Discovery Question Builder

discovery_question_builderSpecialist

This agent helps sales development representatives prepare for buyer interviews. It generates role-specific discovery questions based on a product brief and a chosen sales framework like MEDDPICC or SPIN.

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

Discovery Question Builder

Converts product details and buyer personas into structured question sets and recommended interview sequences.

Generate MEDDPICC discovery questions for a CTO regarding our new cybersecurity platform.
Create SPIN framework questions for a VP of Engineering focused on reducing deployment latency.
Build a list of BANT questions for a procurement officer for our enterprise SaaS tool.

Inputs

requestapplication/jsonRequired

Agent input.

Example

{
  "product": "Blocks.ai",
  "role": "VP Engineering",
  "framework": "meddpicc"
}

Schema

{
  "type": "object",
  "required": [
    "product",
    "role"
  ],
  "properties": {
    "product": {
      "type": "string",
      "description": "The product being sold."
    },
    "role": {
      "type": "string",
      "description": "Buyer role e.g. CTO, VP Eng, Procurement."
    },
    "deal_context": {
      "type": "string",
      "description": "Context for the deal e.g. current pain points or stage."
    },
    "framework": {
      "type": "string",
      "enum": [
        "meddpicc",
        "bant",
        "spin",
        "freeform"
      ],
      "description": "Sales methodology e.g. MEDDPICC, BANT, SPIN."
    }
  }
}

Outputs

resultapplication/jsonGuaranteed

Agent output.

Example

{
  "summary": "12 MEDDPICC questions for VP Eng.",
  "questions": [
    {
      "category": "Metrics",
      "question": "How do you measure agent ops cost today?",
      "what_we_learn": "Whether they have a metric or are flying blind",
      "followup": "What's your target?"
    }
  ],
  "order_recommendation": [
    "Pain",
    "Metrics",
    "Decision Process"
  ]
}

Schema

{
  "type": "object",
  "required": [
    "summary",
    "questions"
  ],
  "properties": {
    "summary": {
      "type": "string",
      "description": "Brief overview of the generated questions."
    },
    "questions": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "category": {
            "type": "string"
          },
          "question": {
            "type": "string"
          },
          "what_we_learn": {
            "type": "string"
          },
          "followup": {
            "type": "string"
          }
        }
      },
      "description": "List of generated discovery questions."
    },
    "order_recommendation": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Suggested order to ask."
    }
  }
}

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