§ Blog

Notes from building
the policy engine.

Architecture, principles, and the integration choices that shape how Yelt enforces policy on AI agents that touch money.

  1. ·3 min read·#launch
    Hello, Yelt.
    Why we built a policy engine and audit ledger for AI agents that touch money — and what we mean by 'tamper-evident' when it's a CFO asking.
  2. ·5 min read·#architecture#policy
    Belt and suspenders: policy as instruction and as enforcement.
    How Yelt compiles a CFO's English sentence into a typed runtime descriptor, drops it into the agent's SKILL.md, and enforces it at the gateway anyway.
  3. ·6 min read·#audit#cryptography
    What 'tamper-evident' actually means at audit time.
    SHA-256, append-only Postgres triggers, and an offline verify CLI. A regulator-grade audit pitch is a cryptographic claim; here's the substrate.