Follow the evidence deeper.
Choose a practice case, run DAID's local checker, or inspect the exact schemas and source revisions.
Run Agent Claim Check v1
Agent Claim Check is DAID's dependency-free, offline and deterministic harness check for one bounded claim and its observable evidence.
node tools/check-agent-claim.mjs examples/agent-claim-check-v1/supported.jsonThe example returns supported. Read that result only with these machine boundaries:
intent_assessment: "not-assessed"
downstream_action_authorized: false
does_not_establish: ["correctness", "safety", "identity", "successful-execution", "authority", "permission"]A supported finding describes only the declared claim/evidence relationship. It is not permission to act.
Guide, examples, and contracts
- Read the canonical Agent Claim Check v1 guide.
- Run the source examples: supported, contradicted, insufficient evidence, and invalid input.
- Inspect the CLI and core.
- Use the canonical input, receipt, and error schemas.
- Review licensing, security reporting, or the existing public-safe Challenge route.
Supporting evidence routes
Each route below has an exact reviewed public revision and a narrow role. This site does not copy or silently extend those projects.
- 01evidencegateRevision-bound receipts, path checks and missing-evidence failure semanticsExact revision
473f9cac98f6 - 02local model reliability exampleGrounded-answer evidence checksExact revision
d4eed6c7bb37 - 03context boundary examplesEvidence-boundary and refusal checksExact revision
c1b5795917f3 - 04agent evidence catalogIdentity-first publisher-claim researchExact revision
576f472e0848 - 05agent action authority examplesAmbiguous external-effect recoveryExact revision
cc0688fba804
Need the complete toolkit?
The Reliability Navigator covers the wider public set of guides, starters and runnable checks. Its route recommendation is not certification that a tool fits every setup.
Open the Reliability Navigator