Kensa

Kensa turns agent traces into pytest evals that run in CI.

[Kensa @kensa_sh]

We've been cooking something..

Stay tuned for tomorrow.

👀

[Kensa @kensa_sh]

1/ Last week, Kensa read through a production agent's traces and caught a silent bug regressing the system.

1 in 4 of its generated summaries were truncating mid-sentence (max output tokens set to 150!)

That bug is one of many reasons we're releasing a new version today.

[Kensa @kensa_sh]

Check us out and let us know what you'd like to see improved!

Until next time 🫡

https://t.co/EC0MnL5yVP

[Kensa @kensa_sh]

1/ Last week, Kensa read through a production agent's traces and caught a silent bug regressing the system.

1 in 4 of its generated summaries were truncating mid-sentence (max output tokens set to 150!)

That bug is one of many reasons we're releasing a new version today.

[Kensa @kensa_sh]

6/ The evals are files you own and commit, nothing leaves your repository. And Kensa remains open source.

Paste this in Claude Code, Codex, or Cursor and let it wire itself:

"Fetch https://t.co/pKNx3M8Oc4 and follow it"

[Kensa @kensa_sh]

People of the world, friends and relatives - prepare yourself for the next version of Kensa, built from the ground up to make your agents even more reliable.

Drops on 22nd.

[Kensa @kensa_sh]

Agents should be held to a higher standard like we do with software.

Let's close the gap.

[satya @satyaborg]

Introducing kensa.

Tell your coding agent to eval any agent: It reads your code, sets up telemetry, finds failure modes, writes scenarios and judges.

kensa CLI + skills orchestrates it.

You review the diffs, not the scaffold.

Open source & MIT license, link below.