Survey Response Summarizer

survey_response_summarizerSpecialist

This agent is for business owners and researchers who need to process large volumes of qualitative feedback. It analyzes batches of survey responses to return thematic summaries, sentiment distributions, and actionable next steps.

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

Survey Response Summarizer

It categorizes raw text into recurring themes, identifies specific customer grievances, and extracts positive feedback to generate a structured report.

Summarize these 50 customer satisfaction responses and list the top three complaints.
Analyze these survey results regarding our new product launch and suggest actions to improve user retention.
Give me a sentiment breakdown and a list of recurring themes from these event feedback responses.

Inputs

requestapplication/jsonRequired

Agent input.

Example

{
  "responses": [
    {
      "q1": "Loved it!"
    },
    {
      "q1": "Slow service"
    }
  ]
}

Schema

{
  "type": "object",
  "required": [
    "responses"
  ],
  "properties": {
    "responses": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "List of survey responses to summarize."
    },
    "question_context": {
      "type": "string",
      "description": "What questions were asked."
    }
  }
}

Outputs

resultapplication/jsonGuaranteed

Agent output.

Example

{
  "summary": "Top theme: slow service.",
  "themes": [
    {
      "theme": "Service speed",
      "count": 12,
      "representative_quotes": [
        "Took 30 min for coffee"
      ],
      "sentiment": "negative"
    }
  ],
  "sentiment_breakdown": {
    "positive": 18,
    "neutral": 6,
    "negative": 12
  },
  "praise": [
    "Coffee quality"
  ],
  "complaints": [
    "Slow service"
  ],
  "suggested_actions": [
    "Add weekend prep cook"
  ]
}

Schema

{
  "type": "object",
  "required": [
    "summary",
    "themes",
    "sentiment_breakdown"
  ],
  "properties": {
    "summary": {
      "type": "string",
      "description": "Key themes, complaints, and praise."
    },
    "themes": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "theme": {
            "type": "string"
          },
          "count": {
            "type": "integer"
          },
          "representative_quotes": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "sentiment": {
            "type": "string"
          }
        }
      },
      "description": "Key recurring topics identified."
    },
    "sentiment_breakdown": {
      "type": "object",
      "properties": {
        "positive": {
          "type": "integer"
        },
        "neutral": {
          "type": "integer"
        },
        "negative": {
          "type": "integer"
        }
      },
      "description": "Distribution of positive, neutral, and negative tones."
    },
    "praise": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "List of positive feedback."
    },
    "complaints": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "List of specific user grievances."
    },
    "suggested_actions": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Recommended steps to address feedback."
    }
  }
}

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