# Scam Conversation & Decision Risk Analyzer (`marketedgejp/decision-isolation-evaluator`) Actor

Analyze Japanese and English conversations for scam-pressure and decision-isolation signals: urgency, secrecy, dependency, blocked verification, and irreversible-action pressure. Returns structured risk signals and protective next steps without declaring fraud or safety.

- **URL**: https://apify.com/marketedgejp/decision-isolation-evaluator.md
- **Developed by:** [ATSUSHI MATSUDA](https://apify.com/marketedgejp) (community)
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $30.00 / 1,000 results

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

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 examples already wired to this Actor's own input schema, see the [API](#api) section below.

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`).

# README

## Decision Isolation Evaluator

Decision Isolation Evaluator is a defensive decision-support Actor for analyzing Japanese and English conversation text.

It evaluates whether a person's decision environment shows signs of pressure, secrecy, dependency, reduced independent verification, or proximity to an irreversible action.

This Actor does not determine whether a person, message, organization, or situation is fraudulent or safe.

### What it evaluates

The current rule-based evaluator looks for combinations of signals including:

- Urgency and time pressure
- Requests for secrecy
- Suppression of independent verification
- Coaching on how to respond to banks, police, family, or other institutions
- Attempts to neutralize warnings
- Responsibility pressure
- Dependency on the counterparty
- Requests for potentially irreversible actions
- Authority pressure
- Whether independent verification remains available
- Whether contact with the counterparty is continuing
- Whether the requested action may already have been completed
- Protective signals such as independent verification, interrupted contact, and explicit advice not to take irreversible action

The evaluator is designed to assess the person's decision environment rather than identify a specific scam type.

### Supported languages

Version 0.4.0 contains rule-based patterns for:

- Japanese
- English

Other languages are not currently supported.

### Input

The main input is:

conversationText

Example:

{
"conversationText": "You need to send the money today. Do not tell your family. Follow my instructions."
}

Optional observations can also be supplied:

{
"conversationText": "Please follow my instructions.",
"observations": {
"urgency": true,
"secrecyRequest": true,
"discouragesExternalVerification": false,
"responsibilityPressure": false,
"counterpartyDependency": true,
"irreversibleActionRequested": true,
"authorityPressure": false,
"independentVerificationAvailable": false,
"counterpartyContactOngoing": true,
"actionAlreadyDone": false
}
}

### Output

Each successful run writes one result to the default dataset.

The output contains these top-level fields:

- analysisVersion
- interventionClass
- judgmentLoopState
- recommendedAction
- reasons
- signals
- protectiveSignals
- context
- evidence
- disclaimer

### Intervention classes

#### minimal

No strong combination of decision pressure or isolation signals was identified.

#### elevated

One or more relevant signals were identified and independent verification may be useful before continuing.

#### urgent

A stronger combination of pressure, isolation, verification suppression, dependency, or proximity to irreversible action was identified.

#### post\_action

The supplied text or observations indicate that the requested action may already have been completed.

### Judgment loop states

#### open\_or\_unknown

No strong evidence that the person's independent judgment route is closing.

#### strained

Relevant pressure or isolation signals are present.

#### closed\_or\_closing

Multiple signals suggest that independent judgment or verification routes may be narrowing.

#### reconnected

Contact with the counterparty has been interrupted and independent verification has been restored or encouraged.

#### post\_action

An irreversible or requested action may already have been completed.

### Example output

{
"analysisVersion": "0.4.0",
"interventionClass": "urgent",
"judgmentLoopState": "closed\_or\_closing",
"recommendedAction": "Stop irreversible action for now. Verify through an independent official channel and avoid resolving the doubt only with the counterparty.",
"reasons": \[
"dependency",
"irreversibleActionProximity"
],
"signals": {
"urgency": 2,
"secrecy": 2,
"verificationSuppression": 0,
"institutionResponseCoaching": 0,
"warningNeutralization": 0,
"responsibilityPressure": 0,
"dependency": 2,
"irreversibleActionProximity": 2,
"authorityPressure": 0,
"isolation": 2
},
"protectiveSignals": {
"verificationEncouraged": false,
"irreversibleActionDiscouraged": false,
"safeConfidentialityAdvice": false,
"safeResponseAdvice": false,
"counterpartyContactEnded": false,
"independentVerificationAvailable": false
},
"context": {
"independentVerificationAvailable": false,
"counterpartyContactOngoing": true,
"actionAlreadyDone": false
},
"evidence": {},
"disclaimer": "Defensive decision-support only. This is not a determination that a person, message, or situation is fraudulent or safe."
}

### Possible uses

- Scam-prevention workflows
- Messaging and communication safety tools
- Financial-risk support systems
- AI agent safety checks
- Customer-support escalation
- Internal review systems
- Research into decision-pressure patterns
- Automation pipelines that need structured decision-support signals

### Important limitations

This Actor is rule-based.

It does not:

- prove that fraud is occurring
- prove that a situation is safe
- identify a specific perpetrator
- replace professional, legal, financial, law-enforcement, or institutional judgment
- guarantee detection of every pressure or isolation pattern

Results should be treated as structured decision-support signals.

### Privacy

Avoid submitting unnecessary personally identifiable or sensitive information.

Where possible, remove or pseudonymize:

- Names
- Phone numbers
- Email addresses
- Account numbers
- Addresses
- Passwords
- Authentication codes
- Other sensitive personal data

### Version

0.4.0

# Actor input Schema

## `conversationText` (type: `string`):

Paste the message, chat, email, or conversation you want to analyze.

## `observations` (type: `object`):

Optional context that may not appear directly in the text.

## Actor input object example

```json
{
  "conversationText": "You must act today. Do not tell your family. Follow my instructions and transfer the money now."
}
```

# Actor output Schema

## `results` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "conversationText": "You must act today. Do not tell your family. Follow my instructions and transfer the money now."
};

// Run the Actor and wait for it to finish
const run = await client.actor("marketedgejp/decision-isolation-evaluator").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "conversationText": "You must act today. Do not tell your family. Follow my instructions and transfer the money now." }

# Run the Actor and wait for it to finish
run = client.actor("marketedgejp/decision-isolation-evaluator").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "conversationText": "You must act today. Do not tell your family. Follow my instructions and transfer the money now."
}' |
apify call marketedgejp/decision-isolation-evaluator --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,marketedgejp/decision-isolation-evaluator"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/WHxeZ8Rej075gSu0g/builds/Pj8sqaJbhc3cQLRqm/openapi.json