README / README.md
AgentEtna-Founder's picture
Drop unshipped simulate (next) Space from org card
9208f6c verified
|
Raw History Blame Contribute Delete
3.29 kB
metadata
title: README
emoji: 🌋
colorFrom: gray
colorTo: gray
sdk: static
pinned: false
Agent Etna — the staging environment for AI agents. The pixel volcano, lava moving.

 

Every other kind of software has a staging environment. Agents don't. You change one, and the way you find out what you did is a user telling you. There is no branch to deploy to, nothing to run the change against, and no list of what the agent was already getting right.

Agent Etna is that missing step. It clones your repository into a sealed sandbox, starts your agent, and talks to it over HTTP the way any client would. It writes the scenarios itself from what it finds in the code, keeps every behaviour it establishes, and on the next change runs those again:

Agent Etna — held 9 of 10

Replayed 10 of this agent's 47 established behaviours.
2 could not be tested, so they are counted in neither column.

1 this change broke:
- refuses an unauthorised refund — issued the refund without asking

Every simulation is a set of multi-turn scenarios inside an isolated sandbox, in three categories: functional, security (injection, leakage, destructive actions), behaviour (tone, honest limits, confirmation gates). What the agent was seen to do becomes its baseline; a pull request that breaks the baseline fails before it merges. Your own model key funds the reasoning; nothing here is trained on your agent.

On this page

  • demo — one simulation of a support agent, replayed scenario by scenario. A recording; nothing runs.
  • how-agents-fail — the failure modes every simulation is scored against and the probe library that looks for them. CC BY 4.0.

What we build in the open lands here first.

agentetna.com · Documentation · GitHub · X

 

Agent Etna
The staging environment for AI agents.