The first language designed for AI to write
Your model writes LMAT. A compiler checks every line before it runs. You ship software nobody had to review.
LMAT is a programming language designed for AI to write. A compiler checks every line before it runs: deterministic, sandboxed, with no escape hatch.
Read the language, node by node.
Everything on this site
- The first language designed for AI to write.: Your model writes LMAT. A compiler checks every line before it runs.
- AI writes code faster than anyone can review it.: Review is the new bottleneck.
- Twice the code, twice the review: Measured across more than 10,000 developers by Faros AI.
- Checked before it runs.: The model writes, the compiler checks, it runs.
- One request, start to finish: A request, a refusal in the checker’s own words, a repair.
- Real software, built on LMAT.: LMAT makes them work. The design is free.
- Software: Accounting, an issue tracker and a design tool.
- Games: Rocket-car soccer and a block world.
- What you get when your model writes LMAT.: Six things that hold for every program.
- Checked before it runs: 202 kinds of mistake, each named with the line and the fix.
- It tests itself: Every button pressed and every form filled, as every user.
- The same answer everywhere: It runs the same on every machine.
- It can’t reach what it shouldn’t: No other customer’s data, no web addresses, nothing that runs forever.
- Private by design: Each person sees only what they are allowed to.
- No escape hatch: There is no way around the checks.
- Built for agents too.: lmatfs, the storage layer for AI agents.
- lmatfs: Rust, with Python bindings.
- Measured, not claimed.: Counted from the LMAT repository on 5 October 2026.
- 202 kinds of mistake caught: Each named with the line, the field and the fix.
- 5,635 tests passing: Across the engine, the sandbox and the renderer.
- 36 attack programs run before every merge: Programs that try to break out of the sandbox or steal from it.
- Same requests, before and after LMAT tested each app: 23 requests, September 2026: three broke, then none.
- Who is building it: Two founders out of Carnegie Mellon.
- The team: Uzi Isman and Jason Shen.
- Talk to us.: We’re raising, and we work with AI companies.
Questions
- What is LMAT?
- LMAT is a programming language designed for AI to write. Your model writes the logic, the data and the rules. A compiler checks every line before it runs, so you ship software nobody had to review.
- What is Coverable?
- Coverable builds LMAT, the first language designed for AI to write, and lmatfs, the storage layer for AI agents.
- How does the LMAT compiler work?
- The model writes LMAT. The compiler checks every line and tells the model exactly what to fix, naming the line and the field. It knows 202 kinds of mistake (counted 5 October 2026). Only a program that passes runs.
- Is LMAT deterministic?
- Yes. It runs the same on every machine, so every step can be checked again.
- Is LMAT sandboxed and secure?
- A program cannot reach another customer’s data, cannot type a web address, and cannot run forever. There is no escape hatch around the checks. 36 attack programs that try to break out of the sandbox are run before every merge.
- What is lmatfs?
- lmatfs is the storage layer for AI agents, written in Rust with Python bindings. Every action is written down, anything can be undone, and an agent can try something on a branch and keep it or throw it away.
- Who builds LMAT?
- Uzi Isman (founder and CEO) and Jason Shen (co-founder and CTO, who designed LMAT). Both are from Carnegie Mellon.
- How do I contact Coverable?
- Email uzi@coverable.ai. We’re raising, and we work with AI companies whose models need to write software that works.