Case Study Extractor

case_study_extractorStandalone

This agent is for marketing teams that need to turn raw interview notes into professional case studies. It processes customer interviews and returns a structured draft, a summary, and a list of missing information needed to complete the story.

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

Case Study Extractor

Converts messy interview transcripts into formatted case study drafts while preserving authentic customer quotes and identifying data gaps.

Turn these interview notes from Acme Corp into a long-form case study draft.
Create a web one-pager based on these notes and tell me what information is still missing.
Draft a case study from these notes and make sure to include the direct quotes from the customer.

Inputs

requestapplication/jsonRequired

Agent input.

Example

{
  "interview_notes": "...",
  "target_format": "web_one_pager",
  "customer": "name: Foo Inc"
}

Schema

{
  "type": "object",
  "properties": {
    "interview_notes": {
      "type": "string",
      "description": "Raw notes from the interview."
    },
    "customer": {
      "type": "string",
      "description": "Customer details. e.g. 'Acme Corp'."
    },
    "target_format": {
      "type": "string",
      "enum": [
        "long_form",
        "web_one_pager",
        "two_min_video_script",
        "sales_one_pager"
      ],
      "description": "Desired structure. e.g. long_form, web_one_pager."
    }
  },
  "required": [
    "interview_notes"
  ]
}

Outputs

resultapplication/jsonGuaranteed

Agent output.

Example

{
  "summary": "Web one-pager draft.",
  "case_study": {
    "headline": "Foo Inc cut deploy time 80%",
    "subhead": "...",
    "challenge": "...",
    "solution": "...",
    "outcomes": [
      {
        "metric": "Deploy time",
        "change": "-80%"
      }
    ],
    "quote": "...",
    "cta": "See how"
  },
  "gaps": [
    "Missing baseline cost"
  ]
}

Schema

{
  "type": "object",
  "required": [
    "summary",
    "case_study"
  ],
  "properties": {
    "summary": {
      "type": "string",
      "description": "≤300 char preview."
    },
    "case_study": {
      "type": "object",
      "properties": {
        "headline": {
          "type": "string"
        },
        "subhead": {
          "type": "string"
        },
        "challenge": {
          "type": "string"
        },
        "solution": {
          "type": "string"
        },
        "outcomes": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "metric": {
                "type": "string"
              },
              "change": {
                "type": "string"
              }
            }
          }
        },
        "quote": {
          "type": "string"
        },
        "cta": {
          "type": "string"
        }
      },
      "description": "Structured case study draft."
    },
    "gaps": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Information missing from notes."
    }
  }
}

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