thinkingLevel: 'medium'
  },
  messages: [
    {
      role: 'user',
      content: 'Analyze the following proposed retail lease for Harbor Bowl LLC, a fast-casual restaurant operator. Produce a decision-ready lease abstract and risk register for the operator\'s real-estate counsel and finance team. Use only the supplied text. Cite the relevant section and quote short supporting language for every risk. Do not treat missing information as fact; identify it as an open question. Return only JSON matching the supplied schema.\n\nPROPOSED LEASE EXCERPT\n\nPremises: Suite 140, approximately 2,850 rentable square feet, Meridian Commons, Austin, Texas.\n\n§2 Term. The Term begins on the earlier of (a) Tenant opening for business or (b) 120 days after Landlord delivers possession. The Term expires ten years after the Rent Commencement Date. Tenant has two five-year extension options by giving notice not less than 12 months and not more than 15 months before the then-current expiration date. No option may be exercised if Tenant is then in default beyond any applicable cure period.\n\n§3 Base Rent. Year 1 Base Rent is $128,250 per year, payable monthly. Base Rent increases by 3% on each anniversary of the Rent Commencement Date. Tenant shall also pay Percentage Rent equal to 6% of annual Gross Sales exceeding the natural breakpoint. Gross Sales includes all sales originating from the Premises, including delivery-platform and online orders fulfilled there, without deduction for third-party commissions.\n\n§4 Additional Rent. Tenant shall pay its Proportionate Share, stated as 8.4%, of Common Area Costs, property taxes, and insurance. Common Area Costs include management fees not exceeding 5% of total Common Area Costs and capital expenditures amortized over the useful life determined by Landlord. There is no annual cap. Tenant shall pay estimates monthly and any reconciliation balance within 20 days after notice. Tenant may audit records once per calendar year by notice given within 60 days after receiving the reconciliation statement.\n\n§6 Delivery and Improvements. Landlord will deliver the Premises broom-clean with existing utility stubs in their current condition. Tenant accepts the Premises as-is. Tenant is responsible for all design, permitting, grease interceptor work, utility upgrades, and construction. Landlord provides a tenant-improvement allowance of $45 per rentable square foot, reimbursed after Tenant opens, provides final lien waivers, and demonstrates that no default exists. Any unused allowance is forfeited. Landlord makes no representation regarding the capacity of electrical, gas, water, sewer, or exhaust systems.\n\n§7 Use and Operation. Permitted Use is a fast-casual restaurant specializing in grain bowls, salads, and nonalcoholic beverages, and no other use. Tenant must operate continuously seven days per week during center hours, except for casualty, force majeure, or repairs approved by Landlord. Failure to operate for more than five consecutive days permits Landlord to collect, as additional rent, $500 per day until operations resume. Tenant receives no exclusive-use protection.\n\n§9 Repairs and Compliance. Tenant shall maintain and replace all equipment and systems exclusively serving the Premises, including HVAC, plumbing lines, grease interceptor, fire suppression, and exhaust equipment, regardless of whether installed by Tenant. Tenant shall comply with all laws affecting Tenant\'s use or occupancy, including accessibility requirements. Landlord maintains the roof, foundation, and structural walls, with the cost included in Common Area Costs unless caused by Tenant.\n\n§12 Assignment. Tenant may not assign the Lease, sublet any portion of the Premises, or undergo a transfer of more than 25% of its ownership interests without Landlord\'s prior written consent, which may be withheld in Landlord\'s sole discretion. Any approved transfer does not release Tenant or any guarantor. Landlord may recapture the Premises instead of approving a proposed assignment or sublease.\n\n§15 Default. Monetary defaults have a five-day cure period after written notice. Nonmonetary defaults have a ten-day cure period, provided that if a default cannot reasonably be cured within ten days, Tenant must begin cure within that period and diligently complete it. Notwithstanding the foregoing, Landlord is not required to provide more than two notices of monetary default in any 12-month period.\n\n§18 Indemnity and Insurance. Tenant indemnifies Landlord against all claims arising in or about the Premises, except to the extent caused by Landlord\'s gross negligence or willful misconduct. Tenant must maintain commercial general liability insurance of at least $5,000,000 per occurrence, business interruption coverage for 18 months, and any other coverage Landlord reasonably requires. Landlord is not liable for lost profits or interruption of Tenant\'s business.\n\n§21 Guaranty. Harbor Bowl Holdings Inc. shall execute Landlord\'s standard form of continuing guaranty covering all Tenant obligations. The guaranty does not burn off or reduce during the Term and remains effective after any assignment.\n\n§24 Relocation. After the fifth Lease Year, Landlord may relocate Tenant to other premises in the center of comparable size. Landlord will pay reasonable moving expenses and the unamortized cost of Tenant\'s initial improvements, calculated on a straight-line basis over ten years. Tenant has no termination right in connection with relocation.\n\n§27 Casualty. If the Premises is materially damaged, Landlord may elect to restore or terminate the Lease. Base Rent abates proportionately while the Premises is unusable, but Additional Rent continues. Tenant may terminate only if restoration is not substantially complete within 270 days after the casualty.\n\nBusiness assumptions supplied by Tenant: planned opening 180 days after possession; estimated initial build-out cost of $650,000; projected first-year Gross Sales of $2,400,000; delivery-platform commissions average 24% of delivery sales; uninterrupted operation at this location is important to catering contracts; the parent company will not approve an unlimited guaranty.'
    }
  ],
  jsonSchema: {
    name: 'response',
    strict: true,
    schema: {
      type: 'object',
      properties: {
        summary: {
          type: 'string'
        },
        keyPoints: {
          type: 'array',
          items: {
            type: 'string'
          }
        },
        category: {
          type: 'string'
        }
      },
      required: [
        'summary',
        'keyPoints',
        'category'
      ],
      additionalProperties: false
    }
  }
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "outputFormat": "JSON",
            "model": "openai:gpt@5-nano",
            "settings": {
                "thinkingLevel": "medium"
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Analyze the following proposed retail lease for Harbor Bowl LLC, a fast-casual restaurant operator. Produce a decision-ready lease abstract and risk register for the operator's real-estate counsel and finance team. Use only the supplied text. Cite the relevant section and quote short supporting language for every risk. Do not treat missing information as fact; identify it as an open question. Return only JSON matching the supplied schema.\n\nPROPOSED LEASE EXCERPT\n\nPremises: Suite 140, approximately 2,850 rentable square feet, Meridian Commons, Austin, Texas.\n\n§2 Term. The Term begins on the earlier of (a) Tenant opening for business or (b) 120 days after Landlord delivers possession. The Term expires ten years after the Rent Commencement Date. Tenant has two five-year extension options by giving notice not less than 12 months and not more than 15 months before the then-current expiration date. No option may be exercised if Tenant is then in default beyond any applicable cure period.\n\n§3 Base Rent. Year 1 Base Rent is $128,250 per year, payable monthly. Base Rent increases by 3% on each anniversary of the Rent Commencement Date. Tenant shall also pay Percentage Rent equal to 6% of annual Gross Sales exceeding the natural breakpoint. Gross Sales includes all sales originating from the Premises, including delivery-platform and online orders fulfilled there, without deduction for third-party commissions.\n\n§4 Additional Rent. Tenant shall pay its Proportionate Share, stated as 8.4%, of Common Area Costs, property taxes, and insurance. Common Area Costs include management fees not exceeding 5% of total Common Area Costs and capital expenditures amortized over the useful life determined by Landlord. There is no annual cap. Tenant shall pay estimates monthly and any reconciliation balance within 20 days after notice. Tenant may audit records once per calendar year by notice given within 60 days after receiving the reconciliation statement.\n\n§6 Delivery and Improvements. Landlord will deliver the Premises broom-clean with existing utility stubs in their current condition. Tenant accepts the Premises as-is. Tenant is responsible for all design, permitting, grease interceptor work, utility upgrades, and construction. Landlord provides a tenant-improvement allowance of $45 per rentable square foot, reimbursed after Tenant opens, provides final lien waivers, and demonstrates that no default exists. Any unused allowance is forfeited. Landlord makes no representation regarding the capacity of electrical, gas, water, sewer, or exhaust systems.\n\n§7 Use and Operation. Permitted Use is a fast-casual restaurant specializing in grain bowls, salads, and nonalcoholic beverages, and no other use. Tenant must operate continuously seven days per week during center hours, except for casualty, force majeure, or repairs approved by Landlord. Failure to operate for more than five consecutive days permits Landlord to collect, as additional rent, $500 per day until operations resume. Tenant receives no exclusive-use protection.\n\n§9 Repairs and Compliance. Tenant shall maintain and replace all equipment and systems exclusively serving the Premises, including HVAC, plumbing lines, grease interceptor, fire suppression, and exhaust equipment, regardless of whether installed by Tenant. Tenant shall comply with all laws affecting Tenant's use or occupancy, including accessibility requirements. Landlord maintains the roof, foundation, and structural walls, with the cost included in Common Area Costs unless caused by Tenant.\n\n§12 Assignment. Tenant may not assign the Lease, sublet any portion of the Premises, or undergo a transfer of more than 25% of its ownership interests without Landlord's prior written consent, which may be withheld in Landlord's sole discretion. Any approved transfer does not release Tenant or any guarantor. Landlord may recapture the Premises instead of approving a proposed assignment or sublease.\n\n§15 Default. Monetary defaults have a five-day cure period after written notice. Nonmonetary defaults have a ten-day cure period, provided that if a default cannot reasonably be cured within ten days, Tenant must begin cure within that period and diligently complete it. Notwithstanding the foregoing, Landlord is not required to provide more than two notices of monetary default in any 12-month period.\n\n§18 Indemnity and Insurance. Tenant indemnifies Landlord against all claims arising in or about the Premises, except to the extent caused by Landlord's gross negligence or willful misconduct. Tenant must maintain commercial general liability insurance of at least $5,000,000 per occurrence, business interruption coverage for 18 months, and any other coverage Landlord reasonably requires. Landlord is not liable for lost profits or interruption of Tenant's business.\n\n§21 Guaranty. Harbor Bowl Holdings Inc. shall execute Landlord's standard form of continuing guaranty covering all Tenant obligations. The guaranty does not burn off or reduce during the Term and remains effective after any assignment.\n\n§24 Relocation. After the fifth Lease Year, Landlord may relocate Tenant to other premises in the center of comparable size. Landlord will pay reasonable moving expenses and the unamortized cost of Tenant's initial improvements, calculated on a straight-line basis over ten years. Tenant has no termination right in connection with relocation.\n\n§27 Casualty. If the Premises is materially damaged, Landlord may elect to restore or terminate the Lease. Base Rent abates proportionately while the Premises is unusable, but Additional Rent continues. Tenant may terminate only if restoration is not substantially complete within 270 days after the casualty.\n\nBusiness assumptions supplied by Tenant: planned opening 180 days after possession; estimated initial build-out cost of $650,000; projected first-year Gross Sales of $2,400,000; delivery-platform commissions average 24% of delivery sales; uninterrupted operation at this location is important to catering contracts; the parent company will not approve an unlimited guaranty."
                }
            ],
            "jsonSchema": {
                "name": "response",
                "strict": True,
                "schema": {
                    "type": "object",
                    "properties": {
                        "summary": {
                            "type": "string"
                        },
                        "keyPoints": {
                            "type": "array",
                            "items": {
                                "type": "string"
                            }
                        },
                        "category": {
                            "type": "string"
                        }
                    },
                    "required": [
                        "summary",
                        "keyPoints",
                        "category"
                    ],
                    "additionalProperties": False
                }
            }
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "9f51ac06-99d8-4297-a48a-f37be4337ef2",
      "outputFormat": "JSON",
      "model": "openai:gpt@5-nano",
      "settings": {
        "thinkingLevel": "medium"
      },
      "messages": [
        {
          "role": "user",
          "content": "Analyze the following proposed retail lease for Harbor Bowl LLC, a fast-casual restaurant operator. Produce a decision-ready lease abstract and risk register for the operator's real-estate counsel and finance team. Use only the supplied text. Cite the relevant section and quote short supporting language for every risk. Do not treat missing information as fact; identify it as an open question. Return only JSON matching the supplied schema.\n\nPROPOSED LEASE EXCERPT\n\nPremises: Suite 140, approximately 2,850 rentable square feet, Meridian Commons, Austin, Texas.\n\n§2 Term. The Term begins on the earlier of (a) Tenant opening for business or (b) 120 days after Landlord delivers possession. The Term expires ten years after the Rent Commencement Date. Tenant has two five-year extension options by giving notice not less than 12 months and not more than 15 months before the then-current expiration date. No option may be exercised if Tenant is then in default beyond any applicable cure period.\n\n§3 Base Rent. Year 1 Base Rent is $128,250 per year, payable monthly. Base Rent increases by 3% on each anniversary of the Rent Commencement Date. Tenant shall also pay Percentage Rent equal to 6% of annual Gross Sales exceeding the natural breakpoint. Gross Sales includes all sales originating from the Premises, including delivery-platform and online orders fulfilled there, without deduction for third-party commissions.\n\n§4 Additional Rent. Tenant shall pay its Proportionate Share, stated as 8.4%, of Common Area Costs, property taxes, and insurance. Common Area Costs include management fees not exceeding 5% of total Common Area Costs and capital expenditures amortized over the useful life determined by Landlord. There is no annual cap. Tenant shall pay estimates monthly and any reconciliation balance within 20 days after notice. Tenant may audit records once per calendar year by notice given within 60 days after receiving the reconciliation statement.\n\n§6 Delivery and Improvements. Landlord will deliver the Premises broom-clean with existing utility stubs in their current condition. Tenant accepts the Premises as-is. Tenant is responsible for all design, permitting, grease interceptor work, utility upgrades, and construction. Landlord provides a tenant-improvement allowance of $45 per rentable square foot, reimbursed after Tenant opens, provides final lien waivers, and demonstrates that no default exists. Any unused allowance is forfeited. Landlord makes no representation regarding the capacity of electrical, gas, water, sewer, or exhaust systems.\n\n§7 Use and Operation. Permitted Use is a fast-casual restaurant specializing in grain bowls, salads, and nonalcoholic beverages, and no other use. Tenant must operate continuously seven days per week during center hours, except for casualty, force majeure, or repairs approved by Landlord. Failure to operate for more than five consecutive days permits Landlord to collect, as additional rent, $500 per day until operations resume. Tenant receives no exclusive-use protection.\n\n§9 Repairs and Compliance. Tenant shall maintain and replace all equipment and systems exclusively serving the Premises, including HVAC, plumbing lines, grease interceptor, fire suppression, and exhaust equipment, regardless of whether installed by Tenant. Tenant shall comply with all laws affecting Tenant's use or occupancy, including accessibility requirements. Landlord maintains the roof, foundation, and structural walls, with the cost included in Common Area Costs unless caused by Tenant.\n\n§12 Assignment. Tenant may not assign the Lease, sublet any portion of the Premises, or undergo a transfer of more than 25% of its ownership interests without Landlord's prior written consent, which may be withheld in Landlord's sole discretion. Any approved transfer does not release Tenant or any guarantor. Landlord may recapture the Premises instead of approving a proposed assignment or sublease.\n\n§15 Default. Monetary defaults have a five-day cure period after written notice. Nonmonetary defaults have a ten-day cure period, provided that if a default cannot reasonably be cured within ten days, Tenant must begin cure within that period and diligently complete it. Notwithstanding the foregoing, Landlord is not required to provide more than two notices of monetary default in any 12-month period.\n\n§18 Indemnity and Insurance. Tenant indemnifies Landlord against all claims arising in or about the Premises, except to the extent caused by Landlord's gross negligence or willful misconduct. Tenant must maintain commercial general liability insurance of at least $5,000,000 per occurrence, business interruption coverage for 18 months, and any other coverage Landlord reasonably requires. Landlord is not liable for lost profits or interruption of Tenant's business.\n\n§21 Guaranty. Harbor Bowl Holdings Inc. shall execute Landlord's standard form of continuing guaranty covering all Tenant obligations. The guaranty does not burn off or reduce during the Term and remains effective after any assignment.\n\n§24 Relocation. After the fifth Lease Year, Landlord may relocate Tenant to other premises in the center of comparable size. Landlord will pay reasonable moving expenses and the unamortized cost of Tenant's initial improvements, calculated on a straight-line basis over ten years. Tenant has no termination right in connection with relocation.\n\n§27 Casualty. If the Premises is materially damaged, Landlord may elect to restore or terminate the Lease. Base Rent abates proportionately while the Premises is unusable, but Additional Rent continues. Tenant may terminate only if restoration is not substantially complete within 270 days after the casualty.\n\nBusiness assumptions supplied by Tenant: planned opening 180 days after possession; estimated initial build-out cost of $650,000; projected first-year Gross Sales of $2,400,000; delivery-platform commissions average 24% of delivery sales; uninterrupted operation at this location is important to catering contracts; the parent company will not approve an unlimited guaranty."
        }
      ],
      "jsonSchema": {
        "name": "response",
        "strict": true,
        "schema": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            },
            "keyPoints": {
              "type": "array",
              "items": {
                "type": "string"
              }
            },
            "category": {
              "type": "string"
            }
          },
          "required": [
            "summary",
            "keyPoints",
            "category"
          ],
          "additionalProperties": false
        }
      }
    }
  ]'

runware run openai:gpt@5-nano \
  outputFormat=JSON \
  settings.thinkingLevel=medium \
  messages.0.role=user \
  messages.0.content="Analyze the following proposed retail lease for Harbor Bowl LLC, a fast-casual restaurant operator. Produce a decision-ready lease abstract and risk register for the operator's real-estate counsel and finance team. Use only the supplied text. Cite the relevant section and quote short supporting language for every risk. Do not treat missing information as fact; identify it as an open question. Return only JSON matching the supplied schema.

PROPOSED LEASE EXCERPT

Premises: Suite 140, approximately 2,850 rentable square feet, Meridian Commons, Austin, Texas.

§2 Term. The Term begins on the earlier of (a) Tenant opening for business or (b) 120 days after Landlord delivers possession. The Term expires ten years after the Rent Commencement Date. Tenant has two five-year extension options by giving notice not less than 12 months and not more than 15 months before the then-current expiration date. No option may be exercised if Tenant is then in default beyond any applicable cure period.

§3 Base Rent. Year 1 Base Rent is \$128,250 per year, payable monthly. Base Rent increases by 3% on each anniversary of the Rent Commencement Date. Tenant shall also pay Percentage Rent equal to 6% of annual Gross Sales exceeding the natural breakpoint. Gross Sales includes all sales originating from the Premises, including delivery-platform and online orders fulfilled there, without deduction for third-party commissions.

§4 Additional Rent. Tenant shall pay its Proportionate Share, stated as 8.4%, of Common Area Costs, property taxes, and insurance. Common Area Costs include management fees not exceeding 5% of total Common Area Costs and capital expenditures amortized over the useful life determined by Landlord. There is no annual cap. Tenant shall pay estimates monthly and any reconciliation balance within 20 days after notice. Tenant may audit records once per calendar year by notice given within 60 days after receiving the reconciliation statement.

§6 Delivery and Improvements. Landlord will deliver the Premises broom-clean with existing utility stubs in their current condition. Tenant accepts the Premises as-is. Tenant is responsible for all design, permitting, grease interceptor work, utility upgrades, and construction. Landlord provides a tenant-improvement allowance of \$45 per rentable square foot, reimbursed after Tenant opens, provides final lien waivers, and demonstrates that no default exists. Any unused allowance is forfeited. Landlord makes no representation regarding the capacity of electrical, gas, water, sewer, or exhaust systems.

§7 Use and Operation. Permitted Use is a fast-casual restaurant specializing in grain bowls, salads, and nonalcoholic beverages, and no other use. Tenant must operate continuously seven days per week during center hours, except for casualty, force majeure, or repairs approved by Landlord. Failure to operate for more than five consecutive days permits Landlord to collect, as additional rent, \$500 per day until operations resume. Tenant receives no exclusive-use protection.

§9 Repairs and Compliance. Tenant shall maintain and replace all equipment and systems exclusively serving the Premises, including HVAC, plumbing lines, grease interceptor, fire suppression, and exhaust equipment, regardless of whether installed by Tenant. Tenant shall comply with all laws affecting Tenant's use or occupancy, including accessibility requirements. Landlord maintains the roof, foundation, and structural walls, with the cost included in Common Area Costs unless caused by Tenant.

§12 Assignment. Tenant may not assign the Lease, sublet any portion of the Premises, or undergo a transfer of more than 25% of its ownership interests without Landlord's prior written consent, which may be withheld in Landlord's sole discretion. Any approved transfer does not release Tenant or any guarantor. Landlord may recapture the Premises instead of approving a proposed assignment or sublease.

§15 Default. Monetary defaults have a five-day cure period after written notice. Nonmonetary defaults have a ten-day cure period, provided that if a default cannot reasonably be cured within ten days, Tenant must begin cure within that period and diligently complete it. Notwithstanding the foregoing, Landlord is not required to provide more than two notices of monetary default in any 12-month period.

§18 Indemnity and Insurance. Tenant indemnifies Landlord against all claims arising in or about the Premises, except to the extent caused by Landlord's gross negligence or willful misconduct. Tenant must maintain commercial general liability insurance of at least \$5,000,000 per occurrence, business interruption coverage for 18 months, and any other coverage Landlord reasonably requires. Landlord is not liable for lost profits or interruption of Tenant's business.

§21 Guaranty. Harbor Bowl Holdings Inc. shall execute Landlord's standard form of continuing guaranty covering all Tenant obligations. The guaranty does not burn off or reduce during the Term and remains effective after any assignment.

§24 Relocation. After the fifth Lease Year, Landlord may relocate Tenant to other premises in the center of comparable size. Landlord will pay reasonable moving expenses and the unamortized cost of Tenant's initial improvements, calculated on a straight-line basis over ten years. Tenant has no termination right in connection with relocation.

§27 Casualty. If the Premises is materially damaged, Landlord may elect to restore or terminate the Lease. Base Rent abates proportionately while the Premises is unusable, but Additional Rent continues. Tenant may terminate only if restoration is not substantially complete within 270 days after the casualty.

Business assumptions supplied by Tenant: planned opening 180 days after possession; estimated initial build-out cost of \$650,000; projected first-year Gross Sales of \$2,400,000; delivery-platform commissions average 24% of delivery sales; uninterrupted operation at this location is important to catering contracts; the parent company will not approve an unlimited guaranty." \
  jsonSchema.name=response \
  jsonSchema.strict=true \
  jsonSchema.schema.type=object \
  jsonSchema.schema.properties.summary.type=string \
  jsonSchema.schema.properties.keyPoints.type=array \
  jsonSchema.schema.properties.keyPoints.items.type=string \
  jsonSchema.schema.properties.category.type=string \
  jsonSchema.schema.required.0=summary \
  jsonSchema.schema.required.1=keyPoints \
  jsonSchema.schema.required.2=category \
  jsonSchema.schema.additionalProperties=false

{
  "taskType": "textInference",
  "taskUUID": "9f51ac06-99d8-4297-a48a-f37be4337ef2",
  "outputFormat": "JSON",
  "model": "openai:gpt@5-nano",
  "settings": {
    "thinkingLevel": "medium"
  },
  "messages": [
    {
      "role": "user",
      "content": "Analyze the following proposed retail lease for Harbor Bowl LLC, a fast-casual restaurant operator. Produce a decision-ready lease abstract and risk register for the operator's real-estate counsel and finance team. Use only the supplied text. Cite the relevant section and quote short supporting language for every risk. Do not treat missing information as fact; identify it as an open question. Return only JSON matching the supplied schema.\n\nPROPOSED LEASE EXCERPT\n\nPremises: Suite 140, approximately 2,850 rentable square feet, Meridian Commons, Austin, Texas.\n\n§2 Term. The Term begins on the earlier of (a) Tenant opening for business or (b) 120 days after Landlord delivers possession. The Term expires ten years after the Rent Commencement Date. Tenant has two five-year extension options by giving notice not less than 12 months and not more than 15 months before the then-current expiration date. No option may be exercised if Tenant is then in default beyond any applicable cure period.\n\n§3 Base Rent. Year 1 Base Rent is $128,250 per year, payable monthly. Base Rent increases by 3% on each anniversary of the Rent Commencement Date. Tenant shall also pay Percentage Rent equal to 6% of annual Gross Sales exceeding the natural breakpoint. Gross Sales includes all sales originating from the Premises, including delivery-platform and online orders fulfilled there, without deduction for third-party commissions.\n\n§4 Additional Rent. Tenant shall pay its Proportionate Share, stated as 8.4%, of Common Area Costs, property taxes, and insurance. Common Area Costs include management fees not exceeding 5% of total Common Area Costs and capital expenditures amortized over the useful life determined by Landlord. There is no annual cap. Tenant shall pay estimates monthly and any reconciliation balance within 20 days after notice. Tenant may audit records once per calendar year by notice given within 60 days after receiving the reconciliation statement.\n\n§6 Delivery and Improvements. Landlord will deliver the Premises broom-clean with existing utility stubs in their current condition. Tenant accepts the Premises as-is. Tenant is responsible for all design, permitting, grease interceptor work, utility upgrades, and construction. Landlord provides a tenant-improvement allowance of $45 per rentable square foot, reimbursed after Tenant opens, provides final lien waivers, and demonstrates that no default exists. Any unused allowance is forfeited. Landlord makes no representation regarding the capacity of electrical, gas, water, sewer, or exhaust systems.\n\n§7 Use and Operation. Permitted Use is a fast-casual restaurant specializing in grain bowls, salads, and nonalcoholic beverages, and no other use. Tenant must operate continuously seven days per week during center hours, except for casualty, force majeure, or repairs approved by Landlord. Failure to operate for more than five consecutive days permits Landlord to collect, as additional rent, $500 per day until operations resume. Tenant receives no exclusive-use protection.\n\n§9 Repairs and Compliance. Tenant shall maintain and replace all equipment and systems exclusively serving the Premises, including HVAC, plumbing lines, grease interceptor, fire suppression, and exhaust equipment, regardless of whether installed by Tenant. Tenant shall comply with all laws affecting Tenant's use or occupancy, including accessibility requirements. Landlord maintains the roof, foundation, and structural walls, with the cost included in Common Area Costs unless caused by Tenant.\n\n§12 Assignment. Tenant may not assign the Lease, sublet any portion of the Premises, or undergo a transfer of more than 25% of its ownership interests without Landlord's prior written consent, which may be withheld in Landlord's sole discretion. Any approved transfer does not release Tenant or any guarantor. Landlord may recapture the Premises instead of approving a proposed assignment or sublease.\n\n§15 Default. Monetary defaults have a five-day cure period after written notice. Nonmonetary defaults have a ten-day cure period, provided that if a default cannot reasonably be cured within ten days, Tenant must begin cure within that period and diligently complete it. Notwithstanding the foregoing, Landlord is not required to provide more than two notices of monetary default in any 12-month period.\n\n§18 Indemnity and Insurance. Tenant indemnifies Landlord against all claims arising in or about the Premises, except to the extent caused by Landlord's gross negligence or willful misconduct. Tenant must maintain commercial general liability insurance of at least $5,000,000 per occurrence, business interruption coverage for 18 months, and any other coverage Landlord reasonably requires. Landlord is not liable for lost profits or interruption of Tenant's business.\n\n§21 Guaranty. Harbor Bowl Holdings Inc. shall execute Landlord's standard form of continuing guaranty covering all Tenant obligations. The guaranty does not burn off or reduce during the Term and remains effective after any assignment.\n\n§24 Relocation. After the fifth Lease Year, Landlord may relocate Tenant to other premises in the center of comparable size. Landlord will pay reasonable moving expenses and the unamortized cost of Tenant's initial improvements, calculated on a straight-line basis over ten years. Tenant has no termination right in connection with relocation.\n\n§27 Casualty. If the Premises is materially damaged, Landlord may elect to restore or terminate the Lease. Base Rent abates proportionately while the Premises is unusable, but Additional Rent continues. Tenant may terminate only if restoration is not substantially complete within 270 days after the casualty.\n\nBusiness assumptions supplied by Tenant: planned opening 180 days after possession; estimated initial build-out cost of $650,000; projected first-year Gross Sales of $2,400,000; delivery-platform commissions average 24% of delivery sales; uninterrupted operation at this location is important to catering contracts; the parent company will not approve an unlimited guaranty."
    }
  ],
  "jsonSchema": {
    "name": "response",
    "strict": true,
    "schema": {
      "type": "object",
      "properties": {
        "summary": {
          "type": "string"
        },
        "keyPoints": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "category": {
          "type": "string"
        }
      },
      "required": [
        "summary",
        "keyPoints",
        "category"
      ],
      "additionalProperties": false
    }
  }
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5-nano',
  settings: {
    systemPrompt: 'You are an experienced warehouse EHS inspection assistant. Analyze only conditions that are directly visible in the supplied image. Do not infer measurements, legal violations, worker intent, or facts outside the frame. Produce a concise professional report with: an executive summary; a numbered findings table containing severity, visible evidence, hazard category, potential consequence, and recommended immediate action; positive safety observations; and items requiring an on-site inspection. Assign severity as Critical, High, Medium, or Low and explain the visual basis. State that the report is a preliminary visual screening and not a substitute for an inspection by a qualified safety professional.',
    maxTokens: 2500,
    thinkingLevel: 'low'
  },
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/510aa7c7-4108-4de0-ba53-5565a164a085.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Review the attached photograph from Receiving Bay 4 at a regional ecommerce distribution center. Prepare a shift-ready safety inspection report for the site EHS manager. Prioritize hazards that need immediate isolation or correction, cite where each condition appears in the image, and avoid reporting anything that is not visibly supported.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5-nano",
            "settings": {
                "systemPrompt": "You are an experienced warehouse EHS inspection assistant. Analyze only conditions that are directly visible in the supplied image. Do not infer measurements, legal violations, worker intent, or facts outside the frame. Produce a concise professional report with: an executive summary; a numbered findings table containing severity, visible evidence, hazard category, potential consequence, and recommended immediate action; positive safety observations; and items requiring an on-site inspection. Assign severity as Critical, High, Medium, or Low and explain the visual basis. State that the report is a preliminary visual screening and not a substitute for an inspection by a qualified safety professional.",
                "maxTokens": 2500,
                "thinkingLevel": "low"
            },
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/510aa7c7-4108-4de0-ba53-5565a164a085.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Review the attached photograph from Receiving Bay 4 at a regional ecommerce distribution center. Prepare a shift-ready safety inspection report for the site EHS manager. Prioritize hazards that need immediate isolation or correction, cite where each condition appears in the image, and avoid reporting anything that is not visibly supported."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "30999b2b-2474-4ed0-87c1-b970299a0a75",
      "model": "openai:gpt@5-nano",
      "settings": {
        "systemPrompt": "You are an experienced warehouse EHS inspection assistant. Analyze only conditions that are directly visible in the supplied image. Do not infer measurements, legal violations, worker intent, or facts outside the frame. Produce a concise professional report with: an executive summary; a numbered findings table containing severity, visible evidence, hazard category, potential consequence, and recommended immediate action; positive safety observations; and items requiring an on-site inspection. Assign severity as Critical, High, Medium, or Low and explain the visual basis. State that the report is a preliminary visual screening and not a substitute for an inspection by a qualified safety professional.",
        "maxTokens": 2500,
        "thinkingLevel": "low"
      },
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/510aa7c7-4108-4de0-ba53-5565a164a085.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Review the attached photograph from Receiving Bay 4 at a regional ecommerce distribution center. Prepare a shift-ready safety inspection report for the site EHS manager. Prioritize hazards that need immediate isolation or correction, cite where each condition appears in the image, and avoid reporting anything that is not visibly supported."
        }
      ]
    }
  ]'

runware run openai:gpt@5-nano \
  settings.systemPrompt="You are an experienced warehouse EHS inspection assistant. Analyze only conditions that are directly visible in the supplied image. Do not infer measurements, legal violations, worker intent, or facts outside the frame. Produce a concise professional report with: an executive summary; a numbered findings table containing severity, visible evidence, hazard category, potential consequence, and recommended immediate action; positive safety observations; and items requiring an on-site inspection. Assign severity as Critical, High, Medium, or Low and explain the visual basis. State that the report is a preliminary visual screening and not a substitute for an inspection by a qualified safety professional." \
  settings.maxTokens=2500 \
  settings.thinkingLevel=low \
  inputs.images.0=https://assets.runware.ai/assets/inputs/510aa7c7-4108-4de0-ba53-5565a164a085.jpg \
  messages.0.role=user \
  messages.0.content="Review the attached photograph from Receiving Bay 4 at a regional ecommerce distribution center. Prepare a shift-ready safety inspection report for the site EHS manager. Prioritize hazards that need immediate isolation or correction, cite where each condition appears in the image, and avoid reporting anything that is not visibly supported."

{
  "taskType": "textInference",
  "taskUUID": "30999b2b-2474-4ed0-87c1-b970299a0a75",
  "model": "openai:gpt@5-nano",
  "settings": {
    "systemPrompt": "You are an experienced warehouse EHS inspection assistant. Analyze only conditions that are directly visible in the supplied image. Do not infer measurements, legal violations, worker intent, or facts outside the frame. Produce a concise professional report with: an executive summary; a numbered findings table containing severity, visible evidence, hazard category, potential consequence, and recommended immediate action; positive safety observations; and items requiring an on-site inspection. Assign severity as Critical, High, Medium, or Low and explain the visual basis. State that the report is a preliminary visual screening and not a substitute for an inspection by a qualified safety professional.",
    "maxTokens": 2500,
    "thinkingLevel": "low"
  },
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/510aa7c7-4108-4de0-ba53-5565a164a085.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Review the attached photograph from Receiving Bay 4 at a regional ecommerce distribution center. Prepare a shift-ready safety inspection report for the site EHS manager. Prioritize hazards that need immediate isolation or correction, cite where each condition appears in the image, and avoid reporting anything that is not visibly supported."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5-nano',
  settings: {
    systemPrompt: 'You are a senior customer insights analyst. Produce concise, decision-ready business writing grounded only in the supplied evidence. Quantify findings when possible, distinguish facts from hypotheses, and never invent customer statements or metrics.',
    maxTokens: 3500,
    thinkingLevel: 'low'
  },
  messages: [
    {
      role: 'user',
      content: 'Prepare a standalone Q2 2026 churn analysis memo for the leadership team of Northstar Relay, a B2B workflow automation platform.\n\nACCOUNT DATA\n- 42 customers churned, representing $318,000 in annual recurring revenue.\n- Q1 comparison: 29 customers and $201,000 ARR churned.\n- Churned accounts by segment: SMB 27 accounts / $81,000 ARR; Mid-market 12 / $147,000; Enterprise 3 / $90,000.\n- Stated cancellation reasons: missing integrations 12; low adoption 10; budget reduction 8; reliability 6; switched to competitor 4; company closed 2.\n- Median customer age at cancellation: 7 months, down from 11 months in Q1.\n- 26 of 42 churned accounts had fewer than three active users in the final 30 days.\n- 19 had not launched a production workflow within 45 days of purchase.\n- Accounts completing an implementation workshop had 4.8% quarterly logo churn; accounts that did not had 11.9%.\n- Integration-related churn included Salesforce 5, NetSuite 4, Microsoft Dynamics 2, and Workday 1.\n\nSUPPORT AND PRODUCT SIGNALS\n- Failed workflow support tickets rose 34% quarter over quarter.\n- Median first response time improved from 5.2 hours to 3.1 hours.\n- Six reliability-related cancellations followed incidents affecting scheduled workflows between April 18 and May 9.\n- A NetSuite connector beta began June 20; no retention outcome is available yet.\n\nCUSTOMER INTERVIEW EXCERPTS\n1. Operations director, 180-person logistics company, $18,000 ARR: “The demo looked straightforward, but nobody on our team owned implementation. After two months we were still testing sample workflows.”\n2. RevOps lead, 420-person software company, $24,000 ARR: “We needed Salesforce custom-object support. The workaround created more maintenance than it removed.”\n3. COO, 75-person agency, $6,000 ARR: “We cut every tool that was not used weekly. Only two people ever logged in.”\n4. Finance systems manager, 900-person manufacturer, $36,000 ARR: “Two scheduled approval workflows failed during close. Support responded quickly, but confidence was gone.”\n5. IT director, 310-person healthcare services company, $21,000 ARR: “The workshop was valuable, but it happened six weeks after signing. By then the internal champion had moved teams.”\n6. Founder, 40-person ecommerce company, $3,600 ARR: “We moved to a cheaper product. It does less, but it connects to NetSuite without custom work.”\n\nDELIVERABLE\nWrite a board-ready memo in Markdown with these sections:\n1. Executive summary: no more than five bullets.\n2. Q2 churn profile: include a compact table covering account count, ARR lost, quarter-over-quarter change, and segment concentration.\n3. Primary churn drivers: rank the top four drivers and support each with specific metrics and interview evidence.\n4. Interpretation: separate confirmed findings from plausible hypotheses requiring validation.\n5. Recommended actions: provide five prioritized actions, each with an owner, timing, and measurable success indicator. Focus on actions feasible within the next two quarters.\n6. Data gaps: list the most important missing evidence.\n\nUse direct, neutral language. Calculate quarter-over-quarter changes from the supplied figures. Do not claim that workshops, incidents, or integrations caused churn beyond what the evidence supports.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5-nano",
            "settings": {
                "systemPrompt": "You are a senior customer insights analyst. Produce concise, decision-ready business writing grounded only in the supplied evidence. Quantify findings when possible, distinguish facts from hypotheses, and never invent customer statements or metrics.",
                "maxTokens": 3500,
                "thinkingLevel": "low"
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Prepare a standalone Q2 2026 churn analysis memo for the leadership team of Northstar Relay, a B2B workflow automation platform.\n\nACCOUNT DATA\n- 42 customers churned, representing $318,000 in annual recurring revenue.\n- Q1 comparison: 29 customers and $201,000 ARR churned.\n- Churned accounts by segment: SMB 27 accounts / $81,000 ARR; Mid-market 12 / $147,000; Enterprise 3 / $90,000.\n- Stated cancellation reasons: missing integrations 12; low adoption 10; budget reduction 8; reliability 6; switched to competitor 4; company closed 2.\n- Median customer age at cancellation: 7 months, down from 11 months in Q1.\n- 26 of 42 churned accounts had fewer than three active users in the final 30 days.\n- 19 had not launched a production workflow within 45 days of purchase.\n- Accounts completing an implementation workshop had 4.8% quarterly logo churn; accounts that did not had 11.9%.\n- Integration-related churn included Salesforce 5, NetSuite 4, Microsoft Dynamics 2, and Workday 1.\n\nSUPPORT AND PRODUCT SIGNALS\n- Failed workflow support tickets rose 34% quarter over quarter.\n- Median first response time improved from 5.2 hours to 3.1 hours.\n- Six reliability-related cancellations followed incidents affecting scheduled workflows between April 18 and May 9.\n- A NetSuite connector beta began June 20; no retention outcome is available yet.\n\nCUSTOMER INTERVIEW EXCERPTS\n1. Operations director, 180-person logistics company, $18,000 ARR: “The demo looked straightforward, but nobody on our team owned implementation. After two months we were still testing sample workflows.”\n2. RevOps lead, 420-person software company, $24,000 ARR: “We needed Salesforce custom-object support. The workaround created more maintenance than it removed.”\n3. COO, 75-person agency, $6,000 ARR: “We cut every tool that was not used weekly. Only two people ever logged in.”\n4. Finance systems manager, 900-person manufacturer, $36,000 ARR: “Two scheduled approval workflows failed during close. Support responded quickly, but confidence was gone.”\n5. IT director, 310-person healthcare services company, $21,000 ARR: “The workshop was valuable, but it happened six weeks after signing. By then the internal champion had moved teams.”\n6. Founder, 40-person ecommerce company, $3,600 ARR: “We moved to a cheaper product. It does less, but it connects to NetSuite without custom work.”\n\nDELIVERABLE\nWrite a board-ready memo in Markdown with these sections:\n1. Executive summary: no more than five bullets.\n2. Q2 churn profile: include a compact table covering account count, ARR lost, quarter-over-quarter change, and segment concentration.\n3. Primary churn drivers: rank the top four drivers and support each with specific metrics and interview evidence.\n4. Interpretation: separate confirmed findings from plausible hypotheses requiring validation.\n5. Recommended actions: provide five prioritized actions, each with an owner, timing, and measurable success indicator. Focus on actions feasible within the next two quarters.\n6. Data gaps: list the most important missing evidence.\n\nUse direct, neutral language. Calculate quarter-over-quarter changes from the supplied figures. Do not claim that workshops, incidents, or integrations caused churn beyond what the evidence supports."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "a94c7cc6-ae7b-4351-bc8d-0bd04a2bc825",
      "model": "openai:gpt@5-nano",
      "settings": {
        "systemPrompt": "You are a senior customer insights analyst. Produce concise, decision-ready business writing grounded only in the supplied evidence. Quantify findings when possible, distinguish facts from hypotheses, and never invent customer statements or metrics.",
        "maxTokens": 3500,
        "thinkingLevel": "low"
      },
      "messages": [
        {
          "role": "user",
          "content": "Prepare a standalone Q2 2026 churn analysis memo for the leadership team of Northstar Relay, a B2B workflow automation platform.\n\nACCOUNT DATA\n- 42 customers churned, representing $318,000 in annual recurring revenue.\n- Q1 comparison: 29 customers and $201,000 ARR churned.\n- Churned accounts by segment: SMB 27 accounts / $81,000 ARR; Mid-market 12 / $147,000; Enterprise 3 / $90,000.\n- Stated cancellation reasons: missing integrations 12; low adoption 10; budget reduction 8; reliability 6; switched to competitor 4; company closed 2.\n- Median customer age at cancellation: 7 months, down from 11 months in Q1.\n- 26 of 42 churned accounts had fewer than three active users in the final 30 days.\n- 19 had not launched a production workflow within 45 days of purchase.\n- Accounts completing an implementation workshop had 4.8% quarterly logo churn; accounts that did not had 11.9%.\n- Integration-related churn included Salesforce 5, NetSuite 4, Microsoft Dynamics 2, and Workday 1.\n\nSUPPORT AND PRODUCT SIGNALS\n- Failed workflow support tickets rose 34% quarter over quarter.\n- Median first response time improved from 5.2 hours to 3.1 hours.\n- Six reliability-related cancellations followed incidents affecting scheduled workflows between April 18 and May 9.\n- A NetSuite connector beta began June 20; no retention outcome is available yet.\n\nCUSTOMER INTERVIEW EXCERPTS\n1. Operations director, 180-person logistics company, $18,000 ARR: “The demo looked straightforward, but nobody on our team owned implementation. After two months we were still testing sample workflows.”\n2. RevOps lead, 420-person software company, $24,000 ARR: “We needed Salesforce custom-object support. The workaround created more maintenance than it removed.”\n3. COO, 75-person agency, $6,000 ARR: “We cut every tool that was not used weekly. Only two people ever logged in.”\n4. Finance systems manager, 900-person manufacturer, $36,000 ARR: “Two scheduled approval workflows failed during close. Support responded quickly, but confidence was gone.”\n5. IT director, 310-person healthcare services company, $21,000 ARR: “The workshop was valuable, but it happened six weeks after signing. By then the internal champion had moved teams.”\n6. Founder, 40-person ecommerce company, $3,600 ARR: “We moved to a cheaper product. It does less, but it connects to NetSuite without custom work.”\n\nDELIVERABLE\nWrite a board-ready memo in Markdown with these sections:\n1. Executive summary: no more than five bullets.\n2. Q2 churn profile: include a compact table covering account count, ARR lost, quarter-over-quarter change, and segment concentration.\n3. Primary churn drivers: rank the top four drivers and support each with specific metrics and interview evidence.\n4. Interpretation: separate confirmed findings from plausible hypotheses requiring validation.\n5. Recommended actions: provide five prioritized actions, each with an owner, timing, and measurable success indicator. Focus on actions feasible within the next two quarters.\n6. Data gaps: list the most important missing evidence.\n\nUse direct, neutral language. Calculate quarter-over-quarter changes from the supplied figures. Do not claim that workshops, incidents, or integrations caused churn beyond what the evidence supports."
        }
      ]
    }
  ]'

runware run openai:gpt@5-nano \
  settings.systemPrompt="You are a senior customer insights analyst. Produce concise, decision-ready business writing grounded only in the supplied evidence. Quantify findings when possible, distinguish facts from hypotheses, and never invent customer statements or metrics." \
  settings.maxTokens=3500 \
  settings.thinkingLevel=low \
  messages.0.role=user \
  messages.0.content="Prepare a standalone Q2 2026 churn analysis memo for the leadership team of Northstar Relay, a B2B workflow automation platform.

ACCOUNT DATA
- 42 customers churned, representing \$318,000 in annual recurring revenue.
- Q1 comparison: 29 customers and \$201,000 ARR churned.
- Churned accounts by segment: SMB 27 accounts / \$81,000 ARR; Mid-market 12 / \$147,000; Enterprise 3 / \$90,000.
- Stated cancellation reasons: missing integrations 12; low adoption 10; budget reduction 8; reliability 6; switched to competitor 4; company closed 2.
- Median customer age at cancellation: 7 months, down from 11 months in Q1.
- 26 of 42 churned accounts had fewer than three active users in the final 30 days.
- 19 had not launched a production workflow within 45 days of purchase.
- Accounts completing an implementation workshop had 4.8% quarterly logo churn; accounts that did not had 11.9%.
- Integration-related churn included Salesforce 5, NetSuite 4, Microsoft Dynamics 2, and Workday 1.

SUPPORT AND PRODUCT SIGNALS
- Failed workflow support tickets rose 34% quarter over quarter.
- Median first response time improved from 5.2 hours to 3.1 hours.
- Six reliability-related cancellations followed incidents affecting scheduled workflows between April 18 and May 9.
- A NetSuite connector beta began June 20; no retention outcome is available yet.

CUSTOMER INTERVIEW EXCERPTS
1. Operations director, 180-person logistics company, \$18,000 ARR: “The demo looked straightforward, but nobody on our team owned implementation. After two months we were still testing sample workflows.”
2. RevOps lead, 420-person software company, \$24,000 ARR: “We needed Salesforce custom-object support. The workaround created more maintenance than it removed.”
3. COO, 75-person agency, \$6,000 ARR: “We cut every tool that was not used weekly. Only two people ever logged in.”
4. Finance systems manager, 900-person manufacturer, \$36,000 ARR: “Two scheduled approval workflows failed during close. Support responded quickly, but confidence was gone.”
5. IT director, 310-person healthcare services company, \$21,000 ARR: “The workshop was valuable, but it happened six weeks after signing. By then the internal champion had moved teams.”
6. Founder, 40-person ecommerce company, \$3,600 ARR: “We moved to a cheaper product. It does less, but it connects to NetSuite without custom work.”

DELIVERABLE
Write a board-ready memo in Markdown with these sections:
1. Executive summary: no more than five bullets.
2. Q2 churn profile: include a compact table covering account count, ARR lost, quarter-over-quarter change, and segment concentration.
3. Primary churn drivers: rank the top four drivers and support each with specific metrics and interview evidence.
4. Interpretation: separate confirmed findings from plausible hypotheses requiring validation.
5. Recommended actions: provide five prioritized actions, each with an owner, timing, and measurable success indicator. Focus on actions feasible within the next two quarters.
6. Data gaps: list the most important missing evidence.

Use direct, neutral language. Calculate quarter-over-quarter changes from the supplied figures. Do not claim that workshops, incidents, or integrations caused churn beyond what the evidence supports."

{
  "taskType": "textInference",
  "taskUUID": "a94c7cc6-ae7b-4351-bc8d-0bd04a2bc825",
  "model": "openai:gpt@5-nano",
  "settings": {
    "systemPrompt": "You are a senior customer insights analyst. Produce concise, decision-ready business writing grounded only in the supplied evidence. Quantify findings when possible, distinguish facts from hypotheses, and never invent customer statements or metrics.",
    "maxTokens": 3500,
    "thinkingLevel": "low"
  },
  "messages": [
    {
      "role": "user",
      "content": "Prepare a standalone Q2 2026 churn analysis memo for the leadership team of Northstar Relay, a B2B workflow automation platform.\n\nACCOUNT DATA\n- 42 customers churned, representing $318,000 in annual recurring revenue.\n- Q1 comparison: 29 customers and $201,000 ARR churned.\n- Churned accounts by segment: SMB 27 accounts / $81,000 ARR; Mid-market 12 / $147,000; Enterprise 3 / $90,000.\n- Stated cancellation reasons: missing integrations 12; low adoption 10; budget reduction 8; reliability 6; switched to competitor 4; company closed 2.\n- Median customer age at cancellation: 7 months, down from 11 months in Q1.\n- 26 of 42 churned accounts had fewer than three active users in the final 30 days.\n- 19 had not launched a production workflow within 45 days of purchase.\n- Accounts completing an implementation workshop had 4.8% quarterly logo churn; accounts that did not had 11.9%.\n- Integration-related churn included Salesforce 5, NetSuite 4, Microsoft Dynamics 2, and Workday 1.\n\nSUPPORT AND PRODUCT SIGNALS\n- Failed workflow support tickets rose 34% quarter over quarter.\n- Median first response time improved from 5.2 hours to 3.1 hours.\n- Six reliability-related cancellations followed incidents affecting scheduled workflows between April 18 and May 9.\n- A NetSuite connector beta began June 20; no retention outcome is available yet.\n\nCUSTOMER INTERVIEW EXCERPTS\n1. Operations director, 180-person logistics company, $18,000 ARR: “The demo looked straightforward, but nobody on our team owned implementation. After two months we were still testing sample workflows.”\n2. RevOps lead, 420-person software company, $24,000 ARR: “We needed Salesforce custom-object support. The workaround created more maintenance than it removed.”\n3. COO, 75-person agency, $6,000 ARR: “We cut every tool that was not used weekly. Only two people ever logged in.”\n4. Finance systems manager, 900-person manufacturer, $36,000 ARR: “Two scheduled approval workflows failed during close. Support responded quickly, but confidence was gone.”\n5. IT director, 310-person healthcare services company, $21,000 ARR: “The workshop was valuable, but it happened six weeks after signing. By then the internal champion had moved teams.”\n6. Founder, 40-person ecommerce company, $3,600 ARR: “We moved to a cheaper product. It does less, but it connects to NetSuite without custom work.”\n\nDELIVERABLE\nWrite a board-ready memo in Markdown with these sections:\n1. Executive summary: no more than five bullets.\n2. Q2 churn profile: include a compact table covering account count, ARR lost, quarter-over-quarter change, and segment concentration.\n3. Primary churn drivers: rank the top four drivers and support each with specific metrics and interview evidence.\n4. Interpretation: separate confirmed findings from plausible hypotheses requiring validation.\n5. Recommended actions: provide five prioritized actions, each with an owner, timing, and measurable success indicator. Focus on actions feasible within the next two quarters.\n6. Data gaps: list the most important missing evidence.\n\nUse direct, neutral language. Calculate quarter-over-quarter changes from the supplied figures. Do not claim that workshops, incidents, or integrations caused churn beyond what the evidence supports."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5-nano',
  settings: {
    thinkingLevel: 'medium',
    maxTokens: 2000
  },
  messages: [
    {
      role: 'user',
      content: 'Draft a persuasive 400–500 word executive summary for Riverbend Community Health’s grant application to the Brightwell County Health Equity Fund. The request is $185,000 for a 12-month expansion of its mobile dental clinic.\n\nUse only the facts below:\n\nRiverbend Community Health is a nonprofit federally qualified health center serving three rural counties. Its mobile dental unit currently visits six elementary schools and two senior centers. During the last completed program year, the unit provided 1,840 patient visits; 71% of patients were uninsured or covered by Medicaid. Average appointment wait time at Riverbend’s fixed dental clinic is nine weeks. Transportation is the most frequently reported barrier to care in Riverbend’s annual patient survey.\n\nThe proposed expansion will add two weekly service days and four new stops: two schools, a food pantry, and a farmworker resource center. Grant funds will support a 0.8 FTE dental hygienist, a part-time driver and patient navigator, portable X-ray equipment, clinical supplies, fuel, and interpretation services in Spanish and Mixteco.\n\nDuring the grant period, Riverbend plans to deliver 1,200 additional visits to at least 750 unique patients. Services will include screenings, cleanings, fluoride treatments, sealants, X-rays, simple restorations, referrals, and help enrolling eligible patients in Medicaid. Riverbend will track visits, unique patients, completed treatment plans, referral completion, insurance enrollment, patient demographics, and satisfaction. Its target is for 65% of patients with identified treatment needs to complete a treatment plan or specialist referral within six months.\n\nThe fund prioritizes improved access, measurable outcomes, culturally responsive care, and plans that can continue after grant funding. Riverbend expects ongoing costs to be supported through Medicaid reimbursement, sliding-fee revenue, and integration of the expanded route into its operating budget. It also plans referral partnerships with two local dental practices for cases beyond the mobile unit’s scope.\n\nWrite for a foundation review committee. Open with the community need and funding request, connect the activities directly to measurable outcomes, and close with the sustainability case. Keep the tone credible, specific, and urgent without exaggeration. Use a short heading followed by cohesive prose, not bullets. Do not invent quotations, statistics, partners, awards, or patient stories. Return only the finished executive summary.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5-nano",
            "settings": {
                "thinkingLevel": "medium",
                "maxTokens": 2000
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Draft a persuasive 400–500 word executive summary for Riverbend Community Health’s grant application to the Brightwell County Health Equity Fund. The request is $185,000 for a 12-month expansion of its mobile dental clinic.\n\nUse only the facts below:\n\nRiverbend Community Health is a nonprofit federally qualified health center serving three rural counties. Its mobile dental unit currently visits six elementary schools and two senior centers. During the last completed program year, the unit provided 1,840 patient visits; 71% of patients were uninsured or covered by Medicaid. Average appointment wait time at Riverbend’s fixed dental clinic is nine weeks. Transportation is the most frequently reported barrier to care in Riverbend’s annual patient survey.\n\nThe proposed expansion will add two weekly service days and four new stops: two schools, a food pantry, and a farmworker resource center. Grant funds will support a 0.8 FTE dental hygienist, a part-time driver and patient navigator, portable X-ray equipment, clinical supplies, fuel, and interpretation services in Spanish and Mixteco.\n\nDuring the grant period, Riverbend plans to deliver 1,200 additional visits to at least 750 unique patients. Services will include screenings, cleanings, fluoride treatments, sealants, X-rays, simple restorations, referrals, and help enrolling eligible patients in Medicaid. Riverbend will track visits, unique patients, completed treatment plans, referral completion, insurance enrollment, patient demographics, and satisfaction. Its target is for 65% of patients with identified treatment needs to complete a treatment plan or specialist referral within six months.\n\nThe fund prioritizes improved access, measurable outcomes, culturally responsive care, and plans that can continue after grant funding. Riverbend expects ongoing costs to be supported through Medicaid reimbursement, sliding-fee revenue, and integration of the expanded route into its operating budget. It also plans referral partnerships with two local dental practices for cases beyond the mobile unit’s scope.\n\nWrite for a foundation review committee. Open with the community need and funding request, connect the activities directly to measurable outcomes, and close with the sustainability case. Keep the tone credible, specific, and urgent without exaggeration. Use a short heading followed by cohesive prose, not bullets. Do not invent quotations, statistics, partners, awards, or patient stories. Return only the finished executive summary."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "86ed748e-0b76-4695-807e-b68909d77b27",
      "model": "openai:gpt@5-nano",
      "settings": {
        "thinkingLevel": "medium",
        "maxTokens": 2000
      },
      "messages": [
        {
          "role": "user",
          "content": "Draft a persuasive 400–500 word executive summary for Riverbend Community Health’s grant application to the Brightwell County Health Equity Fund. The request is $185,000 for a 12-month expansion of its mobile dental clinic.\n\nUse only the facts below:\n\nRiverbend Community Health is a nonprofit federally qualified health center serving three rural counties. Its mobile dental unit currently visits six elementary schools and two senior centers. During the last completed program year, the unit provided 1,840 patient visits; 71% of patients were uninsured or covered by Medicaid. Average appointment wait time at Riverbend’s fixed dental clinic is nine weeks. Transportation is the most frequently reported barrier to care in Riverbend’s annual patient survey.\n\nThe proposed expansion will add two weekly service days and four new stops: two schools, a food pantry, and a farmworker resource center. Grant funds will support a 0.8 FTE dental hygienist, a part-time driver and patient navigator, portable X-ray equipment, clinical supplies, fuel, and interpretation services in Spanish and Mixteco.\n\nDuring the grant period, Riverbend plans to deliver 1,200 additional visits to at least 750 unique patients. Services will include screenings, cleanings, fluoride treatments, sealants, X-rays, simple restorations, referrals, and help enrolling eligible patients in Medicaid. Riverbend will track visits, unique patients, completed treatment plans, referral completion, insurance enrollment, patient demographics, and satisfaction. Its target is for 65% of patients with identified treatment needs to complete a treatment plan or specialist referral within six months.\n\nThe fund prioritizes improved access, measurable outcomes, culturally responsive care, and plans that can continue after grant funding. Riverbend expects ongoing costs to be supported through Medicaid reimbursement, sliding-fee revenue, and integration of the expanded route into its operating budget. It also plans referral partnerships with two local dental practices for cases beyond the mobile unit’s scope.\n\nWrite for a foundation review committee. Open with the community need and funding request, connect the activities directly to measurable outcomes, and close with the sustainability case. Keep the tone credible, specific, and urgent without exaggeration. Use a short heading followed by cohesive prose, not bullets. Do not invent quotations, statistics, partners, awards, or patient stories. Return only the finished executive summary."
        }
      ]
    }
  ]'

runware run openai:gpt@5-nano \
  settings.thinkingLevel=medium \
  settings.maxTokens=2000 \
  messages.0.role=user \
  messages.0.content="Draft a persuasive 400–500 word executive summary for Riverbend Community Health’s grant application to the Brightwell County Health Equity Fund. The request is \$185,000 for a 12-month expansion of its mobile dental clinic.

Use only the facts below:

Riverbend Community Health is a nonprofit federally qualified health center serving three rural counties. Its mobile dental unit currently visits six elementary schools and two senior centers. During the last completed program year, the unit provided 1,840 patient visits; 71% of patients were uninsured or covered by Medicaid. Average appointment wait time at Riverbend’s fixed dental clinic is nine weeks. Transportation is the most frequently reported barrier to care in Riverbend’s annual patient survey.

The proposed expansion will add two weekly service days and four new stops: two schools, a food pantry, and a farmworker resource center. Grant funds will support a 0.8 FTE dental hygienist, a part-time driver and patient navigator, portable X-ray equipment, clinical supplies, fuel, and interpretation services in Spanish and Mixteco.

During the grant period, Riverbend plans to deliver 1,200 additional visits to at least 750 unique patients. Services will include screenings, cleanings, fluoride treatments, sealants, X-rays, simple restorations, referrals, and help enrolling eligible patients in Medicaid. Riverbend will track visits, unique patients, completed treatment plans, referral completion, insurance enrollment, patient demographics, and satisfaction. Its target is for 65% of patients with identified treatment needs to complete a treatment plan or specialist referral within six months.

The fund prioritizes improved access, measurable outcomes, culturally responsive care, and plans that can continue after grant funding. Riverbend expects ongoing costs to be supported through Medicaid reimbursement, sliding-fee revenue, and integration of the expanded route into its operating budget. It also plans referral partnerships with two local dental practices for cases beyond the mobile unit’s scope.

Write for a foundation review committee. Open with the community need and funding request, connect the activities directly to measurable outcomes, and close with the sustainability case. Keep the tone credible, specific, and urgent without exaggeration. Use a short heading followed by cohesive prose, not bullets. Do not invent quotations, statistics, partners, awards, or patient stories. Return only the finished executive summary."

{
  "taskType": "textInference",
  "taskUUID": "86ed748e-0b76-4695-807e-b68909d77b27",
  "model": "openai:gpt@5-nano",
  "settings": {
    "thinkingLevel": "medium",
    "maxTokens": 2000
  },
  "messages": [
    {
      "role": "user",
      "content": "Draft a persuasive 400–500 word executive summary for Riverbend Community Health’s grant application to the Brightwell County Health Equity Fund. The request is $185,000 for a 12-month expansion of its mobile dental clinic.\n\nUse only the facts below:\n\nRiverbend Community Health is a nonprofit federally qualified health center serving three rural counties. Its mobile dental unit currently visits six elementary schools and two senior centers. During the last completed program year, the unit provided 1,840 patient visits; 71% of patients were uninsured or covered by Medicaid. Average appointment wait time at Riverbend’s fixed dental clinic is nine weeks. Transportation is the most frequently reported barrier to care in Riverbend’s annual patient survey.\n\nThe proposed expansion will add two weekly service days and four new stops: two schools, a food pantry, and a farmworker resource center. Grant funds will support a 0.8 FTE dental hygienist, a part-time driver and patient navigator, portable X-ray equipment, clinical supplies, fuel, and interpretation services in Spanish and Mixteco.\n\nDuring the grant period, Riverbend plans to deliver 1,200 additional visits to at least 750 unique patients. Services will include screenings, cleanings, fluoride treatments, sealants, X-rays, simple restorations, referrals, and help enrolling eligible patients in Medicaid. Riverbend will track visits, unique patients, completed treatment plans, referral completion, insurance enrollment, patient demographics, and satisfaction. Its target is for 65% of patients with identified treatment needs to complete a treatment plan or specialist referral within six months.\n\nThe fund prioritizes improved access, measurable outcomes, culturally responsive care, and plans that can continue after grant funding. Riverbend expects ongoing costs to be supported through Medicaid reimbursement, sliding-fee revenue, and integration of the expanded route into its operating budget. It also plans referral partnerships with two local dental practices for cases beyond the mobile unit’s scope.\n\nWrite for a foundation review committee. Open with the community need and funding request, connect the activities directly to measurable outcomes, and close with the sustainability case. Keep the tone credible, specific, and urgent without exaggeration. Use a short heading followed by cohesive prose, not bullets. Do not invent quotations, statistics, partners, awards, or patient stories. Return only the finished executive summary."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5-nano',
  settings: {
    systemPrompt: 'You are a meticulous auction-house catalog specialist. Produce commercially usable catalog copy grounded only in the supplied image and explicitly provided facts. Never convert uncertain visual impressions into unsupported claims.',
    maxTokens: 700,
    thinkingLevel: 'low'
  },
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/04b85de8-9034-40ea-abb3-cb2a2a8261ec.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Prepare a publication-ready auction catalog entry for the furniture shown in the attached intake photograph. Use these headings: LOT TITLE, CATALOG DESCRIPTION, VISIBLE CONDITION, and SEARCH KEYWORDS. Write for a reputable regional auction house in a concise, informed, neutral tone. Describe the form, materials, construction clues, hardware, finish, proportions, decorative details, and visible wear. Distinguish direct visual observations from cautious inferences. Do not invent a maker, date, dimensions, provenance, restoration history, wood species, or geographic origin; if uncertain, use qualified language such as “appears to be” or “in the style of.” The lot title should be specific and no longer than 12 words. The catalog description should be 90–130 words, the condition section 50–80 words, and the search keywords should be a single comma-separated line.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5-nano",
            "settings": {
                "systemPrompt": "You are a meticulous auction-house catalog specialist. Produce commercially usable catalog copy grounded only in the supplied image and explicitly provided facts. Never convert uncertain visual impressions into unsupported claims.",
                "maxTokens": 700,
                "thinkingLevel": "low"
            },
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/04b85de8-9034-40ea-abb3-cb2a2a8261ec.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Prepare a publication-ready auction catalog entry for the furniture shown in the attached intake photograph. Use these headings: LOT TITLE, CATALOG DESCRIPTION, VISIBLE CONDITION, and SEARCH KEYWORDS. Write for a reputable regional auction house in a concise, informed, neutral tone. Describe the form, materials, construction clues, hardware, finish, proportions, decorative details, and visible wear. Distinguish direct visual observations from cautious inferences. Do not invent a maker, date, dimensions, provenance, restoration history, wood species, or geographic origin; if uncertain, use qualified language such as “appears to be” or “in the style of.” The lot title should be specific and no longer than 12 words. The catalog description should be 90–130 words, the condition section 50–80 words, and the search keywords should be a single comma-separated line."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "c6dd806f-90e6-49a7-a489-a44e6f365e19",
      "model": "openai:gpt@5-nano",
      "settings": {
        "systemPrompt": "You are a meticulous auction-house catalog specialist. Produce commercially usable catalog copy grounded only in the supplied image and explicitly provided facts. Never convert uncertain visual impressions into unsupported claims.",
        "maxTokens": 700,
        "thinkingLevel": "low"
      },
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/04b85de8-9034-40ea-abb3-cb2a2a8261ec.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Prepare a publication-ready auction catalog entry for the furniture shown in the attached intake photograph. Use these headings: LOT TITLE, CATALOG DESCRIPTION, VISIBLE CONDITION, and SEARCH KEYWORDS. Write for a reputable regional auction house in a concise, informed, neutral tone. Describe the form, materials, construction clues, hardware, finish, proportions, decorative details, and visible wear. Distinguish direct visual observations from cautious inferences. Do not invent a maker, date, dimensions, provenance, restoration history, wood species, or geographic origin; if uncertain, use qualified language such as “appears to be” or “in the style of.” The lot title should be specific and no longer than 12 words. The catalog description should be 90–130 words, the condition section 50–80 words, and the search keywords should be a single comma-separated line."
        }
      ]
    }
  ]'

runware run openai:gpt@5-nano \
  settings.systemPrompt="You are a meticulous auction-house catalog specialist. Produce commercially usable catalog copy grounded only in the supplied image and explicitly provided facts. Never convert uncertain visual impressions into unsupported claims." \
  settings.maxTokens=700 \
  settings.thinkingLevel=low \
  inputs.images.0=https://assets.runware.ai/assets/inputs/04b85de8-9034-40ea-abb3-cb2a2a8261ec.jpg \
  messages.0.role=user \
  messages.0.content="Prepare a publication-ready auction catalog entry for the furniture shown in the attached intake photograph. Use these headings: LOT TITLE, CATALOG DESCRIPTION, VISIBLE CONDITION, and SEARCH KEYWORDS. Write for a reputable regional auction house in a concise, informed, neutral tone. Describe the form, materials, construction clues, hardware, finish, proportions, decorative details, and visible wear. Distinguish direct visual observations from cautious inferences. Do not invent a maker, date, dimensions, provenance, restoration history, wood species, or geographic origin; if uncertain, use qualified language such as “appears to be” or “in the style of.” The lot title should be specific and no longer than 12 words. The catalog description should be 90–130 words, the condition section 50–80 words, and the search keywords should be a single comma-separated line."

{
  "taskType": "textInference",
  "taskUUID": "c6dd806f-90e6-49a7-a489-a44e6f365e19",
  "model": "openai:gpt@5-nano",
  "settings": {
    "systemPrompt": "You are a meticulous auction-house catalog specialist. Produce commercially usable catalog copy grounded only in the supplied image and explicitly provided facts. Never convert uncertain visual impressions into unsupported claims.",
    "maxTokens": 700,
    "thinkingLevel": "low"
  },
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/04b85de8-9034-40ea-abb3-cb2a2a8261ec.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Prepare a publication-ready auction catalog entry for the furniture shown in the attached intake photograph. Use these headings: LOT TITLE, CATALOG DESCRIPTION, VISIBLE CONDITION, and SEARCH KEYWORDS. Write for a reputable regional auction house in a concise, informed, neutral tone. Describe the form, materials, construction clues, hardware, finish, proportions, decorative details, and visible wear. Distinguish direct visual observations from cautious inferences. Do not invent a maker, date, dimensions, provenance, restoration history, wood species, or geographic origin; if uncertain, use qualified language such as “appears to be” or “in the style of.” The lot title should be specific and no longer than 12 words. The catalog description should be 90–130 words, the condition section 50–80 words, and the search keywords should be a single comma-separated line."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5-nano',
  settings: {
    thinkingLevel: 'low',
    maxTokens: 1200
  },
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/93fa934f-d591-4226-b030-c24cbf52b936.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Inspect the attached retail-shelf photo and write a concise field merchandising audit in plain text with clear headings. Document only what is visibly supported. Include: an overview of the display; observable stockouts or low-stock areas with shelf location; approximate facings by visible product or variant where distinguishable; misplaced, rotated, damaged, or poorly aligned items; visible shelf-edge prices and promotional tags; cleanliness or maintenance issues; and prioritized corrective actions. Distinguish confirmed observations from anything uncertain. If a label, price, brand, or product variant is unreadable, say so rather than guessing. Do not claim planogram noncompliance because no reference planogram is provided.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5-nano",
            "settings": {
                "thinkingLevel": "low",
                "maxTokens": 1200
            },
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/93fa934f-d591-4226-b030-c24cbf52b936.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Inspect the attached retail-shelf photo and write a concise field merchandising audit in plain text with clear headings. Document only what is visibly supported. Include: an overview of the display; observable stockouts or low-stock areas with shelf location; approximate facings by visible product or variant where distinguishable; misplaced, rotated, damaged, or poorly aligned items; visible shelf-edge prices and promotional tags; cleanliness or maintenance issues; and prioritized corrective actions. Distinguish confirmed observations from anything uncertain. If a label, price, brand, or product variant is unreadable, say so rather than guessing. Do not claim planogram noncompliance because no reference planogram is provided."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "f3b80ab0-b7fe-48cd-bd0a-b13d6225a723",
      "model": "openai:gpt@5-nano",
      "settings": {
        "thinkingLevel": "low",
        "maxTokens": 1200
      },
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/93fa934f-d591-4226-b030-c24cbf52b936.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Inspect the attached retail-shelf photo and write a concise field merchandising audit in plain text with clear headings. Document only what is visibly supported. Include: an overview of the display; observable stockouts or low-stock areas with shelf location; approximate facings by visible product or variant where distinguishable; misplaced, rotated, damaged, or poorly aligned items; visible shelf-edge prices and promotional tags; cleanliness or maintenance issues; and prioritized corrective actions. Distinguish confirmed observations from anything uncertain. If a label, price, brand, or product variant is unreadable, say so rather than guessing. Do not claim planogram noncompliance because no reference planogram is provided."
        }
      ]
    }
  ]'

runware run openai:gpt@5-nano \
  settings.thinkingLevel=low \
  settings.maxTokens=1200 \
  inputs.images.0=https://assets.runware.ai/assets/inputs/93fa934f-d591-4226-b030-c24cbf52b936.jpg \
  messages.0.role=user \
  messages.0.content="Inspect the attached retail-shelf photo and write a concise field merchandising audit in plain text with clear headings. Document only what is visibly supported. Include: an overview of the display; observable stockouts or low-stock areas with shelf location; approximate facings by visible product or variant where distinguishable; misplaced, rotated, damaged, or poorly aligned items; visible shelf-edge prices and promotional tags; cleanliness or maintenance issues; and prioritized corrective actions. Distinguish confirmed observations from anything uncertain. If a label, price, brand, or product variant is unreadable, say so rather than guessing. Do not claim planogram noncompliance because no reference planogram is provided."

{
  "taskType": "textInference",
  "taskUUID": "f3b80ab0-b7fe-48cd-bd0a-b13d6225a723",
  "model": "openai:gpt@5-nano",
  "settings": {
    "thinkingLevel": "low",
    "maxTokens": 1200
  },
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/93fa934f-d591-4226-b030-c24cbf52b936.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Inspect the attached retail-shelf photo and write a concise field merchandising audit in plain text with clear headings. Document only what is visibly supported. Include: an overview of the display; observable stockouts or low-stock areas with shelf location; approximate facings by visible product or variant where distinguishable; misplaced, rotated, damaged, or poorly aligned items; visible shelf-edge prices and promotional tags; cleanliness or maintenance issues; and prioritized corrective actions. Distinguish confirmed observations from anything uncertain. If a label, price, brand, or product variant is unreadable, say so rather than guessing. Do not claim planogram noncompliance because no reference planogram is provided."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5-nano',
  settings: {
    systemPrompt: 'You are a podcast editorial producer. Turn source transcripts into accurate, engaging release materials without inventing facts, quotes, timestamps, or credentials. Preserve scientific nuance, explain technical terms plainly, and distinguish preliminary findings from established evidence. Return clean, publication-ready copy with the requested headings.',
    maxTokens: 2200,
    thinkingLevel: 'low'
  },
  messages: [
    {
      role: 'user',
      content: 'Create the launch kit for an episode of Signal & Soil, a practical climate-science podcast for informed general audiences.\n\nDELIVERABLES\n1. Five episode-title options, each under 65 characters and free of clickbait.\n2. A 90–120 word episode summary.\n3. Six chapter titles paired with the approximate timestamps supplied in the transcript.\n4. Three key takeaways, each one sentence.\n5. A LinkedIn post of 100–140 words for the podcast account.\n6. Two social captions under 220 characters each: one curious, one pragmatic.\n7. A factual accuracy note listing any claims the editor should verify before publication.\n\nSTYLE\nClear, intelligent, warm, and grounded. Emphasize practical implications for farmers and food systems. Do not imply that biochar is a universal solution. Use only information in the transcript. Paraphrase rather than fabricating direct quotes.\n\nSOURCE TRANSCRIPT\n[00:00] HOST MAYA CHEN: Today we are asking whether biochar can help farms hold more water while storing carbon. Our guest is Dr. Lena Ortiz, a soil biogeochemist at Great Plains State University. Her team has completed the second growing season of a three-year field trial in western Kansas.\n\n[02:10] ORTIZ: Biochar is a carbon-rich material made by heating crop residues in a low-oxygen chamber. The process is called pyrolysis. The properties of the final material depend heavily on the feedstock and temperature, so biochar is not one uniform product.\n\n[05:35] ORTIZ: In our trial, we incorporated locally produced wheat-straw biochar into 24 dryland sorghum plots. We are comparing two application rates with untreated control plots. These are interim observations, not final results.\n\n[08:20] ORTIZ: During the first season, soil moisture in the upper 20 centimeters was modestly higher in the amended plots after light rain. We did not see a statistically significant yield difference. In the second season, a severe heat wave complicated interpretation, and the laboratory analysis is still underway.\n\n[12:45] HOST: Farmers often ask about cost. ORTIZ: That is currently the largest barrier. The biochar itself, transport, and field application can be expensive. It makes more sense to investigate regional systems using nearby residues than to haul bulky material long distances.\n\n[16:30] ORTIZ: People sometimes describe biochar as permanent carbon storage. That is too simple. A resistant fraction can remain in soil for a long time, but persistence varies with production conditions, soil type, and climate. Our project is measuring changes over three years; it cannot directly prove century-scale storage.\n\n[20:05] HOST: Are there risks? ORTIZ: Poorly characterized material may contain contaminants or alter soil pH in unhelpful ways. Producers should request an analysis of the material and begin with small trials. Biochar also should not replace erosion control, crop rotation, or careful nutrient management.\n\n[24:15] ORTIZ: The most promising model may connect waste management with soil improvement. A cooperative could convert clean local residues, use process heat, test every batch, and apply the material nearby. But the economics and emissions of the entire system need to be counted.\n\n[28:40] HOST: What should listeners remember? ORTIZ: Biochar is a tool with interesting potential, not a shortcut. Match the material to the soil, verify quality, and look at the full system from residue source to field performance.\n\n[30:10] END'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5-nano",
            "settings": {
                "systemPrompt": "You are a podcast editorial producer. Turn source transcripts into accurate, engaging release materials without inventing facts, quotes, timestamps, or credentials. Preserve scientific nuance, explain technical terms plainly, and distinguish preliminary findings from established evidence. Return clean, publication-ready copy with the requested headings.",
                "maxTokens": 2200,
                "thinkingLevel": "low"
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Create the launch kit for an episode of Signal & Soil, a practical climate-science podcast for informed general audiences.\n\nDELIVERABLES\n1. Five episode-title options, each under 65 characters and free of clickbait.\n2. A 90–120 word episode summary.\n3. Six chapter titles paired with the approximate timestamps supplied in the transcript.\n4. Three key takeaways, each one sentence.\n5. A LinkedIn post of 100–140 words for the podcast account.\n6. Two social captions under 220 characters each: one curious, one pragmatic.\n7. A factual accuracy note listing any claims the editor should verify before publication.\n\nSTYLE\nClear, intelligent, warm, and grounded. Emphasize practical implications for farmers and food systems. Do not imply that biochar is a universal solution. Use only information in the transcript. Paraphrase rather than fabricating direct quotes.\n\nSOURCE TRANSCRIPT\n[00:00] HOST MAYA CHEN: Today we are asking whether biochar can help farms hold more water while storing carbon. Our guest is Dr. Lena Ortiz, a soil biogeochemist at Great Plains State University. Her team has completed the second growing season of a three-year field trial in western Kansas.\n\n[02:10] ORTIZ: Biochar is a carbon-rich material made by heating crop residues in a low-oxygen chamber. The process is called pyrolysis. The properties of the final material depend heavily on the feedstock and temperature, so biochar is not one uniform product.\n\n[05:35] ORTIZ: In our trial, we incorporated locally produced wheat-straw biochar into 24 dryland sorghum plots. We are comparing two application rates with untreated control plots. These are interim observations, not final results.\n\n[08:20] ORTIZ: During the first season, soil moisture in the upper 20 centimeters was modestly higher in the amended plots after light rain. We did not see a statistically significant yield difference. In the second season, a severe heat wave complicated interpretation, and the laboratory analysis is still underway.\n\n[12:45] HOST: Farmers often ask about cost. ORTIZ: That is currently the largest barrier. The biochar itself, transport, and field application can be expensive. It makes more sense to investigate regional systems using nearby residues than to haul bulky material long distances.\n\n[16:30] ORTIZ: People sometimes describe biochar as permanent carbon storage. That is too simple. A resistant fraction can remain in soil for a long time, but persistence varies with production conditions, soil type, and climate. Our project is measuring changes over three years; it cannot directly prove century-scale storage.\n\n[20:05] HOST: Are there risks? ORTIZ: Poorly characterized material may contain contaminants or alter soil pH in unhelpful ways. Producers should request an analysis of the material and begin with small trials. Biochar also should not replace erosion control, crop rotation, or careful nutrient management.\n\n[24:15] ORTIZ: The most promising model may connect waste management with soil improvement. A cooperative could convert clean local residues, use process heat, test every batch, and apply the material nearby. But the economics and emissions of the entire system need to be counted.\n\n[28:40] HOST: What should listeners remember? ORTIZ: Biochar is a tool with interesting potential, not a shortcut. Match the material to the soil, verify quality, and look at the full system from residue source to field performance.\n\n[30:10] END"
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "fb733ee2-f10b-48a6-a9f2-69e8682777e9",
      "model": "openai:gpt@5-nano",
      "settings": {
        "systemPrompt": "You are a podcast editorial producer. Turn source transcripts into accurate, engaging release materials without inventing facts, quotes, timestamps, or credentials. Preserve scientific nuance, explain technical terms plainly, and distinguish preliminary findings from established evidence. Return clean, publication-ready copy with the requested headings.",
        "maxTokens": 2200,
        "thinkingLevel": "low"
      },
      "messages": [
        {
          "role": "user",
          "content": "Create the launch kit for an episode of Signal & Soil, a practical climate-science podcast for informed general audiences.\n\nDELIVERABLES\n1. Five episode-title options, each under 65 characters and free of clickbait.\n2. A 90–120 word episode summary.\n3. Six chapter titles paired with the approximate timestamps supplied in the transcript.\n4. Three key takeaways, each one sentence.\n5. A LinkedIn post of 100–140 words for the podcast account.\n6. Two social captions under 220 characters each: one curious, one pragmatic.\n7. A factual accuracy note listing any claims the editor should verify before publication.\n\nSTYLE\nClear, intelligent, warm, and grounded. Emphasize practical implications for farmers and food systems. Do not imply that biochar is a universal solution. Use only information in the transcript. Paraphrase rather than fabricating direct quotes.\n\nSOURCE TRANSCRIPT\n[00:00] HOST MAYA CHEN: Today we are asking whether biochar can help farms hold more water while storing carbon. Our guest is Dr. Lena Ortiz, a soil biogeochemist at Great Plains State University. Her team has completed the second growing season of a three-year field trial in western Kansas.\n\n[02:10] ORTIZ: Biochar is a carbon-rich material made by heating crop residues in a low-oxygen chamber. The process is called pyrolysis. The properties of the final material depend heavily on the feedstock and temperature, so biochar is not one uniform product.\n\n[05:35] ORTIZ: In our trial, we incorporated locally produced wheat-straw biochar into 24 dryland sorghum plots. We are comparing two application rates with untreated control plots. These are interim observations, not final results.\n\n[08:20] ORTIZ: During the first season, soil moisture in the upper 20 centimeters was modestly higher in the amended plots after light rain. We did not see a statistically significant yield difference. In the second season, a severe heat wave complicated interpretation, and the laboratory analysis is still underway.\n\n[12:45] HOST: Farmers often ask about cost. ORTIZ: That is currently the largest barrier. The biochar itself, transport, and field application can be expensive. It makes more sense to investigate regional systems using nearby residues than to haul bulky material long distances.\n\n[16:30] ORTIZ: People sometimes describe biochar as permanent carbon storage. That is too simple. A resistant fraction can remain in soil for a long time, but persistence varies with production conditions, soil type, and climate. Our project is measuring changes over three years; it cannot directly prove century-scale storage.\n\n[20:05] HOST: Are there risks? ORTIZ: Poorly characterized material may contain contaminants or alter soil pH in unhelpful ways. Producers should request an analysis of the material and begin with small trials. Biochar also should not replace erosion control, crop rotation, or careful nutrient management.\n\n[24:15] ORTIZ: The most promising model may connect waste management with soil improvement. A cooperative could convert clean local residues, use process heat, test every batch, and apply the material nearby. But the economics and emissions of the entire system need to be counted.\n\n[28:40] HOST: What should listeners remember? ORTIZ: Biochar is a tool with interesting potential, not a shortcut. Match the material to the soil, verify quality, and look at the full system from residue source to field performance.\n\n[30:10] END"
        }
      ]
    }
  ]'

runware run openai:gpt@5-nano \
  settings.systemPrompt="You are a podcast editorial producer. Turn source transcripts into accurate, engaging release materials without inventing facts, quotes, timestamps, or credentials. Preserve scientific nuance, explain technical terms plainly, and distinguish preliminary findings from established evidence. Return clean, publication-ready copy with the requested headings." \
  settings.maxTokens=2200 \
  settings.thinkingLevel=low \
  messages.0.role=user \
  messages.0.content="Create the launch kit for an episode of Signal & Soil, a practical climate-science podcast for informed general audiences.

DELIVERABLES
1. Five episode-title options, each under 65 characters and free of clickbait.
2. A 90–120 word episode summary.
3. Six chapter titles paired with the approximate timestamps supplied in the transcript.
4. Three key takeaways, each one sentence.
5. A LinkedIn post of 100–140 words for the podcast account.
6. Two social captions under 220 characters each: one curious, one pragmatic.
7. A factual accuracy note listing any claims the editor should verify before publication.

STYLE
Clear, intelligent, warm, and grounded. Emphasize practical implications for farmers and food systems. Do not imply that biochar is a universal solution. Use only information in the transcript. Paraphrase rather than fabricating direct quotes.

SOURCE TRANSCRIPT
[00:00] HOST MAYA CHEN: Today we are asking whether biochar can help farms hold more water while storing carbon. Our guest is Dr. Lena Ortiz, a soil biogeochemist at Great Plains State University. Her team has completed the second growing season of a three-year field trial in western Kansas.

[02:10] ORTIZ: Biochar is a carbon-rich material made by heating crop residues in a low-oxygen chamber. The process is called pyrolysis. The properties of the final material depend heavily on the feedstock and temperature, so biochar is not one uniform product.

[05:35] ORTIZ: In our trial, we incorporated locally produced wheat-straw biochar into 24 dryland sorghum plots. We are comparing two application rates with untreated control plots. These are interim observations, not final results.

[08:20] ORTIZ: During the first season, soil moisture in the upper 20 centimeters was modestly higher in the amended plots after light rain. We did not see a statistically significant yield difference. In the second season, a severe heat wave complicated interpretation, and the laboratory analysis is still underway.

[12:45] HOST: Farmers often ask about cost. ORTIZ: That is currently the largest barrier. The biochar itself, transport, and field application can be expensive. It makes more sense to investigate regional systems using nearby residues than to haul bulky material long distances.

[16:30] ORTIZ: People sometimes describe biochar as permanent carbon storage. That is too simple. A resistant fraction can remain in soil for a long time, but persistence varies with production conditions, soil type, and climate. Our project is measuring changes over three years; it cannot directly prove century-scale storage.

[20:05] HOST: Are there risks? ORTIZ: Poorly characterized material may contain contaminants or alter soil pH in unhelpful ways. Producers should request an analysis of the material and begin with small trials. Biochar also should not replace erosion control, crop rotation, or careful nutrient management.

[24:15] ORTIZ: The most promising model may connect waste management with soil improvement. A cooperative could convert clean local residues, use process heat, test every batch, and apply the material nearby. But the economics and emissions of the entire system need to be counted.

[28:40] HOST: What should listeners remember? ORTIZ: Biochar is a tool with interesting potential, not a shortcut. Match the material to the soil, verify quality, and look at the full system from residue source to field performance.

[30:10] END"

{
  "taskType": "textInference",
  "taskUUID": "fb733ee2-f10b-48a6-a9f2-69e8682777e9",
  "model": "openai:gpt@5-nano",
  "settings": {
    "systemPrompt": "You are a podcast editorial producer. Turn source transcripts into accurate, engaging release materials without inventing facts, quotes, timestamps, or credentials. Preserve scientific nuance, explain technical terms plainly, and distinguish preliminary findings from established evidence. Return clean, publication-ready copy with the requested headings.",
    "maxTokens": 2200,
    "thinkingLevel": "low"
  },
  "messages": [
    {
      "role": "user",
      "content": "Create the launch kit for an episode of Signal & Soil, a practical climate-science podcast for informed general audiences.\n\nDELIVERABLES\n1. Five episode-title options, each under 65 characters and free of clickbait.\n2. A 90–120 word episode summary.\n3. Six chapter titles paired with the approximate timestamps supplied in the transcript.\n4. Three key takeaways, each one sentence.\n5. A LinkedIn post of 100–140 words for the podcast account.\n6. Two social captions under 220 characters each: one curious, one pragmatic.\n7. A factual accuracy note listing any claims the editor should verify before publication.\n\nSTYLE\nClear, intelligent, warm, and grounded. Emphasize practical implications for farmers and food systems. Do not imply that biochar is a universal solution. Use only information in the transcript. Paraphrase rather than fabricating direct quotes.\n\nSOURCE TRANSCRIPT\n[00:00] HOST MAYA CHEN: Today we are asking whether biochar can help farms hold more water while storing carbon. Our guest is Dr. Lena Ortiz, a soil biogeochemist at Great Plains State University. Her team has completed the second growing season of a three-year field trial in western Kansas.\n\n[02:10] ORTIZ: Biochar is a carbon-rich material made by heating crop residues in a low-oxygen chamber. The process is called pyrolysis. The properties of the final material depend heavily on the feedstock and temperature, so biochar is not one uniform product.\n\n[05:35] ORTIZ: In our trial, we incorporated locally produced wheat-straw biochar into 24 dryland sorghum plots. We are comparing two application rates with untreated control plots. These are interim observations, not final results.\n\n[08:20] ORTIZ: During the first season, soil moisture in the upper 20 centimeters was modestly higher in the amended plots after light rain. We did not see a statistically significant yield difference. In the second season, a severe heat wave complicated interpretation, and the laboratory analysis is still underway.\n\n[12:45] HOST: Farmers often ask about cost. ORTIZ: That is currently the largest barrier. The biochar itself, transport, and field application can be expensive. It makes more sense to investigate regional systems using nearby residues than to haul bulky material long distances.\n\n[16:30] ORTIZ: People sometimes describe biochar as permanent carbon storage. That is too simple. A resistant fraction can remain in soil for a long time, but persistence varies with production conditions, soil type, and climate. Our project is measuring changes over three years; it cannot directly prove century-scale storage.\n\n[20:05] HOST: Are there risks? ORTIZ: Poorly characterized material may contain contaminants or alter soil pH in unhelpful ways. Producers should request an analysis of the material and begin with small trials. Biochar also should not replace erosion control, crop rotation, or careful nutrient management.\n\n[24:15] ORTIZ: The most promising model may connect waste management with soil improvement. A cooperative could convert clean local residues, use process heat, test every batch, and apply the material nearby. But the economics and emissions of the entire system need to be counted.\n\n[28:40] HOST: What should listeners remember? ORTIZ: Biochar is a tool with interesting potential, not a shortcut. Match the material to the soil, verify quality, and look at the full system from residue source to field performance.\n\n[30:10] END"
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5-nano',
  settings: {
    thinkingLevel: 'low',
    maxTokens: 800
  },
  messages: [
    {
      role: 'user',
      content: 'Prepare the final public status-page update for a resolved payment-processing incident. The incident began at 14:20 UTC on August 31, 2026, and service has just been fully restored. First, call the available function to obtain the exact current UTC date and time; do not estimate it or draft the notice before receiving the function result. After the developer executes the call and sends the result in a follow-up turn, write a concise customer-facing update with: a clear “Resolved” heading, the restoration timestamp in UTC, the incident duration calculated from the start time, confirmation that queued transactions are processing normally, and a brief apology. Do not invent a cause.'
    }
  ],
  tools: [
    {
      type: 'function',
      name: 'get_current_utc_time',
      description: 'Returns the current date and time in UTC.',
      schema: {}
    }
  ],
  toolChoice: {
    type: 'tool',
    name: 'get_current_utc_time'
  }
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5-nano",
            "settings": {
                "thinkingLevel": "low",
                "maxTokens": 800
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Prepare the final public status-page update for a resolved payment-processing incident. The incident began at 14:20 UTC on August 31, 2026, and service has just been fully restored. First, call the available function to obtain the exact current UTC date and time; do not estimate it or draft the notice before receiving the function result. After the developer executes the call and sends the result in a follow-up turn, write a concise customer-facing update with: a clear “Resolved” heading, the restoration timestamp in UTC, the incident duration calculated from the start time, confirmation that queued transactions are processing normally, and a brief apology. Do not invent a cause."
                }
            ],
            "tools": [
                {
                    "type": "function",
                    "name": "get_current_utc_time",
                    "description": "Returns the current date and time in UTC.",
                    "schema": {}
                }
            ],
            "toolChoice": {
                "type": "tool",
                "name": "get_current_utc_time"
            }
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "541cdcc7-a83a-4d9c-8b4c-97318be592dc",
      "model": "openai:gpt@5-nano",
      "settings": {
        "thinkingLevel": "low",
        "maxTokens": 800
      },
      "messages": [
        {
          "role": "user",
          "content": "Prepare the final public status-page update for a resolved payment-processing incident. The incident began at 14:20 UTC on August 31, 2026, and service has just been fully restored. First, call the available function to obtain the exact current UTC date and time; do not estimate it or draft the notice before receiving the function result. After the developer executes the call and sends the result in a follow-up turn, write a concise customer-facing update with: a clear “Resolved” heading, the restoration timestamp in UTC, the incident duration calculated from the start time, confirmation that queued transactions are processing normally, and a brief apology. Do not invent a cause."
        }
      ],
      "tools": [
        {
          "type": "function",
          "name": "get_current_utc_time",
          "description": "Returns the current date and time in UTC.",
          "schema": {}
        }
      ],
      "toolChoice": {
        "type": "tool",
        "name": "get_current_utc_time"
      }
    }
  ]'

runware run openai:gpt@5-nano \
  settings.thinkingLevel=low \
  settings.maxTokens=800 \
  messages.0.role=user \
  messages.0.content="Prepare the final public status-page update for a resolved payment-processing incident. The incident began at 14:20 UTC on August 31, 2026, and service has just been fully restored. First, call the available function to obtain the exact current UTC date and time; do not estimate it or draft the notice before receiving the function result. After the developer executes the call and sends the result in a follow-up turn, write a concise customer-facing update with: a clear “Resolved” heading, the restoration timestamp in UTC, the incident duration calculated from the start time, confirmation that queued transactions are processing normally, and a brief apology. Do not invent a cause." \
  tools.0.type=function \
  tools.0.name=get_current_utc_time \
  tools.0.description="Returns the current date and time in UTC." \
  toolChoice.type=tool \
  toolChoice.name=get_current_utc_time

{
  "taskType": "textInference",
  "taskUUID": "541cdcc7-a83a-4d9c-8b4c-97318be592dc",
  "model": "openai:gpt@5-nano",
  "settings": {
    "thinkingLevel": "low",
    "maxTokens": 800
  },
  "messages": [
    {
      "role": "user",
      "content": "Prepare the final public status-page update for a resolved payment-processing incident. The incident began at 14:20 UTC on August 31, 2026, and service has just been fully restored. First, call the available function to obtain the exact current UTC date and time; do not estimate it or draft the notice before receiving the function result. After the developer executes the call and sends the result in a follow-up turn, write a concise customer-facing update with: a clear “Resolved” heading, the restoration timestamp in UTC, the incident duration calculated from the start time, confirmation that queued transactions are processing normally, and a brief apology. Do not invent a cause."
    }
  ],
  "tools": [
    {
      "type": "function",
      "name": "get_current_utc_time",
      "description": "Returns the current date and time in UTC.",
      "schema": {}
    }
  ],
  "toolChoice": {
    "type": "tool",
    "name": "get_current_utc_time"
  }
}