Launching today
BotGauge
The trust layer for your agents
469 followers
The trust layer for your agents
469 followers
AI agents don't just generate answers anymore. They take actions, call tools, and access real data. BotGauge helps engineering teams find where agents break before users do. Run adaptive red-team attacks and evals, catch security and behavioral failures, and replay every issue with full traces. Turn failures into regression tests, continuously retest as your agents evolve, and monitor their behavior in production. One reliability layer from development to deployment.
Free Options
Launch Team / Built With
SeamlessMake your next Instagram post the one they actually swipe through
Promoted
Really excited for users to start using this
@subham_sharma11 Thank you! We’re excited too. Can’t wait to hear what you think once you try it.
A friend of mine runs a booking agent. A user talked it into changing a trip without asking anyone. Scary how easy it was.
@om_prakash49 Yikes, that’s the scary kind of failure, because nothing looks broken. The agent did exactly what it was asked, just for the wrong person. Honestly it’s the same class of thing red-teaming is built for, so if your friend ever wants to throw it at that booking agent, I’d love to hear what it turns up
Really love this. It's something we will definitely look into as we roll out AI chat in our app in the coming months, as it's exactly the type of testing and safeguards we need.
@billmaroulis Thank you, that’s great to hear! Rolling out chat is the perfect time to test. Sign up and try it on your app’s chat before launch, and tell us what it finds.
The trace is what makes a failed eval useful for me. Being able to replay the same tool calls should make it easier to check whether a fix holds.
@oleksii_sekundant Yes, exactly. A fix you can’t replay is mostly a guess. Running the same tool calls again is the only real way to know the hole is actually closed and not just hidden.
“So we built an attacker” — great line 😄 I like it
@alexkhlystova Haha thanks! Glad it landed. 😄
@pradeepsoundararajan Thank you so much! 🙏
The part that stuck with me is turning each failure into a permanent eval that runs on every release. The quiet failures Pramin described — an agent retrying a failed tool call in a loop, or holding an approval for 117 role-play attempts and folding on the 118th — are exactly the ones that never show up as crashes. Replaying the same tool calls with the full trace feels like the only way to know a fix actually fixed it, rather than just changing the prompt and hoping. Curious how you handle the cases where the break comes from instructions hidden in a document the agent reads, rather than from the user directly.