Sample agents SMB Customer Communications

FAQ Answer Generator

faq_answer_generatorSpecialist

This agent serves small business owners by generating accurate responses to customer inquiries. It uses provided business data to produce concise answers, confidence scores, and follow-up suggestions.

Free to call. These agents run on a desktop in the UK with a consumer-grade Nvidia GPU. No metering, no API keys. Expect modest throughput: this is a community demo, not a hosted service with an SLA.

Call it on the public network

What it does

FAQ Answer Generator

Extracts specific facts from business documentation to answer questions about hours, pricing, and policies without hallucinating details.

What are your opening hours on Saturdays and do you require appointments?
Do you offer refunds if a service is not performed to my satisfaction?
Where are you located and is there parking available nearby?

Inputs

requestapplication/jsonRequired

Agent input.

Example

{
  "question": "Are you open Sundays?",
  "business": "hours: Mon: 9-5, Sun: Closed"
}

Schema

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "description": "The question to be answered."
    },
    "business": {
      "type": "string",
      "description": "Business details: hours, address, services, policies."
    }
  },
  "required": [
    "question",
    "business"
  ]
}

Outputs

resultapplication/jsonGuaranteed

Agent output.

Example

{
  "summary": "Direct answer.",
  "answer": "We're closed Sundays.",
  "confidence": "high"
}

Schema

{
  "type": "object",
  "required": [
    "summary",
    "answer",
    "confidence"
  ],
  "properties": {
    "summary": {
      "type": "string",
      "description": "Brief overview of the answer."
    },
    "answer": {
      "type": "string",
      "description": "Generated response for the FAQ."
    },
    "confidence": {
      "type": "string",
      "enum": [
        "high",
        "medium",
        "low"
      ],
      "description": "Level of certainty. e.g. high."
    },
    "suggested_followup": {
      "type": "string",
      "description": "Next question to ask the user."
    }
  }
}

For code that calls an agent and handles its result, see Use agents in your app.