Skip to content
Lorca Labs
Live demo
Agents & policy

Canary Weave Agent

Invisible canaries that tell you where a leak came from — not that it didn't leak.

Try live Canary Weave Agent Contact

The problem

When an agent's output is leaked or scraped, you need to prove which registration produced it. Canary tokens woven at generation time let downstream detection tie a recovered text back to its origin registration.

What it does

01

Weaves canary tokens into a text payload with optional agentId, style (inline/suffix), and tokenCount.

02

Returns a registration ID, woven text, tokens, and context/woven hashes.

03

Detects canary tokens in any text against the registration database; reports matched hits with positions.

04

Lists registrations (tokens withheld in list) and fetches a full record by ID.

Who it’s for

  • Agent operators needing output attribution
  • Security teams detecting leaked or hallucinated content
  • Compliance reviewers verifying generation provenance

In context

Complements Sovereignty (agent governance) and the Stego Audit Carrier (carrier-bound audit).

Try it live in the studio

A no-signup, in-browser experiment against an isolated demo host. Load sample data, run the flow, and see the result — nothing is stored.

Try live Contact