An LLM authors the artifact at compile time. The runtime stays free of inference.
Compiled AI is a paradigm for systems that must be deterministic, auditable, and fast. The model runs offline to draft a config, rule, or policy; an external validator proves the artifact does what it claims; the committed artifact is then consumed by a boring, well-known tool — Semgrep, OPA, Terraform, GitHub Actions — with no model in the request path.
- semgrep-rule-compiler — compiles incident postmortems and code samples into gate-verified Semgrep rules. The first reference implementation of the five-part shape (spec → compiler → gates → artifact → runtime).
- Use it. Open an issue with a pattern you'd want compiled.
- Extend it. PRs for new languages, rule modes, or autofix — all gated the same way.
- Build the next compiler. Have a deterministic tool that consumes config or rules (OPA, Terraform, GitHub Actions, an in-house policy engine)? Open an issue describing the use case — we're looking for collaborators on adjacent compile targets.
Contact: open an issue on any repo, or compiledailabs@gmail.com.