TrustScanAI

🧠 TruthScan AI — Claim Verification Agent

A powerful AI agent that verifies claims, tweets, news paragraphs, and WhatsApp forwards by fact-checking against trusted sources. Built with CrewAI and deployed as an Apify Actor.

💡 What it does

Users can paste:

• A claim or statement
• A tweet or social media post
• A news paragraph
• A WhatsApp forward

👉 The agent:

• Breaks the claim into factual sub-claims
• Searches trusted sources (Wikipedia, government sites, news outlets)
• Rates truthfulness with confidence scores
• Explains why content is misleading or true
• Provides evidence and reasoning

🔥 Why this matters

• Extremely relevant: Misinformation is a critical problem
• Clear social good: Helps combat fake news and disinformation
• No scraping auth hell: Uses public APIs and search tools
• Strong AI reasoning demo: Showcases advanced claim analysis

How it works

The TruthScan AI agent receives a claim from the user and systematically fact-checks it using multiple verification tools. The agent searches Wikipedia, performs web searches via DuckDuckGo, and analyzes the gathered evidence to provide a comprehensive verdict with confidence scoring and detailed explanations.

🧩 Tools Used

• DuckDuckGo Search: Web search for current information
• Wikipedia API: Access to encyclopedic knowledge
• Simple HTTP Fetch: Direct access to trusted sources
• LLM Reasoning: Advanced claim analysis and verdict generation

🧠 Output Example

Input: "Drinking hot water cures COVID-19"

Output:

Verdict: ❌ False
Confidence: 92%

Evidence:
- WHO states no drink cures COVID-19
- Medical journals confirm no thermal effect on virus
- No peer-reviewed studies support this claim

Reason people believe it:
- Authority bias from social media "experts"  
- Fear-driven misinformation during pandemic
- Confusion between symptom relief and cure

How to use

Simply provide any claim, tweet, or text content in the claim input field. The agent will automatically analyze it and provide a detailed verification report.

Pay Per Event

This template uses the Pay Per Event (PPE) monetization model, which provides flexible pricing based on defined events.

To charge users, define events in JSON format and save them on the Apify platform. Here is an example schema with the task-completed event:

[
    {
        "task-completed": {
            "eventTitle": "Task completed",
            "eventDescription": "Cost per query answered.",
            "eventPriceUsd": 0.1
        }
    }
]

In the Actor, trigger the event with:

await Actor.charge(event_name='task-completed')

This approach allows you to programmatically charge users directly from your Actor, covering the costs of execution and related services, such as LLM input/output tokens.

To set up the PPE model for this Actor:

• Configure the OpenAI API key environment variable: provide your OpenAI API key to the OPENAI_API_KEY in the Actor's Environment variables.
• Configure Pay Per Event: establish the Pay Per Event pricing schema in the Actor's Monetization settings. First, set the Pricing model to Pay per event and add the schema. An example schema can be found in .actor/pay_per_event.json.

Included features

• Apify SDK for Python - a toolkit for building Apify Actors and scrapers in Python
• Input schema - define and easily validate a schema for your Actor's input
• Dataset - store structured data where each object stored has the same attributes
• Key-value store - store any kind of data, such as JSON documents, images, or text files

Resources

• What are AI agents?
• Python tutorials in Academy
• Apify Python SDK documentation
• CrewAI documentation
• Integration with Make, GitHub, Zapier, Google Drive, and other apps

🚀 Getting Started

1. Configure OpenAI API Key: Set your OPENAI_API_KEY in the Actor's environment variables
2. Input a claim: Paste any claim, tweet, or statement you want to verify
3. Get results: Receive a comprehensive fact-check report with evidence and confidence scores

Example Verification Process

Input Claim: "5G towers cause COVID-19 symptoms"

TruthScan AI Process:

1. Sub-claim extraction: Breaks down into "5G towers emit harmful radiation" + "Radiation causes COVID-19 symptoms"
2. Evidence gathering: Searches WHO, CDC, scientific journals, fact-checkers
3. Analysis: Evaluates source credibility and scientific consensus
4. Verdict generation: Provides clear assessment with reasoning

Output:

Verdict: ❌ False
Confidence: 96%

Evidence:
- WHO: No evidence linking 5G to COVID-19
- Multiple peer-reviewed studies show 5G safety
- COVID-19 spreads in areas without 5G coverage
- Virus identified as SARS-CoV-2, not radiation effect

Reasoning: 
COVID-19 is caused by a virus (SARS-CoV-2), not electromagnetic radiation. 
5G operates at frequencies well below harmful ionizing radiation levels.

Why people believe it:
- Correlation fallacy (5G rollout coincided with pandemic)
- Distrust of new technology
- Conspiracy theory amplification on social media

Getting started

For complete information see this article. In short, you will:

1. Build the Actor
2. Run the Actor with your claim to verify

Pull the Actor for local development

If you would like to develop locally, you can pull the existing Actor from Apify console using Apify CLI:

1. Install apify-cli

   Using Homebrew

   $brew install apify-cli
   

   Using NPM

   $npm -g install apify-cli
   

2. Pull the Actor by its unique <ActorId>, which is one of the following:

   • unique name of the Actor to pull (e.g. "apify/hello-world")
   • or ID of the Actor to pull (e.g. "E2jjCZBezvAZnX8Rb")

   You can find both by clicking on the Actor title at the top of the page, which will open a modal containing both Actor unique name and Actor ID.

   This command will copy the Actor into the current directory on your local machine.

   $apify pull <ActorId>
   

Documentation reference

To learn more about Apify and Actors, take a look at the following resources:

• Apify SDK for JavaScript documentation
• Apify SDK for Python documentation
• Apify Platform documentation
• Join our developer community on Discord