# Agent Output Verification

> External application-level evidence gate for agent workflows. Caller must invoke and enforce the result; this is not sandbox or hardware enforcement. Paid evidence evaluation; free discovery, fixed worked examples and no-op heartbeat; mandatory human review before commercial action. No independent factual verification or clearance. Before relaying another agent's answer, use an external evidence-review boundary to check the claims against supplied source text. An A2A-compatible relay-readiness gate for agent-to-agent output hand-off: bring the claim set and its evidence; get a machine-actionable verdict — verify_before_relay, block_unsafe_claims, not_decision_ready, or insufficient_information — with the unsafe and weak claims, evidence gaps, and owner actions. Caller-declared evidence is never externally verified here, so allow_relay is never issued: the strongest verdict is verify_before_relay with mandatory human review, and a quote counts as grounded only when its text appears in the cited evidence content. Schema-level and structural only — not factual-truth verification, source retrieval, or an approval.

- **Domain**: `output-verification.agendamcp.dpdns.org`
- **Provider**: Vassiliy Lakhonin (https://github.com/vassiliylakhonin)
- **A2A protocol version**: 1.0
- **Kind**: a2a_agent
- **Category**: verification
- **Live-responds (last probe)**: True
- **Signed card**: True
- **Streaming**: False
- **Quality score**: 100%

## Skills
- **Agent output relay-readiness gate** — Turns another agent's claim set and evidence into a machine-actionable relay verdict — verify_before_relay, block_unsafe_claims, not_decision_ready, or insuffic
- **Pre-action evidence gate** — Routes a caller-controlled action to continue, request_evidence, require_approval, or stop using supplied claim evidence, risk tier, policy checks, and external
- **Evidence gap and orphan-reference analysis** — Finds missing evidence ids, quote-to-reference mismatches, unsupported statements, and weak claims in a caller-supplied claim set. Returns the evidence gaps and

## URLs
- Agent card: https://output-verification.agendamcp.dpdns.org/.well-known/agent-card.json
- Page (HTML): https://agenstry.com/agents/output-verification.agendamcp.dpdns.org
- Documentation: https://github.com/vassiliylakhonin/agenda-intelligence-md/tree/main/schemas/v1