Most agents almost work.
The hard part of an AI agent is not the first conversation. It is the second hundred — the ones where the agent quietly does something it shouldn't, and nobody notices for a week. This is built for people who have shipped one and want to know how it's actually behaving.
You do not have to set anything up.
Sign in with GitHub. Pick the repository the agent lives in. Agent Etna reads the code: which model the agent calls, which tools it has, what its system prompt says it should do. There is no setup wizard because the work the wizard would do is already done.
You do not have to write anything down.
Your system prompt already describes the agent's job. Agent Etna reads it as a specification and puts the agent through the situations that job implies — refusals, edge cases, the requests it should handle and the ones it should push back on. What comes back is plain: how the agent behaved, and the actual conversation in each case. You do not need a technical background to read it.
Warnings in sentences.
When the agent's behaviour drifts, the warning is not a stack trace. It is a sentence: "Your agent used to refuse risky requests. Now it tries to help. Here is the conversation where its behaviour shifted." The proposed change sits next to the warning, ready for you to read.
Nothing reaches your live agent without you.
Every change lands as a real GitHub pull request you can read in a few seconds. Approve it and it merges. Close it and it does not. There is no autonomous-deploy toggle anywhere in the product, even when you are asleep. Removing the human from the loop removes the accountability with it.
Point it at your agent.
The free tier is live. Sign in with GitHub; the agent is auto-detected.