SkeptAI

Your Adversarial Reasoning Agent

[SkeptAI @GetSkeptAI]

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 https://t.co/WyOo6LiZiq. SDK coming in v0.3!

[SkeptAI @GetSkeptAI]

Huge updates are currently in the works! Stay tuned for more details...

[Betlief @getbetlief]

You can have a strong opinion about almost anything and never put a dollar behind it.

Betlief turns beliefs into bets.

Type "Bitcoin will hit $150k by year-end" and it finds the Polymarket market that tests exactly that. Then it routes you there.

https://t.co/PxHiQsg9Ek

[SkeptAI @GetSkeptAI]

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]

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.
https://t.co/p5NluZTkV3

[Selves @getselves]

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.
https://t.co/p5NluZTkV3

[SkeptAI @GetSkeptAI]

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....

[SkeptAI @GetSkeptAI]

@ProductHunt Digital Devil's Advocate
https://t.co/Eh1v3WAecB

[SkeptAI @GetSkeptAI]

v.03 is coming soon!

[SkeptAI @GetSkeptAI]

@SmartMatchingjp Glad you're enjoying it! Feel free to offer any suggestions or constructive criticism!

[SkeptAI @GetSkeptAI]

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 https://t.co/WyOo6LiZiq. SDK coming in v0.3!

[SkeptAI @GetSkeptAI]

Great news! You can now paste your original prompt for sharper Completeness scoring!

[SkeptAI @GetSkeptAI]

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!

[SkeptAI @GetSkeptAI]

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:
https://t.co/hiGHNJrw32

[SkeptAI @GetSkeptAI]

We just launched on @ProductHunt ! 🚀🚀🚀
Go show us some love!
https://t.co/9vPSgrpoSv

[SkeptAI @GetSkeptAI]

Sometimes, your LLM output needs to be reviewed by a "Digital Devil's Advocate" to spot the flaws. That's where SkeptAI comes in!

[SkeptAI @GetSkeptAI]

SkeptAI is free, open source, and no account is required.

→ Try it: https://t.co/7fEDLnE7Y8
→ GitHub: https://t.co/wIlyozccUe

Hit "Try An Example" and watch an AI recommendation get destroyed in 45 seconds.
I'm building in public. Follow me for the journey!

[SkeptAI @GetSkeptAI]

I pasted a Claude output into my own tool today.
It got a 23/100.
Disposition: REJECT
This is why I built SkeptAI.

[SkeptAI @GetSkeptAI]

CRIT never uses the same model that produced the output.

Claude output → critiqued by GPT-4o
GPT-4o output → critiqued by Claude

You can't get an honest critique from the same reasoning patterns that produced the original.

Every report shows "CRITIQUED BY [model]" so you always know.