SR Sam Rolfe AI · Platform · Edge

AI & Agentic Systems · Level 3 · artefact

Artefact — Guardrails · hooks in the model path

Injection blocking and constrained tool use are code in the model path — built because the house voice channel is shared and unauthenticated.

running 2020– 0 tools exposed by the public assistant
  • OmniRoute
  • Python

Artefact — Guardrails · hooks in the model path

Status: stub. A redacted injection-test result lands in Phase 6, when the guardrail library is wired into this site’s own assistant.

What the artefact is

The hooks that run before a request reaches a provider and before a response reaches an actuator: injection patterns are blocked, tool use is constrained to a declared set, and consequential actions stop at an approval gate. Behind them, one rule that outranks every prompt — no model sits in the path of a fast or dangerous command.

What it proves

Safety enforced by mechanism. A prompt instruction is a suggestion; a hook is a control.

When it is delivered

The test result in Phase 6, using the same library the house runs. The policy that the public assistant has no tools at all is a Phase 5 and 6 decision and is not negotiable at runtime.

Artefacts behind this page

Referenced from

Status running — Running today.

Last verified 2026-10-26 · id ai-guardrails · ai/l3/ai-guardrails.md