{"id":"27d4197c23d465e16094baaf79de1ba3c2a04d66eca773d55729f56f6c036195","title":"Cursor introduces the Agent SDK for building and deploying agents in code","argument":"Cursor introduces the Agent SDK, a framework for defining agents in code and deploying them to Cursor infrastructure. Cursor says agents can respond to team events, follow policies teams can inspect and change, and hand work to specialized agents or subagents.\n\nCursor describes kb-reviewer as a team-built example, created in about a day to check every pull request in Cursor's main codebase against lessons in a knowledge base. It flags changes that contradict a recorded lesson, cites the note behind each finding, and encourages engineers to reconcile reported discrepancies. As an Escape Meridian interpretation, this example illustrates Cursor's argument that teams can tailor agents to their workflows and carry prior decisions into code review. The post does not report an independent evaluation of the agent's accuracy or effects.\n\nCursor says the SDK includes evals and event replay. The post describes agents' instructions, tools, connections to outside services, and evals as code that can go through the same version control and review process as other software. It says agents can run on Cursor infrastructure or a team's own infrastructure.\n\nHow well do agents built with the SDK perform on real team workflows, including whether their findings and policy decisions are reliable?","topicIds":["intelligence-and-discovery","work-and-agency"],"domain":"work","claimType":"attributed reading","limits":"This is a Cursor product announcement; it offers no independent evaluation of agent accuracy, reliability, or effects on team workflows. The kb-reviewer account describes a Cursor team's own use and does not report measured outcomes. The PGA Tour software development factory example includes a testimonial from PGA America Principal Engineer Michael Gyarmathy, not independent performance evidence.","speaker":{"name":"Rustam Lalkaka","roleAtSource":"Article author"},"source":{"title":"Introducing the Agent SDK · Cursor","publisher":"Cursor","format":"Article","url":"https://cursor.com/blog/agent-sdk","publishedAt":"2026-10-20T12:00:00.000Z","dateBasis":"Date stated by the publisher."},"evidence":[{"text":"Cursor announces the Agent SDK as a framework for defining agents in code and deploying them to Cursor infrastructure.","excerpt":"Today, we're releasing the Agent SDK, the framework we use to build our own managed agents like Bugbot, Security Reviewer, and Rollouts.","url":"https://cursor.com/blog/agent-sdk","relationship":"Source-stated"},{"text":"Cursor says agents can respond to team events and follow inspectable, changeable policies.","excerpt":"They respond to the events your team already handles and follow policies your team can inspect and change.","url":"https://cursor.com/blog/agent-sdk","relationship":"Source-stated"},{"text":"Cursor presents kb-reviewer as a team-built agent that checks pull requests against the team's recorded lessons and cites supporting notes.","excerpt":"It now runs on every PR in their main codebase, flags changes that contradict a recorded lesson, cites the note behind each finding, and encourages engineers to reconcile the discrepancies it reports.","url":"https://cursor.com/blog/agent-sdk","relationship":"Source-stated"},{"text":"Cursor says the SDK supports evals and event replay, and describes deployment both on Cursor infrastructure and on a team's own infrastructure.","excerpt":"The Agent SDK also supports evals and event replay out of the box, allowing for rapid development with assurances that critical workflows execute the way you expect.","url":"https://cursor.com/blog/agent-sdk","relationship":"Source-stated"},{"text":"The post's examples illustrate Cursor's claim that agents can be tailored to team workflows, but do not independently establish their accuracy or effects.","excerpt":"With the Agent SDK, they built kb-reviewer in about a day.","url":"https://cursor.com/blog/agent-sdk","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"found","sourceUrl":"https://cursor.com/blog/agent-sdk","checkedAt":"2026-11-05T03:54:03.940Z","items":[{"type":"image","url":"https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/OG%20Images/agent-sdk-blog-og-WlJMIsDgzkUUfvyf1R9PJSIfytr7Sx.png","sourceUrl":"https://cursor.com/blog/agent-sdk","attribution":"Cursor","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-05T03:54:04.098Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How well do agents built with the SDK perform on real team workflows, including whether their findings and policy decisions are reliable?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Cursor introduces the Agent SDK for building and deploying agents in code","summary":"Cursor introduces the Agent SDK, a framework for defining agents in code and deploying them to Cursor infrastructure. Cursor says agents can respond to team events, follow policies teams can inspect and change, and hand work to specialized agents or subagents.\n\nCursor describes kb-reviewer as a team-built example, created in about a day to check every pull request in Cursor's main codebase against lessons in a knowledge base. It flags changes that contradict a recorded lesson, cites the note behind each finding, and encourages engineers to reconcile reported discrepancies. As an Escape Meridian interpretation, this example illustrates Cursor's argument that teams can tailor agents to their workflows and carry prior decisions into code review. The post does not report an independent evaluation of the agent's accuracy or effects.\n\nCursor says the SDK includes evals and event replay. The post describes agents' instructions, tools, connections to outside services, and evals as code that can go through the same version control and review process as other software. It says agents can run on Cursor infrastructure or a team's own infrastructure.\n\nHow well do agents built with the SDK perform on real team workflows, including whether their findings and policy decisions are reliable?","question":"How well do agents built with the SDK perform on real team workflows, including whether their findings and policy decisions are reliable?","claims":[{"text":"Cursor announces the Agent SDK as a framework for defining agents in code and deploying them to Cursor infrastructure.","excerpt":"Today, we're releasing the Agent SDK, the framework we use to build our own managed agents like Bugbot, Security Reviewer, and Rollouts.","support":"source-stated"},{"text":"Cursor says agents can respond to team events and follow inspectable, changeable policies.","excerpt":"They respond to the events your team already handles and follow policies your team can inspect and change.","support":"source-stated"},{"text":"Cursor presents kb-reviewer as a team-built agent that checks pull requests against the team's recorded lessons and cites supporting notes.","excerpt":"It now runs on every PR in their main codebase, flags changes that contradict a recorded lesson, cites the note behind each finding, and encourages engineers to reconcile the discrepancies it reports.","support":"source-stated"},{"text":"Cursor says the SDK supports evals and event replay, and describes deployment both on Cursor infrastructure and on a team's own infrastructure.","excerpt":"The Agent SDK also supports evals and event replay out of the box, allowing for rapid development with assurances that critical workflows execute the way you expect.","support":"source-stated"},{"text":"The post's examples illustrate Cursor's claim that agents can be tailored to team workflows, but do not independently establish their accuracy or effects.","excerpt":"With the Agent SDK, they built kb-reviewer in about a day.","support":"interpretation"}],"limitations":["This is a Cursor product announcement; it offers no independent evaluation of agent accuracy, reliability, or effects on team workflows.","The kb-reviewer account describes a Cursor team's own use and does not report measured outcomes.","The PGA Tour software development factory example includes a testimonial from PGA America Principal Engineer Michael Gyarmathy, not independent performance evidence."],"mediaId":"ea41a986fe71530705d404a78abe5b69b65db5b8b1f8f056c2242994f5f3b2db","correctionReason":null,"id":"27d4197c23d465e16094baaf79de1ba3c2a04d66eca773d55729f56f6c036195","publicationId":"ed06e261-2ba2-43f2-8ec8-3b23447c51b8","version":1,"sourceUrl":"https://cursor.com/blog/agent-sdk","sourceTitle":"Introducing the Agent SDK · Cursor","publisher":"Cursor","publishedAt":"2026-10-20T12:00:00.000Z","originalPublished":{"value":"2026-10-20T12:00:00.000Z","precision":"instant","basis":"publisher_page"},"firstObservedAt":"2026-10-26T19:21:22.331Z","createdAt":"2026-11-05T03:54:58.277Z","historical":true,"entityIds":["cursor"],"topicIds":["intelligence-and-discovery","work-and-agency"],"media":[{"id":"ea41a986fe71530705d404a78abe5b69b65db5b8b1f8f056c2242994f5f3b2db","kind":"article","url":"https://cursor.com/blog/agent-sdk","sourceUrl":"https://cursor.com/blog/agent-sdk","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-05T03:54:04.098Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."},{"id":"9fb7a51b770425b98496986f09d1435dcc30e2edfd3029ea7f1fb3886463cc80","kind":"image","url":"https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/OG%20Images/agent-sdk-blog-og-WlJMIsDgzkUUfvyf1R9PJSIfytr7Sx.png","sourceUrl":"https://cursor.com/blog/agent-sdk","label":"View source image","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-05T03:54:04.098Z","method":"publisher_association_and_head","contentType":"image/png","cacheUntil":1793851144098},"recommendationReason":"Observed on the acquired publisher source; availability checked."}],"sourceMedia":{"status":"found","sourceUrl":"https://cursor.com/blog/agent-sdk","checkedAt":"2026-11-05T03:54:03.940Z","items":[{"type":"image","url":"https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/OG%20Images/agent-sdk-blog-og-WlJMIsDgzkUUfvyf1R9PJSIfytr7Sx.png","sourceUrl":"https://cursor.com/blog/agent-sdk","attribution":"Cursor","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-05T03:54:04.098Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"ea41a986fe71530705d404a78abe5b69b65db5b8b1f8f056c2242994f5f3b2db","confidence":0.87,"provider":"typesafe","model":"jev-1.13.0","inputHash":"a69db1b7591200a6f1fcbab2ff951754c750681182ad4c7de9337354c0d8e381","decidedAt":"2026-11-05T03:54:05.317Z"},"provenance":{"textHash":"b39117e61867f46e7e10198ffa583c7c8f89b2c239cee2b3af6715f8ed6ba606","observationId":"383d49bbd0541bb5f9951f9ea040031d5b76541e0cc5645557371e780c212316","retrievedAt":"2026-11-05T03:54:03.940Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"0d08fad2-1d5b-45a4-810c-8ff4a6e70539"},"reviewer":{"model":"gpt-6-luna","runId":"208f8293-5434-4566-8eab-2e57c947acaa"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-05T03:54:58.277Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Rustam Lalkaka","url":null,"kind":"Person"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Rustam Lalkaka","url":null,"kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Rustam Lalkaka","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://cursor.com/blog/agent-sdk","locator":"document/html[1]/body[1]/main[23]/script[0]@21976.author"},"assertionId":"90b517feb448e6f5f313cf62f61a0ce6397008f2b7e11938c5f09381214c7163:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-05T03:54:03.940Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"90b517feb448e6f5f313cf62f61a0ce6397008f2b7e11938c5f09381214c7163","sourceUrl":"https://cursor.com/blog/agent-sdk","contentSha256":"a8624c2e3425afa5a8f1f468574269cc537397cf79c28d3f0c8a5a537a3d6d84","textHash":"b39117e61867f46e7e10198ffa583c7c8f89b2c239cee2b3af6715f8ed6ba606","observedAt":"2026-11-05T03:54:03.940Z"}},{"actor":{"name":"Rustam Lalkaka","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Rustam Lalkaka","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://cursor.com/blog/agent-sdk","locator":"head/meta[name=author|citation_author]"},"assertionId":"90b517feb448e6f5f313cf62f61a0ce6397008f2b7e11938c5f09381214c7163:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-05T03:54:03.940Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"90b517feb448e6f5f313cf62f61a0ce6397008f2b7e11938c5f09381214c7163","sourceUrl":"https://cursor.com/blog/agent-sdk","contentSha256":"a8624c2e3425afa5a8f1f468574269cc537397cf79c28d3f0c8a5a537a3d6d84","textHash":"b39117e61867f46e7e10198ffa583c7c8f89b2c239cee2b3af6715f8ed6ba606","observedAt":"2026-11-05T03:54:03.940Z"}}],"participationCoverage":{"total":2,"returned":2,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://cursor.com/blog/agent-sdk","snapshotId":"90b517feb448e6f5f313cf62f61a0ce6397008f2b7e11938c5f09381214c7163","contentSha256":"a8624c2e3425afa5a8f1f468574269cc537397cf79c28d3f0c8a5a537a3d6d84","textHash":"b39117e61867f46e7e10198ffa583c7c8f89b2c239cee2b3af6715f8ed6ba606","observedAt":"2026-11-05T03:54:03.940Z","basis":"publisher-page-metadata","sourceLinks":7,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/27d4197c23d465e16094baaf79de1ba3c2a04d66eca773d55729f56f6c036195/source"}},"canonicalUrl":"https://escapemeridian.com/readings/cursor-introduces-the-agent-sdk-for-building-and-deploying-27d4197c","formats":{"html":"/readings/cursor-introduces-the-agent-sdk-for-building-and-deploying-27d4197c","markdown":"/readings/cursor-introduces-the-agent-sdk-for-building-and-deploying-27d4197c.md","json":"/readings/cursor-introduces-the-agent-sdk-for-building-and-deploying-27d4197c.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-evals","name":"Evals","explanation":"Structured tests of what an AI system can do or how it behaves, run before or after release.","referenceUrl":"https://developers.google.com/machine-learning/glossary#evals"}],"entities":[{"id":"cursor","name":"Cursor","kind":"organization","context":"Cursor makes an AI coding environment and publishes evaluations of agents working on software tasks.","referenceUrls":["https://cursor.com/","https://cursor.com/evals","https://cursor.com/blog/real-time-rl-for-composer"],"path":"/entities/cursor","json":"/entities/cursor.json","markdown":"/entities/cursor.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"27d4197c23d465e16094baaf79de1ba3c2a04d66eca773d55729f56f6c036195","revision":"ed06e261-2ba2-43f2-8ec8-3b23447c51b8","revisionKind":"publication-id","title":"Cursor introduces the Agent SDK for building and deploying agents in code","url":"https://escapemeridian.com/readings/cursor-introduces-the-agent-sdk-for-building-and-deploying-27d4197c"},"source":{"type":"source","id":"https://cursor.com/blog/agent-sdk","revision":"b39117e61867f46e7e10198ffa583c7c8f89b2c239cee2b3af6715f8ed6ba606","revisionKind":"sha256-source-text","title":"Introducing the Agent SDK · Cursor","url":"https://cursor.com/blog/agent-sdk"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"27d4197c23d465e16094baaf79de1ba3c2a04d66eca773d55729f56f6c036195","title":"Cursor introduces the Agent SDK for building and deploying agents in code","argument":"Cursor introduces the Agent SDK, a framework for defining agents in code and deploying them to Cursor infrastructure. Cursor says agents can respond to team events, follow policies teams can inspect and change, and hand work to specialized agents or subagents.\n\nCursor describes kb-reviewer as a team-built example, created in about a day to check every pull request in Cursor's main codebase against lessons in a knowledge base. It flags changes that contradict a recorded lesson, cites the note behind each finding, and encourages engineers to reconcile reported discrepancies. As an Escape Meridian interpretation, this example illustrates Cursor's argument that teams can tailor agents to their workflows and carry prior decisions into code review. The post does not report an independent evaluation of the agent's accuracy or effects.\n\nCursor says the SDK includes evals and event replay. The post describes agents' instructions, tools, connections to outside services, and evals as code that can go through the same version control and review process as other software. It says agents can run on Cursor infrastructure or a team's own infrastructure.\n\nHow well do agents built with the SDK perform on real team workflows, including whether their findings and policy decisions are reliable?","topicIds":["intelligence-and-discovery","work-and-agency"],"domain":"work","claimType":"attributed reading","limits":"This is a Cursor product announcement; it offers no independent evaluation of agent accuracy, reliability, or effects on team workflows. The kb-reviewer account describes a Cursor team's own use and does not report measured outcomes. The PGA Tour software development factory example includes a testimonial from PGA America Principal Engineer Michael Gyarmathy, not independent performance evidence.","speaker":{"name":"Rustam Lalkaka","roleAtSource":"Article author"},"source":{"title":"Introducing the Agent SDK · Cursor","publisher":"Cursor","format":"Article","url":"https://cursor.com/blog/agent-sdk","publishedAt":"2026-10-20T12:00:00.000Z","dateBasis":"Date stated by the publisher."},"evidence":[{"text":"Cursor announces the Agent SDK as a framework for defining agents in code and deploying them to Cursor infrastructure.","excerpt":"Today, we're releasing the Agent SDK, the framework we use to build our own managed agents like Bugbot, Security Reviewer, and Rollouts.","url":"https://cursor.com/blog/agent-sdk","relationship":"Source-stated"},{"text":"Cursor says agents can respond to team events and follow inspectable, changeable policies.","excerpt":"They respond to the events your team already handles and follow policies your team can inspect and change.","url":"https://cursor.com/blog/agent-sdk","relationship":"Source-stated"},{"text":"Cursor presents kb-reviewer as a team-built agent that checks pull requests against the team's recorded lessons and cites supporting notes.","excerpt":"It now runs on every PR in their main codebase, flags changes that contradict a recorded lesson, cites the note behind each finding, and encourages engineers to reconcile the discrepancies it reports.","url":"https://cursor.com/blog/agent-sdk","relationship":"Source-stated"},{"text":"Cursor says the SDK supports evals and event replay, and describes deployment both on Cursor infrastructure and on a team's own infrastructure.","excerpt":"The Agent SDK also supports evals and event replay out of the box, allowing for rapid development with assurances that critical workflows execute the way you expect.","url":"https://cursor.com/blog/agent-sdk","relationship":"Source-stated"},{"text":"The post's examples illustrate Cursor's claim that agents can be tailored to team workflows, but do not independently establish their accuracy or effects.","excerpt":"With the Agent SDK, they built kb-reviewer in about a day.","url":"https://cursor.com/blog/agent-sdk","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"found","sourceUrl":"https://cursor.com/blog/agent-sdk","checkedAt":"2026-11-05T03:54:03.940Z","items":[{"type":"image","url":"https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/OG%20Images/agent-sdk-blog-og-WlJMIsDgzkUUfvyf1R9PJSIfytr7Sx.png","sourceUrl":"https://cursor.com/blog/agent-sdk","attribution":"Cursor","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-05T03:54:04.098Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How well do agents built with the SDK perform on real team workflows, including whether their findings and policy decisions are reliable?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Cursor introduces the Agent SDK for building and deploying agents in code","summary":"Cursor introduces the Agent SDK, a framework for defining agents in code and deploying them to Cursor infrastructure. Cursor says agents can respond to team events, follow policies teams can inspect and change, and hand work to specialized agents or subagents.\n\nCursor describes kb-reviewer as a team-built example, created in about a day to check every pull request in Cursor's main codebase against lessons in a knowledge base. It flags changes that contradict a recorded lesson, cites the note behind each finding, and encourages engineers to reconcile reported discrepancies. As an Escape Meridian interpretation, this example illustrates Cursor's argument that teams can tailor agents to their workflows and carry prior decisions into code review. The post does not report an independent evaluation of the agent's accuracy or effects.\n\nCursor says the SDK includes evals and event replay. The post describes agents' instructions, tools, connections to outside services, and evals as code that can go through the same version control and review process as other software. It says agents can run on Cursor infrastructure or a team's own infrastructure.\n\nHow well do agents built with the SDK perform on real team workflows, including whether their findings and policy decisions are reliable?","question":"How well do agents built with the SDK perform on real team workflows, including whether their findings and policy decisions are reliable?","claims":[{"text":"Cursor announces the Agent SDK as a framework for defining agents in code and deploying them to Cursor infrastructure.","excerpt":"Today, we're releasing the Agent SDK, the framework we use to build our own managed agents like Bugbot, Security Reviewer, and Rollouts.","support":"source-stated"},{"text":"Cursor says agents can respond to team events and follow inspectable, changeable policies.","excerpt":"They respond to the events your team already handles and follow policies your team can inspect and change.","support":"source-stated"},{"text":"Cursor presents kb-reviewer as a team-built agent that checks pull requests against the team's recorded lessons and cites supporting notes.","excerpt":"It now runs on every PR in their main codebase, flags changes that contradict a recorded lesson, cites the note behind each finding, and encourages engineers to reconcile the discrepancies it reports.","support":"source-stated"},{"text":"Cursor says the SDK supports evals and event replay, and describes deployment both on Cursor infrastructure and on a team's own infrastructure.","excerpt":"The Agent SDK also supports evals and event replay out of the box, allowing for rapid development with assurances that critical workflows execute the way you expect.","support":"source-stated"},{"text":"The post's examples illustrate Cursor's claim that agents can be tailored to team workflows, but do not independently establish their accuracy or effects.","excerpt":"With the Agent SDK, they built kb-reviewer in about a day.","support":"interpretation"}],"limitations":["This is a Cursor product announcement; it offers no independent evaluation of agent accuracy, reliability, or effects on team workflows.","The kb-reviewer account describes a Cursor team's own use and does not report measured outcomes.","The PGA Tour software development factory example includes a testimonial from PGA America Principal Engineer Michael Gyarmathy, not independent performance evidence."],"mediaId":"ea41a986fe71530705d404a78abe5b69b65db5b8b1f8f056c2242994f5f3b2db","correctionReason":null,"id":"27d4197c23d465e16094baaf79de1ba3c2a04d66eca773d55729f56f6c036195","publicationId":"ed06e261-2ba2-43f2-8ec8-3b23447c51b8","version":1,"sourceUrl":"https://cursor.com/blog/agent-sdk","sourceTitle":"Introducing the Agent SDK · Cursor","publisher":"Cursor","publishedAt":"2026-10-20T12:00:00.000Z","originalPublished":{"value":"2026-10-20T12:00:00.000Z","precision":"instant","basis":"publisher_page"},"firstObservedAt":"2026-10-26T19:21:22.331Z","createdAt":"2026-11-05T03:54:58.277Z","historical":true,"entityIds":["cursor"],"topicIds":["intelligence-and-discovery","work-and-agency"],"media":[{"id":"ea41a986fe71530705d404a78abe5b69b65db5b8b1f8f056c2242994f5f3b2db","kind":"article","url":"https://cursor.com/blog/agent-sdk","sourceUrl":"https://cursor.com/blog/agent-sdk","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-05T03:54:04.098Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."},{"id":"9fb7a51b770425b98496986f09d1435dcc30e2edfd3029ea7f1fb3886463cc80","kind":"image","url":"https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/OG%20Images/agent-sdk-blog-og-WlJMIsDgzkUUfvyf1R9PJSIfytr7Sx.png","sourceUrl":"https://cursor.com/blog/agent-sdk","label":"View source image","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-05T03:54:04.098Z","method":"publisher_association_and_head","contentType":"image/png","cacheUntil":1793851144098},"recommendationReason":"Observed on the acquired publisher source; availability checked."}],"sourceMedia":{"status":"found","sourceUrl":"https://cursor.com/blog/agent-sdk","checkedAt":"2026-11-05T03:54:03.940Z","items":[{"type":"image","url":"https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/OG%20Images/agent-sdk-blog-og-WlJMIsDgzkUUfvyf1R9PJSIfytr7Sx.png","sourceUrl":"https://cursor.com/blog/agent-sdk","attribution":"Cursor","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-05T03:54:04.098Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"ea41a986fe71530705d404a78abe5b69b65db5b8b1f8f056c2242994f5f3b2db","confidence":0.87,"provider":"typesafe","model":"jev-1.13.0","inputHash":"a69db1b7591200a6f1fcbab2ff951754c750681182ad4c7de9337354c0d8e381","decidedAt":"2026-11-05T03:54:05.317Z"},"provenance":{"textHash":"b39117e61867f46e7e10198ffa583c7c8f89b2c239cee2b3af6715f8ed6ba606","observationId":"383d49bbd0541bb5f9951f9ea040031d5b76541e0cc5645557371e780c212316","retrievedAt":"2026-11-05T03:54:03.940Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"0d08fad2-1d5b-45a4-810c-8ff4a6e70539"},"reviewer":{"model":"gpt-6-luna","runId":"208f8293-5434-4566-8eab-2e57c947acaa"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-05T03:54:58.277Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Rustam Lalkaka","url":null,"kind":"Person"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Rustam Lalkaka","url":null,"kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Rustam Lalkaka","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://cursor.com/blog/agent-sdk","locator":"document/html[1]/body[1]/main[23]/script[0]@21976.author"},"assertionId":"90b517feb448e6f5f313cf62f61a0ce6397008f2b7e11938c5f09381214c7163:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-05T03:54:03.940Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"90b517feb448e6f5f313cf62f61a0ce6397008f2b7e11938c5f09381214c7163","sourceUrl":"https://cursor.com/blog/agent-sdk","contentSha256":"a8624c2e3425afa5a8f1f468574269cc537397cf79c28d3f0c8a5a537a3d6d84","textHash":"b39117e61867f46e7e10198ffa583c7c8f89b2c239cee2b3af6715f8ed6ba606","observedAt":"2026-11-05T03:54:03.940Z"}},{"actor":{"name":"Rustam Lalkaka","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Rustam Lalkaka","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://cursor.com/blog/agent-sdk","locator":"head/meta[name=author|citation_author]"},"assertionId":"90b517feb448e6f5f313cf62f61a0ce6397008f2b7e11938c5f09381214c7163:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-05T03:54:03.940Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"90b517feb448e6f5f313cf62f61a0ce6397008f2b7e11938c5f09381214c7163","sourceUrl":"https://cursor.com/blog/agent-sdk","contentSha256":"a8624c2e3425afa5a8f1f468574269cc537397cf79c28d3f0c8a5a537a3d6d84","textHash":"b39117e61867f46e7e10198ffa583c7c8f89b2c239cee2b3af6715f8ed6ba606","observedAt":"2026-11-05T03:54:03.940Z"}}],"participationCoverage":{"total":2,"returned":2,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://cursor.com/blog/agent-sdk","snapshotId":"90b517feb448e6f5f313cf62f61a0ce6397008f2b7e11938c5f09381214c7163","contentSha256":"a8624c2e3425afa5a8f1f468574269cc537397cf79c28d3f0c8a5a537a3d6d84","textHash":"b39117e61867f46e7e10198ffa583c7c8f89b2c239cee2b3af6715f8ed6ba606","observedAt":"2026-11-05T03:54:03.940Z","basis":"publisher-page-metadata","sourceLinks":7,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/27d4197c23d465e16094baaf79de1ba3c2a04d66eca773d55729f56f6c036195/source"}}}],"audits":[{"publicationId":"ed06e261-2ba2-43f2-8ec8-3b23447c51b8","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"Claims are attributed to Cursor's announcement. The testimonial is correctly credited to Michael Gyarmathy, Principal Engineer at PGA America. The kb-reviewer example is credited to a Cursor team, and the interpretive sentence is explicitly labeled as Escape Meridian interpretation.","excerpt":"Michael Gyarmathy\nPrincipal Engineer, PGA America"},{"dimension":"summary","status":"pass","explanation":"The reading leads with the actor (Cursor) and the development (the Agent SDK, described plainly as a framework for defining agents in code). It conveys the tailoring argument, the kb-reviewer example, evals, version control and deployment options, and notes the missing independent evaluation. Terms such as evals and event replay could use tooltips, but they do not block understanding. The question follows from the evidence without leading. It does not mention that Cursor builds its own Bugbot and similar agents with this framework, though a claim covers that.","excerpt":"Until now, building one has generally meant adopting a product designed around someone else's workflow or starting from scratch."},{"dimension":"date","status":"pass","explanation":"The originalPublished date of 2026-10-20, based on the publisher page, matches the feed date. Nothing indicates an earlier first publication. The draft makes no conflicting date claim.","excerpt":null},{"dimension":"support","status":"uncertain","explanation":"The summary says kb-reviewer checks every pull request in Cursor's main codebase. The source says a team within Cursor runs it on every PR in their main codebase, which may mean that team's codebase rather than Cursor's overall main codebase. The smallest repair is to say 'the team's main codebase.' The other claims and limitations are supported and appropriately hedged.","excerpt":"It now runs on every PR in their main codebase, flags changes that contradict a recorded lesson"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct link to the original Cursor blog post. It is the most direct way to access the source.","excerpt":null}],"createdAt":"2026-11-05T03:54:58.277Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}