AI acceptance testing

Crazy Monkeys

Ship gate for AI

Let the monkeys stress it before your users do.

Your agent shipped a feature. Did it actually do what you told it to? Crazy Monkeys returns a versioned acceptance verdict with evidence: ship or don’t, before merge or client handoff.

Built for small teams and solo builders shipping AI apps, agents, and tool-calling features.

We are in limited design-partner mode. No self-serve signup yet. If you ship agents or tool-calling apps, request a free audit run on one preview.

Signed agent policy

Proof you can trust

• Baseline on your preview or PR
• Catch tool-call loops and injection nonsense
• Ship / no-ship keyed to the build (SHA)
• Evidence you can keep: not a script dump

What you get

One run answers, for a specific workflow on a specific commit:

1. What it was supposed to do
2. What “correct” looks like
3. Evidence (telemetry / traces / captures)
4. Pass or fail
5. Diff since the last run on the same step
6. SHA the verdict was produced against

The runner underneath can change. The contract shape does not. The script is interchangeable. The ledger is the product.

What we are not

• Not QA automation theater
• Not an AI bot that authors your Playwright suite as the SKU
• Not a coverage-as-a-Service staffing shop
• Not a self-serve signup product (yet)

How it fits CI

Point us at a preview. We run acceptance. You get ship or don’t ship before merge. Today that starts with a free audit run on one agent preview, not a self-serve install.

Free audit run

Would you like a free audit run on one agent?

Email bobby@crazymonkeys.ai with a preview URL for one agent or tool-calling flow and what “good” looks like in a couple of bullets. You keep the repo. We share the receipt keyed to that build.