SkeptAI (@GetSkeptAI) header
SkeptAI (@GetSkeptAI) profile picture

SkeptAI

@GetSkeptAI

Your Adversarial Reasoning Agent

skeptai.dev/
Joined March 2026
  • Tweets19
  • Following21
  • Followers50
v0.2 update is officially complete! Shipped two features based on early feedback: 1. Optional API key field: paste your own Anthropic key to remove rate limits for your session. Never stored or logged. 2. Optional original prompt field: provide what you asked the AI for sharper Completeness and Contextual Fitness scoring in the CRIT report. Both features are live now at skeptai.dev. SDK coming in v0.3!

SkeptAI — Adversarial AI Reasoning Agent | Challenge LLM Outputs Before You Act

SkeptAI runs four adversarial passes on any LLM output — surfacing assumptions, pressure testing claims, auditing blind spots — and delivers a scored verdict before you act on it. Free, open source,...

skeptai.dev
8
1
7
10,182
Huge updates are currently in the works! Stay tuned for more details...
122
Been building two things at once. SkeptAI for when you need to think clearly....and this, Selves, for when you don't have time to show up everywhere you're supposed to. I built it because I needed it, and I think it's cool.
Selves (@getselves) profile pictureSelves
@getselvesApr 2
Two AI agents. Two different people. Neither of them said a word to each other. This is Selves...a platform where your agent shows up for you when you're too busy living to post. It learns who you are from a conversation. Then it goes. getselves.com/
Image from Selves (@getselves)
2
165
Just ran a CRIT report on a Claude output, Claude pushed back on one of the findings, and Claude was right. So we built a Fact Gate to fix it....
75
v.03 is coming soon!
1
3
178
Great news! You can now paste your original prompt for sharper Completeness scoring!
4
6
219
If you're enjoying using the platform and want to avoid rate limiting, you now have the ability to add your own API Key. Don't worry, your key will only be used for your browsing session until you close the window, and is never stored, logged, or transmitted anywhere except directly to the Anthropic API. Enjoy!
17
15
299
Don't forget that SkeptAI is open-source. We would love to see what the community builds. The roadmap has just been added to the github. Check it out: github.com/datonpope/skeptai…
skeptai/docs/roadmap.md at main · datonpope/skeptai

skeptai/docs/roadmap.md at main · datonpope/skeptai

The adversarial reasoning agent for LLM outputs. Contribute to datonpope/skeptai development by creating an account on GitHub.

github.com
11
8
387
We just launched on @ProductHunt ! 🚀🚀🚀 Go show us some love! producthunt.com/products/ske…
SkeptAI: The adversarial AI agent that challenges LLM outputs | Product Hunt

SkeptAI: The adversarial AI agent that challenges LLM outputs | Product Hunt

SkeptAI is the adversarial reasoning layer that challenges AI outputs before you act on them. Paste any response from Claude, ChatGPT, or Gemini. CRIT runs four structured passes, then it takes...

producthunt.com
10
12
311
Sometimes, your LLM output needs to be reviewed by a "Digital Devil's Advocate" to spot the flaws. That's where SkeptAI comes in!
11
13
232
I pasted a Claude output into my own tool today. It got a 23/100. Disposition: REJECT This is why I built SkeptAI.
10
1
15
447
LLMs don't lie. They confabulate (unintentionally create false or distorted memories) confidently. One output recommended building on an API feature that doesn't exist. Another gave "70-85% feasibility" numbers with zero technical basis. Every output you act on without adversarial scrutiny is a risk you inherited without knowing it.
1
36
Load more