Anvil : Test & Code Quality
Anvil writes tests, reviews code, debugs, and refactors, running in parallel while Engine codes. 4 modes. Catches bugs before Shield sees them.
The benefit of running Anvil
Three outcomes you get the week Anvil turns on. Not features, not roadmap items: actual results your team will feel.
Bugs caught before QA sees them
Tests, reviews, debugs in parallel while Engine codes.
Refactors that don't break
Full test suite runs before and after every change.
Four modes, one agent
Test Architect, Code Reviewer, Debugger, Refactorer: pick what you need.
4 jobs, one agent
Every capability below is in production today. No roadmap items, no coming-soons.
Test Architect mode
Unit, integration, E2E test design. Coverage goals, test hierarchy, fixture strategy.
Code Reviewer mode
Correctness, security, performance, readability, line-by-line review.
Debugger mode
Root cause analysis with transcript-grounded reasoning. No shotgun fixes.
Refactorer mode
Optimize without breaking. Perf passes, cleanup, idiomatic patterns.
What Anvil plugs into
Anvil does not replace what you already use. It routes through the tools your business lives in.
A real Anvil run, end to end
What you actually see when Anvil runs. Example output below; all data fabricated for illustration, no real clients shown.
Anvil runs with 5 teammates
No agent works alone. Anvil feeds into, and pulls from, these agents in every workflow.
Quick answers
Does Anvil replace Shield?
No, Anvil catches early bugs during dev. Shield is the final QA gate.
Can Anvil refactor without breaking?
Yes, runs full test suite before and after every refactor.
Which mode should I pick?
Depends on task: 'write tests' → Test Architect, 'fix this bug' → Debugger, 'clean this up' → Refactorer.
Put Anvil to work today
Deploy free from the Starter Kit in under 30 minutes. Prefer a full setup done for you? Book a strategy call and we'll map Anvil to your biggest bottleneck.