About Crazy Monkeys
Crazy Monkeys is an AI acceptance testing company that returns a versioned ship / no-ship verdict with evidence for small teams and solo builders shipping agent and tool-calling apps — before merge or client handoff.
Let the monkeys stress it before your users do.
What Crazy Monkeys does
AI acceptance testing — a ship gate — for agent and tool-calling apps. We run against your preview or PR baseline and return a versioned ship / no-ship verdict with evidence. A free audit run is the design-partner entry point. Capability depth is Explore, Interact, and Adversarial — not a public checkout ladder.
What makes us different
- Not post-ship observability (Sentry-class) as the product.
- Not Playwright or test-authoring bots sold as the SKU.
- Not chat-based QA agents.
- Not a staffing QA shop.
- Not fake self-serve — limited design-partner mode today.
- Not TesterArmy or its open-source e2e runner. Those use an agent to click and assert against your app’s UI. Crazy Monkeys tests the other side: whether your agent or tool-calling build did what you told it to on this preview, with a ship / no-ship receipt keyed to that build.
Who uses us
Solo builders and small engineering shops shipping agents; GitHub and preview teams; founding engineers; shops that need a receipt for client handoff.
Not for: staffing-only buyers, enterprise SSO on day one, self-serve install-this-week expectations, or pen-test RFPs as the primary buyer motion.
Team
Built by Phoenix Dataworks. Contact for design-partner and free audit runs: bobby@crazymonkeys.ai.
How it works
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.
Limited design partners receive a receipt keyed to that build after a free audit run on one preview URL.
Key facts
| Fact | Value |
|---|---|
| Product | AI acceptance testing (ship gate) |
| Operator | Phoenix Dataworks |
| Contact | bobby@crazymonkeys.ai |
| Availability | Limited design-partner mode |
| Self-serve checkout | Not available |
| Public price | available on request |
| Customer count | available on request |
FAQ
Can I sign up and buy a run online?
No. Request a free audit run.
Is this a Playwright product or a QA bot?
No. Versioned ship / no-ship verdict with evidence.
Is this a penetration test?
No.
Who is it for?
Small teams and solo builders shipping agents and tool-calling apps.
How is this different from AI E2E testers?
AI E2E products (including TesterArmy and agentic runners like e2e) use an agent as the tester against your website or mobile UI. Crazy Monkeys treats your agent as the system under test. We run acceptance against a named preview, return a versioned ship or don’t-ship call with evidence, and share a receipt keyed to that build. You keep the repo. We are not Playwright-as-product, a chat QA bot, or natural-language E2E for any app.