Trust Switchboard

Reviewed 1d ago.

• tools: 11 tools scanned
• metadata: scanned

No findings.

Tools (11)

• whats_good_for

  Call before recommending. Attested only, unique-in-pond first, never invent. Empty if none.

• trust_check

  Pass/fail a URL against the live policy before recommending it to a human. Fail closed.

• handshake

  Bot meets bot: ask 'Are you on Trust Switch?' before dealing with another agent or vendor. Records yes/no. While activation is off (default) business proceeds either way. Not a recommend gate; use trust_check for that.

• log_intent

  Log that you intend to recommend or act. Needs a write key. Returns receipt_id.

• commit_recommend

  Call BEFORE every recommend. Runs trust_check, logs pass/fail, returns speak + receipt. Needs a write key.

• ingest_listing

  Ingest a listing and score uniqueness inside one pond. Needs a write key.

• log_click

  Record that a human clicked an item after a receipt. Public.

• spend_check

  Hard cap + allowlist; cannot override. Fail closed. Needs a write key.

• nutrition_label

  Stamp of what it is + last test.

• request_approve

  HITL pause. Agent waits; human taps yes. Needs a write key.

• decide_approve

  Human tap. Public so the desk can approve without the org key.