YouTube Fact Checker and AI Detector

Analyzes a YouTube video transcript and visuals to detect AI-generated content and verify factual claims against external sources.

Prompt Template

Analyze the following YouTube video: "{{YouTube URL: e.g. https://www.youtube.com/watch?v=PUCO-demo}}"

Step 1 — Extract content:
First, retrieve the transcript of the video. If no transcript is available, analyze the video content directly including visuals and audio.

Step 2 — Analyze:
Based on the extracted content, evaluate the following:
- How likely is the content (claims, narrative) to be fabricated or AI-generated?
- How likely are the visuals to be AI-generated?
- Cross-reference all key claims with external sources using a "{{Scrutiny Level: High, Medium, Low}}" level of scrutiny.

Output a short markdown summary strictly using this format:

**Content:** [Insert %] probability of being fabricated or AI-generated  
**Video:** [Insert %] probability of visuals being AI-generated  
**Likeliness of the content being made up:** [Insert %]  

**Sources that support the content:**
- [Source Name/Title] (URL)

**Sources that contradict the content:**
- [Source Name/Title] (URL)

If no reliable sources can confirm any claim, output only:  
**NO EVIDENCE FOUND THAT THIS CONTENT IS REAL**

Prompt Guide

Best For

  • Starting from a structured, reusable prompt instead of a blank chat.
  • Adapting the prompt to your own inputs while keeping the original intent intact.
  • Workflows related to Education & Academic.

How To Use It

  1. Copy the full prompt template.
  2. Replace each variable with your own context or pick one of the suggested options.
  3. Paste the completed prompt into ChatGPT, Claude, Gemini, or another AI assistant.

Variables In This Prompt

YouTube URL

e.g. https://www.youtube.com/watch?v=PUCO-demo

Scrutiny Level

High, Medium, Low

Example Starting Point

Analyze the following YouTube video: "e.g. https://www.youtube.com/watch?v=PUCO-demo"

Step 1 — Extract content:
First, retrieve the transcript of the video. If no transcript is available, analyze the video content directly including visuals and audio.

Step 2 — Analyze:
Based on the extracted content, evaluate the following:
- How likely is the content (claims, narrative) to be fabricated or AI-generated?
- How likely are the visuals to be AI-generated?
- Cross-reference all key claims with external sources using a "High" level of scrutiny.

Output a short markdown summary strictly using this format:

**Content:** [Insert %] probability of being fabricated or AI-generated  
**Video:** [Insert %] probability of visuals being AI-generated  
**Likeliness of the content being made up:** [Insert %]  

**Sources that support the content:**
- [Source Name/Title] (URL)

**Sources that...

How Variables Work

Variable Syntax

Variables are wrapped in {{ and }} and follow this pattern:

{{variable name: option1, option2, option3 }}

Predefined Variables

A selection can reference a predefined variable list using square brackets. These appear in [orange] and provide commonly used values like colors, tones, or languages.

{{Tone: [tones] }}

Custom Selection Lists

You can also provide an inline list of choices separated by commas.

{{Format: bullet points, paragraphs, numbered list }}
💡

Tip: You don't need the PUCO app to use these prompts! Simply copy the template and replace each {{…}} section with your own text directly in ChatGPT, Claude, Gemini, or any other AI assistant.

Use this prompt in seconds — not minutes

Install PUCO for Mac: press a hotkey in any app, fill a smart form, paste into ChatGPT, Claude or Gemini. Every variable becomes a curated dropdown. Your last values are remembered.

Download on the Mac App Store