MATCH · EXPLAIN · NEGOTIATE
Curated registry: inspect candidates before selection
Inspect seven synthetic registry entries. Apply hard eligibility gates before ranking and proposing a compatible local contract.
Candidate inspector
Your experiment
Select each registry row and read its capabilities and rejection reasons. Increase metadata TTL and explain why a previously stale record can become eligible without proving that its service is alive.
Ranked eligible candidates
Proposed local contract
Explain the exact score
Latency term = 1 − fixture p95 / 500. Cost term = 1 − fictional cost / 10. Observed-success term = (successes + 1) / (observations + 2). Weighted score = sum(weight × term) / sum(weights). All fixture terms are in [0,1]. If all weights are zero, every score is zero; agent ID gives a deterministic tie-break.
None of these terms can override tenant scope, curator policy, required skill/format/delivery, metadata TTL, cost budget or minimum observations. Inspection playback only reveals the computation; it does not advance metadata age. Use the separate age control for that experiment.
Offline registry-selection policy with synthetic entries, latencies, observations and fictional cost units. This is not a production marketplace, ADK registry API, real Agent Card schema validator, signature verifier, authentication system or remote-agent invocation. Curator approval is a fixture flag, not cryptographic proof. A high historical success estimate does not establish trust, safety or future reliability; no statistical confidence claim is made. Metadata freshness is not a liveness check. A2A does not prescribe this ranking formula or a standard curated-registry API. The local proposed contract is descriptive JSON, not an A2A wire request. Agent discovery and curated registry concepts.
Freshness is not liveness
Inspect the seven synthetic entries and select shade. Its metadata starts at age 180 seconds, so the default sixty-second TTL excludes it even though its invented latency looks attractive. Increase TTL to 180, leave additional age at zero, and inspect eligibility at the inclusive boundary. Add ten elapsed seconds to exclude it again. This experiment changes a metadata policy; it does not check whether that service is reachable, authenticated or healthy now.
Apply hard requirements first
Tenant limits entries to the selected team. Required skill and Output format must be supported by a candidate; Require streaming adds a delivery constraint. Curator approval excludes unapproved fixtures when enabled. Metadata TTL is compared with each entry age plus Additional elapsed time. Cost budget and Minimum observations are separate gates. An attractive score cannot compensate for failing any of these requirements. Select an agent in the inspector to read its exact fields and rejection reasons, including agents that never reach ranking.
Rank only eligible entries
Latency, cost and observed-success weights adjust the three terms shown in the formula. They are relative weights, not probabilities or independent pass thresholds. Setting every weight to zero gives equal zero scores and an agent-ID tie-break. A small observation count can create a misleading-looking success estimate, which is why the minimum-observations gate is separate. Curator approval and historical outcomes are fictional metadata, not verified identity, cryptographic trust or a safety assessment.
Inspect the contract and the clock
Play reveals the six filtering and ranking stages over sixty seconds. Pause freezes the view, Next stage advances inspection, Restart rewinds, Speed changes teaching pace, and the timeline seeks. Restore defaults resets the policy inputs; selecting a row or inspector agent changes which record you examine. Playback does not age metadata: use Additional elapsed time for that. The proposed contract names the selected agent, skill, output format and delivery mode, but no remote negotiation or invocation occurs. An empty contract is an explicit incompatibility result, not a reason to silently ignore a required capability.