YourAIGuard troch vspendyala

YourAIGuard — AI Response Trust Monitor for ChatGPT

AI models can sound confident even when they're wrong. YourAIGuard watches every ChatGPT response and gives you an instant, private assessment of its reasoning quality
using a research-proven methodology — no account, no API key, and no data ever leaves your browser.

How it works

After each ChatGPT response, YourAIGuard checks it against seven reasoning quality criteria:

• C1 — Relevance to prompt
• C2 — Directly addresses the question
• C3 — Step-by-step or structured reasoning
• C4 — Uses justification or explanation
• C5 — Internal consistency
• C6 — Acknowledges uncertainty or limits when needed
• C7 — Sufficiently complete for the prompt

Conversation-level instability tracking

Over the course of a conversation, reasoning quality can drift. After 10 exchanges, YourAIGuard computes a temporal instability index based on the paper "Temporal
Instability Phases Precede and Predict Reasoning Error in Generative Pre-Trained Transformers" (Pendyala) and shows one of three phases:

• 🟢 AI is reasoning clearly
• 🟡 AI reasoning is showing strain
• 🔴 AI reasoning may be unreliable

Tap the 📊 button on any response to open a timeline showing confidence, per-criterion pass/fail tracks, and the instability score across the entire conversation.

Fully private and offline

All analysis runs on-device using a bundled MiniLM sentence-embedding model. The extension makes no external network requests and sends no data anywhere — not to us, not to
OpenAI, not to anyone.

No setup required

Install and open ChatGPT.

That's it.