Agent EvidencePortable trust records for agent work.

Make answers, artifacts, tool decisions, reviews, redactions, and replays auditable without turning evidence into a UI, runtime, trace backend, or storage system.

Claim-level grounding

Connect each claim to supporting, contradicting, qualifying, or background evidence instead of relying on loose citations.

Provenance that survives review

Preserve source, tool, model, artifact, human, peer-agent, runtime, trace, and span refs as a portable production graph.

Verification is not review

Keep automated checks, human verdicts, waivers, rubrics, and sign-off facts separate but linked.

Replay honesty

Describe what can be reconstructed, what is approximate, and which facts are unavailable, expired, redacted, or not collected.

Redaction-aware export

Share audit packs with stable ids, hashes, schemas, access metadata, and explicit redaction records.

AI-friendly docs

Publish llms.txt, llms-full.txt, public JSON Schemas, examples, and versioned snapshots for agent consumption.

What Agent Evidence Defines

Agent Evidence is the trust layer around agent work. It packages the facts needed to inspect, verify, review, replay, redact, and export an agent outcome.

Contract	What it answers
Evidence Pack	What scoped outcome is being audited, and how complete is the evidence?
Claim Map	Which claims were made, and how is each claim supported or challenged?
Source Map	Which sources were selected, omitted, stale, contradicted, or unavailable?
Provenance Chain	Which tools, models, artifacts, humans, peers, and runtime steps produced the outcome?
Verification and Review	Which checks ran, and who or what issued a verdict?
Replay Case	What can be reconstructed, and which facts are missing?
Redaction and Privacy	What was transformed or withheld before sharing?
Export Manifest	Which files, schemas, hashes, access rules, and completeness states were exported?

Start Here

中文入口

LLM Entrypoints

llms.txt: concise navigation index for AI clients.
llms-full.txt: current English documentation concatenated with source URLs.
llm.txt and llm-full.txt: compatibility aliases.

Agent Standards Ecosystem

Agent Evidence is part of a connected standards family:

See the Agent standards ecosystem page for mutual links and future standard candidates.