intent-classification: a scope guard in front of agent workflows

A modular gateway: define each agent's scope and confidence threshold, plug it in before the workflow — one reusable guard, many scopes.

Notes

Repository; no figures.

source-backed — Public repository, docs or live artifact. About this label

Destinations

Try a walkthrough

• Route the next step of an agent →

  Let Jev choose a proposed next step, then apply an explicit allow, review or fallback policy before any tool runs.

Verification levels

Report a problem →

Filed under

• #guardrail
• #classification
• #agents

In collections

• Agent harnesses →