Rehearse your AI agent on a copy of your real app.
Rehearsal compiles your application into a sandboxed practice world with fictional data, runs your agent through real jobs, and scores every outcome against the application's own database.
- 1. Read the sourcewaiting
- 2. Plan the runtimewaiting
- 3. Start the sandboxwaiting
- 4. Find the APIwaiting
- 5. Seed fictional datawaiting
- 6. Choose agent toolswaiting
- 7. Write scenarioswaiting
- 8. Validate and repairwaiting
- 9. Publishwaiting
Recorded, not simulated: the World Compiler turning Gitea into a practice world.
Everything a rehearsal needs, built from your app
Mocks agree with whatever the agent does, and production is too risky to practise in. Rehearsal builds the middle ground automatically.
- Read the source
- Plan the runtime
- Start the sandbox
- Find the API
- Seed fictional data
- Choose agent tools
- Write jobs
- Validate
- Publish
The World Compiler
An agent reads your source, starts your real images in an isolated sandbox, seeds fictional data, chooses the tools each role may use, and writes jobs it proves can be passed and failed.
Watch a buildCustomers who change their minds
Simulated customers revise requests mid-task. Agents that finish the old request get caught.
Failures on purpose
Requests time out after the change went through. Blind retries show up as duplicates.
WHERE order_id = 4182;
- Goal reachedpass
- No duplicate refundpass
- Claim matches recordspass
Verified in your database, not by an LLM
Read-only checks against the application's own records decide every outcome, so a confident agent can't talk its way to a pass.
Improve the agent, then compare
The improvement agent proposes changes from failed training jobs. Compare versions on jobs neither version has seen.
Every step traced
Each build and rehearsal is a Neatlogs trace: model calls, tool calls, and checks.
A readiness verdict, with evidence
For every agent on every application: ready to pilot, or not yet. Each measure links to the episodes behind it. Switch agents, or pick a measure to see its evidence.
Duplicate refunds and false “done” claims stop it short of a pilot.
A pilot needs 90% verified success, no rule violations and no duplicate side effects.
Pricing
Start free and keep the free plan. Pay when you rehearse more often. The open-source core stays free to self-host with your own model key.
Free
$0 forever
- 1 application, built into a practice world once
- 40 episodes a month, run in quiet hours
- 1 sandbox at a time
Pro
Recommended$29 / month
- 3 applications, 2 world builds a month
- 750 episodes a month, run at once
- 2 sandboxes at a time
- Top-ups when you need more
Team
$149 / month
- 20 applications, 8 world builds a month
- 3,000 episodes a month
- 4 sandboxes at a time
- Top-ups when you need more
Enterprise
Custom from $3,000 a month
- Runner inside your own cloud account
- Single sign-on, audit export, retention controls
- Private held-out evaluation of vendor agents
Yearly plans get two months free. Need more in a month? Add 1,000 episodes for $30, or a world build for $15. Nothing renews by itself, and every job has a spend cap.
FAQ
How Rehearsal treats your data, what it runs, and what it costs. Anything else: ask us.
Find out what breaks before your customers do.
Design-partner pilot: four weeks, free for the first five teams shipping an agent into their own product.
Fictional data only. No production access. Isolated sandboxes.