# Detect social-engineering pressure in a support chat

**Use case:** 

Analyze support-chat conversations for social-engineering pressure, secrecy, dependency, blocked independent verification, urgency, and irreversible-action pressure. Returns structured decision-support signals and recommended protective next steps without declaring fraud or safety.

## Input

```json
{
  "conversationText": "A support agent told me to keep this secret, not contact the company's official support, and follow only their instructions. They said I must act today and install a remote-access app."
}
```

## Output

```json
{
  "analysisVersion": {
    "label": "Analysis version",
    "format": "string"
  },
  "interventionClass": {
    "label": "Intervention class",
    "format": "string"
  },
  "judgmentLoopState": {
    "label": "Judgment loop state",
    "format": "string"
  },
  "recommendedAction": {
    "label": "Recommended action",
    "format": "string"
  },
  "reasons": {
    "label": "Reasons",
    "format": "array"
  },
  "signals": {
    "label": "Signals",
    "format": "object"
  },
  "protectiveSignals": {
    "label": "Protective signals",
    "format": "object"
  },
  "context": {
    "label": "Context",
    "format": "object"
  },
  "evidence": {
    "label": "Evidence",
    "format": "object"
  },
  "disclaimer": {
    "label": "Disclaimer",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [Scam Conversation & Decision Risk Analyzer](https://apify.com/marketedgejp/decision-isolation-evaluator.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/marketedgejp/decision-isolation-evaluator.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/marketedgejp/decision-isolation-evaluator.md

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).