{"api":"v1","generated_at":"2026-10-01T05:54:16.825Z","licence":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"TOLL, with a link to the page cited"},"page":"https://tollindex.com/e/saylorinnovations-com-api-kb-agent-evaluation-tests-09e54c","pinned_page":"https://tollindex.com/e/saylorinnovations-com-api-kb-agent-evaluation-tests-09e54c/at/2026-10-01T05-50Z","pinned":false,"method":"https://tollindex.com/ledger/method","snapshot_at":"2026-10-01T05:50:06.230Z","snapshot_stamp":"2026-10-01T05-50Z","endpoint":{"slug":"saylorinnovations-com-api-kb-agent-evaluation-tests-09e54c","canonical_url":"https://saylorinnovations.com/api/kb/agent-evaluation-tests","resource":"https://saylorinnovations.com/api/kb/agent-evaluation-tests","http_method":"GET","type":"http","x402_version":2,"registries":["cdp"],"primary_registry":"cdp","curated_by_coinbase":false,"description":"Agent Evaluation-Test Generator. A procedure for turning an agent specification into a real evaluation suite: translating vague requirements into observable, gradable claims (correct tool/arguments/outcome/refusal/budget), partitioning the case space into normal/boundary/adversarial/permission/cost cases, building safe sandboxed fixtures so evaluation can't cause real side effects, preferring deterministic state/tool-trace graders over LLM-judge-only scoring, running baseline vs candidate with…","service_name":"Saylor Innovations Guide Library","declared_category":null,"declared_tags":["agent-evaluation","regression-testing","llm-testing","safety-gates","release-process"],"route_template":null,"registry_updated":"2026-09-25T20:48:02.047Z"},"derived":{"note":"fields no registry supplies; TOLL derives them and marks them derived on the page","title":"kb agent evaluation tests","category":"inference","first_observed_by_toll":"2026-09-24T17:09:13.017Z","last_observed_by_toll":"2026-10-01T05:50:06.230Z","observation_began":"2026-09-10"},"presence":{"listed_now":true,"first_absent_at":null,"delisting_confirmed_at":null,"events":[{"registry":"cdp","at":"2026-09-24T17:09:13.017Z","event":"listed"}]},"accepts":[{"registry":"cdp","ordinal":0,"network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","asset_name":null,"symbol":"USDC","decimals":6,"amount_display":"0.01 USDC","amount_units":0.01,"decimals_known":true,"pay_to":"7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7","scheme":"exact"},{"registry":"cdp","ordinal":1,"network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","asset":"Es9vMFrzaCERmJfrF4H2FYD4KCoNkY11McCe8BenwNYB","asset_name":null,"symbol":"USDT","decimals":6,"amount_display":"0.01 USDT","amount_units":0.01,"decimals_known":true,"pay_to":"7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7","scheme":"exact"},{"registry":"cdp","ordinal":2,"network":"eip155:8453","asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","asset_name":"USD Coin","symbol":"USDC","decimals":6,"amount_display":"0.01 USDC","amount_units":0.01,"decimals_known":true,"pay_to":"0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa","scheme":"exact"},{"registry":"cdp","ordinal":3,"network":"eip155:137","asset":"0x3c499c542cef5e3811e1192ce70d8cc03d5c3359","asset_name":"USD Coin","symbol":"USDC","decimals":6,"amount_display":"0.01 USDC","amount_units":0.01,"decimals_known":true,"pay_to":"0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa","scheme":"exact"},{"registry":"cdp","ordinal":4,"network":"eip155:42161","asset":"0xaf88d065e77c8cc2239327c5edb3a432268e5831","asset_name":"USD Coin","symbol":"USDC","decimals":6,"amount_display":"0.01 USDC","amount_units":0.01,"decimals_known":true,"pay_to":"0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa","scheme":"exact"},{"registry":"cdp","ordinal":5,"network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","asset":"So11111111111111111111111111111111111111112","asset_name":null,"symbol":null,"decimals":null,"amount_display":"79151 smallest units, decimals unknown","amount_units":null,"decimals_known":false,"pay_to":"7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7","scheme":"exact"}],"counters":{"observed_at":"2026-10-01T05:50:06.230Z","calls_30d":2,"unique_payers_30d":1,"last_called_at":"2026-09-25T20:48:01.864Z"},"validation":{"latest":{"observed_at":"2026-09-30T05:42:08.748Z","state":"pass","failed_checks":[],"endpoint_http_status":402,"run_id":"daily-2026-09-30"},"uptime":[{"days":7,"observed":5,"passed":5,"ratio":1},{"days":30,"observed":5,"passed":5,"ratio":1},{"days":90,"observed":5,"passed":5,"ratio":1}],"history_90d":[{"observed_at":"2026-09-30T05:42:08.748Z","state":"pass","failed_checks":[],"run_id":"daily-2026-09-30","state_changed":false},{"observed_at":"2026-09-29T18:02:44.598Z","state":"pass","failed_checks":[],"run_id":"daily-2026-09-29","state_changed":false},{"observed_at":"2026-09-28T03:56:05.331Z","state":"pass","failed_checks":[],"run_id":"daily-2026-09-28","state_changed":false},{"observed_at":"2026-09-25T19:38:22.181Z","state":"pass","failed_checks":[],"run_id":"daily-2026-09-25","state_changed":false},{"observed_at":"2026-09-25T19:15:16.716Z","state":"pass","failed_checks":[],"run_id":"new-after-daily-2026-09-24","state_changed":true}]},"seller":{"wallet":"7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7","page":"https://tollindex.com/seller/7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7","endpoints":397,"hosts":1},"reports":0,"registry_record":{"cdp":[{"tags":["agent-evaluation","regression-testing","llm-testing","safety-gates","release-process"],"type":"http","accepts":[{"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","extra":{"memo":"saylor:agent-evaluation-tests","session":"eyJhcnRpY2xlSWQiOiJhZ2VudC1ldmFsdWF0aW9uLXRlc3RzIiwicmVmZXJlbmNlIjoiRk15aTRQUHlNUGtNOGNhS0VOVlNDTm9ldkFMbUJMS3JzMkRtTVRtVG1Wd2ciLCJyZWNpcGllbnQiOiI3TFNqZnJKZjhmTnNCOFZBOXU3TjNXRW4yNXNtUUxwb2IzU3Z5VXZYYWN5NyIsIm1pbnQiOiJFUGpGV2RkNUF1ZnFTU3FlTTJxTjF4enliYXBDOEc0d0VHR2tad3lURHQxdiIsIm1pbkFtb3VudCI6MTAwMDAsImV4cCI6MTc5MDM2OTQwMTk5OH0.ErCKIJAubhAWBuRvPZX5CzyUOh6u1yecC0LdxY4gT50","feePayer":"BENrLoUbndxoNMUS5JXApGMtNykLjFXXixMtpDwDR9SP","reference":"FMyi4PPyMPkM8caKENVSCNoevALmBLKrs2DmMTmTmVwg"},"payTo":"7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7","amount":"10000","scheme":"exact","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","maxTimeoutSeconds":120},{"asset":"Es9vMFrzaCERmJfrF4H2FYD4KCoNkY11McCe8BenwNYB","extra":{"memo":"saylor:agent-evaluation-tests","session":"eyJhcnRpY2xlSWQiOiJhZ2VudC1ldmFsdWF0aW9uLXRlc3RzIiwicmVmZXJlbmNlIjoiQXdQendYbWZVTFBZWURTVGpzUGprS2dwOXhRNlFja2s0bkJWQTNGQUxOOFIiLCJyZWNpcGllbnQiOiI3TFNqZnJKZjhmTnNCOFZBOXU3TjNXRW4yNXNtUUxwb2IzU3Z5VXZYYWN5NyIsIm1pbnQiOiJFczl2TUZyemFDRVJtSmZyRjRIMkZZRDRLQ29Oa1kxMU1jQ2U4QmVud05ZQiIsIm1pbkFtb3VudCI6MTAwMDAsImV4cCI6MTc5MDM2OTQwMTk5OH0.oRqMUirjAHrjNf3QDg9YryravsIKmCeNt4HM1Builcw","feePayer":"BENrLoUbndxoNMUS5JXApGMtNykLjFXXixMtpDwDR9SP","reference":"AwPzwXmfULPYYDSTjsPjkKgp9xQ6Qckk4nBVA3FALN8R"},"payTo":"7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7","amount":"10000","scheme":"exact","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","maxTimeoutSeconds":120},{"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","extra":{"memo":"saylor:agent-evaluation-tests","name":"USD Coin","note":"Base settles through an x402 facilitator. Send payload.signature and payload.authorization (EIP-3009); there is no self-submitted path on this network.","version":"2","facilitatorOnly":true,"assetTransferMethod":"eip3009"},"payTo":"0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa","amount":"10000","scheme":"exact","network":"eip155:8453","maxTimeoutSeconds":120},{"asset":"0x3c499c542cEF5E3811e1192ce70d8cC03d5c3359","extra":{"memo":"saylor:agent-evaluation-tests","name":"USD Coin","note":"Polygon settles through an x402 facilitator. Send payload.signature and payload.authorization (EIP-3009); there is no self-submitted path on this network.","version":"2","facilitatorOnly":true,"assetTransferMethod":"eip3009"},"payTo":"0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa","amount":"10000","scheme":"exact","network":"eip155:137","maxTimeoutSeconds":120},{"asset":"0xaf88d065e77c8cC2239327C5EDb3A432268e5831","extra":{"memo":"saylor:agent-evaluation-tests","name":"USD Coin","note":"Arbitrum settles through an x402 facilitator. Send payload.signature and payload.authorization (EIP-3009); there is no self-submitted path on this network.","version":"2","facilitatorOnly":true,"assetTransferMethod":"eip3009"},"payTo":"0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa","amount":"10000","scheme":"exact","network":"eip155:42161","maxTimeoutSeconds":120},{"asset":"So11111111111111111111111111111111111111112","extra":{"memo":"saylor:agent-evaluation-tests","note":"Native SOL: send lamports with a system transfer, not an SPL transfer. Price is quoted live and this quote expires in 120s.","native":true,"session":"eyJhcnRpY2xlSWQiOiJhZ2VudC1ldmFsdWF0aW9uLXRlc3RzIiwicmVmZXJlbmNlIjoiRkM1c2lZZUU5YW9BUk1yWG54RXFCNVlCRnVYV1MzdE1FTDdLQzJoNThRb1UiLCJyZWNpcGllbnQiOiI3TFNqZnJKZjhmTnNCOFZBOXU3TjNXRW4yNXNtUUxwb2IzU3Z5VXZYYWN5NyIsIm1pbnQiOm51bGwsIm1pbkFtb3VudCI6NzkxNTEsImV4cCI6MTc5MDM2OTQwMTk5OH0.UEO6Le3RZL_I5i7TvjnM-HKcI9F5PIV85Uk6NaaR9LQ","reference":"FC5siYeE9aoARMrXnxEqB5YBFuXWS3tMEL7KC2h58QoU","solUsdPrice":122.55,"quotedLamports":"81599"},"payTo":"7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7","amount":"79151","scheme":"exact","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","maxTimeoutSeconds":120}],"iconUrl":"https://res.cloudinary.com/bdb-prod/image/upload/c_fill,ar_1:1,w_256,h_256,f_auto,q_auto/v1790235422/bazaar-icons/bc5e2b3d111ebbef.jpg","quality":{"lastCalledAt":"2026-09-25T20:48:01.864Z","l30DaysTotalCalls":2,"l30DaysUniquePayers":1},"resource":"https://saylorinnovations.com/api/kb/agent-evaluation-tests","extensions":{"bazaar":{"info":{"input":{"type":"http","method":"GET"},"output":{"type":"json","example":{"c":"AI & Agents","t":"Agent Evaluation-Test Generator","id":"agent-evaluation-tests","body":"A procedure for turning an agent specification into a real evaluation suite: translating vague requirements into observable, gradable claims (correct tool/arguments/outcome/refusal/budget), partitioning the case space into normal/boundary/adversarial/permission/cost cases, building safe sandboxed fixtures so evaluation can't cause real side effects, preferring deterministic state/tool-trace graders over LLM-judge-only scoring, running baseline vs candidate with repeats to quantify variance, and converting every production incident into a permanent regression case with a zero-tolerance gate for critical failures."}}},"schema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","POST","PUT","PATCH","DELETE","HEAD"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string","const":"json"},"example":{"type":"object","required":["id","t","c","body"],"properties":{"c":{"type":"string"},"t":{"type":"string"},"id":{"type":"string"},"body":{"type":"string"},"price":{"type":["number","null"]},"license":{"type":"string"}}}}}}}}},"description":"Agent Evaluation-Test Generator. A procedure for turning an agent specification into a real evaluation suite: translating vague requirements into observable, gradable claims (correct tool/arguments/outcome/refusal/budget), partitioning the case space into normal/boundary/adversarial/permission/cost cases, building safe sandboxed fixtures so evaluation can't cause real side effects, preferring deterministic state/tool-trace graders over LLM-judge-only scoring, running baseline vs candidate with…","lastUpdated":"2026-09-25T20:48:02.047Z","serviceName":"Saylor Innovations Guide Library","x402Version":2}]}}