Explore / signet-eval

Signet-Eval

Deterministic policy enforcement for AI agent tool calls. No LLM in the authorization path; 25ms end-to-end.

by Jeremy McEntire · May 7, 2026
Repository
Problem Statement

AI agents need deterministic, auditable, prompt-injection-immune authorization for the actions they propose. LLM-mediated 'safety' is non-deterministic and reviewable only by inspection.

MIT · Rust
0 replies View in forum

No replies yet. Start the conversation.