{"id":"28c24d96d7bfbe4e277162b73a982f1daf52fcbdeae9eec1a19fc2a0b9007599","title":"How Figma’s PMs use AI in their daily work","argument":"Lenny’s Newsletter presents growth product manager Ezra Mechaber describing how Figma PMs use AI in their work. Mechaber says he and fellow PMs turned his personal Claude Code setup into PM OS, a shared repo of 31 skills that the description says every Figma PM uses. The episode preview describes the repo as used by 60+ PMs.\n\nThe examples range from a “chief of staff” setup and a skill Mechaber runs to manage Slack, to bug bashing with Codex. The description also highlights AutoXP, called an automated growth PM, which it says found a “huge win” on its first experiment and runs experiments with one human checkpoint. It offers practical examples of how a team might organize AI-assisted work; the provided page does not establish how broadly the workflows improve results or what the experiment measured.\n\nThe episode description frames PM OS as a repo, not a product, and points to how the skills were built and refined. That makes the account about a shared working setup as well as individual tools. What was the first AutoXP experiment, and what did its human checkpoint review?","topicIds":["work-and-agency"],"domain":"work","claimType":"attributed reading","limits":"The supplied evidence is a publisher-page description, not a transcript; it does not give details of the demonstrations or the speakers’ full explanations. The page does not specify what the first AutoXP experiment tested, how it defined a “huge win,” or what the human checkpoint reviewed. The episode description says every PM at Figma uses PM OS, while its preview describes the repo as used by 60+ PMs; it gives no further account of adoption or usage.","speaker":{"name":"Claire Vo","roleAtSource":"Article author"},"source":{"title":"How Figma’s PMs actually use AI every day | Ezra Mechaber (PM, Figma)","publisher":"Lenny's Newsletter","format":"Article","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","publishedAt":"2026-11-02T13:04:11+00:00","dateBasis":"Date stated by the publisher."},"evidence":[{"text":"Lenny’s Newsletter identifies Ezra Mechaber as a growth product manager at Figma and describes the episode as a demonstration of his AI workflows.","excerpt":"Figma growth PM Ezra Mechaber demos PM OS, a 31-skill repo used by 60+ PMs","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","relationship":"Source-stated"},{"text":"The episode description says Mechaber and fellow PMs developed PM OS from his personal Claude Code setup, as a shared repo of 31 skills.","excerpt":"he and a couple of fellow PMs turned his personal Claude Code setup into PM OS, a shared repo of 31 skills","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","relationship":"Source-stated"},{"text":"The description says every PM at Figma uses PM OS; its episode preview describes the repo as used by 60+ PMs.","excerpt":"a shared repo of 31 skills that every PM at Figma now uses","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","relationship":"Source-stated"},{"text":"The episode description characterizes AutoXP as an automated growth PM and says it found a “huge win” on its first experiment.","excerpt":"AutoXP—an automated growth PM that found a huge win on its very first experiment","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","relationship":"Source-stated"},{"text":"The episode description says AutoXP runs experiments with one human checkpoint.","excerpt":"How AutoXP runs experiments with one human checkpoint","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","relationship":"Source-stated"}],"sourceMedia":{"status":"found","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","checkedAt":"2026-11-04T20:52:37.191Z","items":[{"type":"video","url":"https://www.youtube.com/watch?v=ztt8irafLMQ","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","attribution":"Lenny's Newsletter","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-04T20:52:37.904Z"},{"type":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/11f4fa87-2e46-4a6a-b3ab-6f110e781154_728x524.png","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","attribution":"Lenny's Newsletter","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-04T20:52:37.904Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"What was the first AutoXP experiment, and what did its human checkpoint review?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"How Figma’s PMs use AI in their daily work","summary":"Lenny’s Newsletter presents growth product manager Ezra Mechaber describing how Figma PMs use AI in their work. Mechaber says he and fellow PMs turned his personal Claude Code setup into PM OS, a shared repo of 31 skills that the description says every Figma PM uses. The episode preview describes the repo as used by 60+ PMs.\n\nThe examples range from a “chief of staff” setup and a skill Mechaber runs to manage Slack, to bug bashing with Codex. The description also highlights AutoXP, called an automated growth PM, which it says found a “huge win” on its first experiment and runs experiments with one human checkpoint. It offers practical examples of how a team might organize AI-assisted work; the provided page does not establish how broadly the workflows improve results or what the experiment measured.\n\nThe episode description frames PM OS as a repo, not a product, and points to how the skills were built and refined. That makes the account about a shared working setup as well as individual tools. What was the first AutoXP experiment, and what did its human checkpoint review?","question":"What was the first AutoXP experiment, and what did its human checkpoint review?","claims":[{"text":"Lenny’s Newsletter identifies Ezra Mechaber as a growth product manager at Figma and describes the episode as a demonstration of his AI workflows.","excerpt":"Figma growth PM Ezra Mechaber demos PM OS, a 31-skill repo used by 60+ PMs","support":"source-stated"},{"text":"The episode description says Mechaber and fellow PMs developed PM OS from his personal Claude Code setup, as a shared repo of 31 skills.","excerpt":"he and a couple of fellow PMs turned his personal Claude Code setup into PM OS, a shared repo of 31 skills","support":"source-stated"},{"text":"The description says every PM at Figma uses PM OS; its episode preview describes the repo as used by 60+ PMs.","excerpt":"a shared repo of 31 skills that every PM at Figma now uses","support":"source-stated"},{"text":"The episode description characterizes AutoXP as an automated growth PM and says it found a “huge win” on its first experiment.","excerpt":"AutoXP—an automated growth PM that found a huge win on its very first experiment","support":"source-stated"},{"text":"The episode description says AutoXP runs experiments with one human checkpoint.","excerpt":"How AutoXP runs experiments with one human checkpoint","support":"source-stated"}],"limitations":["The supplied evidence is a publisher-page description, not a transcript; it does not give details of the demonstrations or the speakers’ full explanations.","The page does not specify what the first AutoXP experiment tested, how it defined a “huge win,” or what the human checkpoint reviewed.","The episode description says every PM at Figma uses PM OS, while its preview describes the repo as used by 60+ PMs; it gives no further account of adoption or usage."],"mediaId":"c4cd7eed2a813f19cddb7bc43b96847946181f51eb2d7193c11b4aff75fe4d50","correctionReason":null,"id":"28c24d96d7bfbe4e277162b73a982f1daf52fcbdeae9eec1a19fc2a0b9007599","publicationId":"f6c4760f-d5e2-4b1d-8bda-387b7cca2ff4","version":1,"sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","sourceTitle":"How Figma’s PMs actually use AI every day | Ezra Mechaber (PM, Figma)","publisher":"Lenny's Newsletter","publishedAt":"2026-11-02T13:04:11+00:00","originalPublished":{"value":"2026-11-02T13:04:11+00:00","precision":"instant","basis":"publisher_page"},"firstObservedAt":"2026-11-04T12:33:27.008Z","createdAt":"2026-11-06T20:23:21.793Z","historical":true,"entityIds":["lennys-newsletter"],"topicIds":["work-and-agency"],"media":[{"id":"c4cd7eed2a813f19cddb7bc43b96847946181f51eb2d7193c11b4aff75fe4d50","kind":"article","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-04T20:52:37.904Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."},{"id":"a80e54e1ed5154e3e71d577b10a8d4a983c985c05526db98c453fdf453245b77","kind":"video","url":"https://www.youtube.com/watch?v=ztt8irafLMQ","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","label":"Watch source","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-04T20:52:37.904Z","method":"publisher_association_and_head","contentType":"text/html","cacheUntil":1793825557904},"recommendationReason":"Observed on the acquired publisher source; availability checked."},{"id":"ff673996562c9d2d58dfb444e7ae773473557e95a673c5e1ab274d7292b4a840","kind":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/11f4fa87-2e46-4a6a-b3ab-6f110e781154_728x524.png","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","label":"View source image","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-04T20:52:37.904Z","method":"publisher_association_and_head","contentType":"image/png","cacheUntil":1793825857904},"recommendationReason":"Observed on the acquired publisher source; availability checked."}],"sourceMedia":{"status":"found","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","checkedAt":"2026-11-04T20:52:37.191Z","items":[{"type":"video","url":"https://www.youtube.com/watch?v=ztt8irafLMQ","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","attribution":"Lenny's Newsletter","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-04T20:52:37.904Z"},{"type":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/11f4fa87-2e46-4a6a-b3ab-6f110e781154_728x524.png","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","attribution":"Lenny's Newsletter","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-04T20:52:37.904Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"editorialDecision":{"outcome":"accept","reasonCodes":["useful_perspective"],"rubricVersion":"stream-admission-v5","mediaId":"c4cd7eed2a813f19cddb7bc43b96847946181f51eb2d7193c11b4aff75fe4d50","confidence":0.61,"provider":"typesafe","model":"jev-1.13.0","inputHash":"b20b4f81c4e753507af4643436358a29d1ec31eeb6a2281e2e7d263512d5e2b5","decidedAt":"2026-11-04T21:22:39.206Z"},"provenance":{"textHash":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","observationId":"dba620aacb933c01ac4b337df78782c2111e53065b96e4df66084654b91c30f1","retrievedAt":"2026-11-04T20:52:37.191Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"59e26025-1f37-45d7-8488-0f7c73f8cdd1"},"reviewer":{"model":"gpt-6-luna","runId":"4b39b326-6767-4ffc-8d7c-520c15546626"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-06T20:23:21.793Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Claire Vo","url":"https://substack.com/@clairevo","kind":"Person"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Claire Vo","url":"https://substack.com/@clairevo","kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Claire Vo","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","locator":"document/html[1]/body[2]/div[1]/div[1]/div[1]/script[0]@23426.author"},"assertionId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-04T20:52:37.191Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","contentSha256":"1f0ee8dbf39dbf622b9c52ab2b19380ad8185045606f0c973cb1f5e408789e71","textHash":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","observedAt":"2026-11-04T20:52:37.191Z"}},{"actor":{"name":"Claire Vo","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Claire Vo","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","locator":"head/meta[name=author|citation_author]"},"assertionId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-04T20:52:37.191Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","contentSha256":"1f0ee8dbf39dbf622b9c52ab2b19380ad8185045606f0c973cb1f5e408789e71","textHash":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","observedAt":"2026-11-04T20:52:37.191Z"}},{"actor":{"name":"Lenny's Newsletter","url":"https://www.lennysnewsletter.com/","kind":"unknown","actorId":null},"role":"publisher","scope":{"kind":"publication","locator":null},"literalCredit":"Lenny's Newsletter","status":"stated","provenance":{"basis":"article-publisher","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","locator":"document/html[1]/body[2]/div[1]/div[1]/div[1]/script[0]@23426.publisher"},"assertionId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-04T20:52:37.191Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","contentSha256":"1f0ee8dbf39dbf622b9c52ab2b19380ad8185045606f0c973cb1f5e408789e71","textHash":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","observedAt":"2026-11-04T20:52:37.191Z"}}],"participationCoverage":{"total":3,"returned":3,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":{"name":"Lenny's Newsletter","url":"https://www.lennysnewsletter.com/"},"sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","snapshotId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a","contentSha256":"1f0ee8dbf39dbf622b9c52ab2b19380ad8185045606f0c973cb1f5e408789e71","textHash":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","observedAt":"2026-11-04T20:52:37.191Z","basis":"publisher-page-metadata","sourceLinks":65,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/28c24d96d7bfbe4e277162b73a982f1daf52fcbdeae9eec1a19fc2a0b9007599/source"}},"canonicalUrl":"https://escapemeridian.com/readings/how-figma-s-pms-use-ai-in-their-daily-work-28c24d96","formats":{"html":"/readings/how-figma-s-pms-use-ai-in-their-daily-work-28c24d96","markdown":"/readings/how-figma-s-pms-use-ai-in-their-daily-work-28c24d96.md","json":"/readings/how-figma-s-pms-use-ai-in-their-daily-work-28c24d96.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":[],"entities":[{"id":"lennys-newsletter","name":"Lenny's Newsletter","kind":"organization","context":"Lenny's Newsletter is Lenny Rachitsky's publication and podcast on product management, growth and career questions for product people.","referenceUrls":["https://www.lennysnewsletter.com/","https://www.lennysnewsletter.com/feed"],"path":"/entities/lennys-newsletter","json":"/entities/lennys-newsletter.json","markdown":"/entities/lennys-newsletter.md"},{"id":"claude","name":"Claude","kind":"model","context":"Claude is Anthropic’s family of AI models and assistants for tasks such as writing, analysis and coding.","referenceUrls":["https://claude.com/product/overview","https://www.anthropic.com/news","https://www.anthropic.com/research/team/economics"],"path":"/entities/claude","json":"/entities/claude.json","markdown":"/entities/claude.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"28c24d96d7bfbe4e277162b73a982f1daf52fcbdeae9eec1a19fc2a0b9007599","revision":"f6c4760f-d5e2-4b1d-8bda-387b7cca2ff4","revisionKind":"publication-id","title":"How Figma’s PMs use AI in their daily work","url":"https://escapemeridian.com/readings/how-figma-s-pms-use-ai-in-their-daily-work-28c24d96"},"source":{"type":"source","id":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","revision":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","revisionKind":"sha256-source-text","title":"How Figma’s PMs actually use AI every day | Ezra Mechaber (PM, Figma)","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every"},"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":"28c24d96d7bfbe4e277162b73a982f1daf52fcbdeae9eec1a19fc2a0b9007599","title":"How Figma’s PMs use AI in their daily work","argument":"Lenny’s Newsletter presents growth product manager Ezra Mechaber describing how Figma PMs use AI in their work. Mechaber says he and fellow PMs turned his personal Claude Code setup into PM OS, a shared repo of 31 skills that the description says every Figma PM uses. The episode preview describes the repo as used by 60+ PMs.\n\nThe examples range from a “chief of staff” setup and a skill Mechaber runs to manage Slack, to bug bashing with Codex. The description also highlights AutoXP, called an automated growth PM, which it says found a “huge win” on its first experiment and runs experiments with one human checkpoint. It offers practical examples of how a team might organize AI-assisted work; the provided page does not establish how broadly the workflows improve results or what the experiment measured.\n\nThe episode description frames PM OS as a repo, not a product, and points to how the skills were built and refined. That makes the account about a shared working setup as well as individual tools. What was the first AutoXP experiment, and what did its human checkpoint review?","topicIds":["work-and-agency"],"domain":"work","claimType":"attributed reading","limits":"The supplied evidence is a publisher-page description, not a transcript; it does not give details of the demonstrations or the speakers’ full explanations. The page does not specify what the first AutoXP experiment tested, how it defined a “huge win,” or what the human checkpoint reviewed. The episode description says every PM at Figma uses PM OS, while its preview describes the repo as used by 60+ PMs; it gives no further account of adoption or usage.","speaker":{"name":"Claire Vo","roleAtSource":"Article author"},"source":{"title":"How Figma’s PMs actually use AI every day | Ezra Mechaber (PM, Figma)","publisher":"Lenny's Newsletter","format":"Article","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","publishedAt":"2026-11-02T13:04:11+00:00","dateBasis":"Date stated by the publisher."},"evidence":[{"text":"Lenny’s Newsletter identifies Ezra Mechaber as a growth product manager at Figma and describes the episode as a demonstration of his AI workflows.","excerpt":"Figma growth PM Ezra Mechaber demos PM OS, a 31-skill repo used by 60+ PMs","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","relationship":"Source-stated"},{"text":"The episode description says Mechaber and fellow PMs developed PM OS from his personal Claude Code setup, as a shared repo of 31 skills.","excerpt":"he and a couple of fellow PMs turned his personal Claude Code setup into PM OS, a shared repo of 31 skills","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","relationship":"Source-stated"},{"text":"The description says every PM at Figma uses PM OS; its episode preview describes the repo as used by 60+ PMs.","excerpt":"a shared repo of 31 skills that every PM at Figma now uses","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","relationship":"Source-stated"},{"text":"The episode description characterizes AutoXP as an automated growth PM and says it found a “huge win” on its first experiment.","excerpt":"AutoXP—an automated growth PM that found a huge win on its very first experiment","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","relationship":"Source-stated"},{"text":"The episode description says AutoXP runs experiments with one human checkpoint.","excerpt":"How AutoXP runs experiments with one human checkpoint","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","relationship":"Source-stated"}],"sourceMedia":{"status":"found","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","checkedAt":"2026-11-04T20:52:37.191Z","items":[{"type":"video","url":"https://www.youtube.com/watch?v=ztt8irafLMQ","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","attribution":"Lenny's Newsletter","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-04T20:52:37.904Z"},{"type":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/11f4fa87-2e46-4a6a-b3ab-6f110e781154_728x524.png","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","attribution":"Lenny's Newsletter","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-04T20:52:37.904Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"What was the first AutoXP experiment, and what did its human checkpoint review?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"How Figma’s PMs use AI in their daily work","summary":"Lenny’s Newsletter presents growth product manager Ezra Mechaber describing how Figma PMs use AI in their work. Mechaber says he and fellow PMs turned his personal Claude Code setup into PM OS, a shared repo of 31 skills that the description says every Figma PM uses. The episode preview describes the repo as used by 60+ PMs.\n\nThe examples range from a “chief of staff” setup and a skill Mechaber runs to manage Slack, to bug bashing with Codex. The description also highlights AutoXP, called an automated growth PM, which it says found a “huge win” on its first experiment and runs experiments with one human checkpoint. It offers practical examples of how a team might organize AI-assisted work; the provided page does not establish how broadly the workflows improve results or what the experiment measured.\n\nThe episode description frames PM OS as a repo, not a product, and points to how the skills were built and refined. That makes the account about a shared working setup as well as individual tools. What was the first AutoXP experiment, and what did its human checkpoint review?","question":"What was the first AutoXP experiment, and what did its human checkpoint review?","claims":[{"text":"Lenny’s Newsletter identifies Ezra Mechaber as a growth product manager at Figma and describes the episode as a demonstration of his AI workflows.","excerpt":"Figma growth PM Ezra Mechaber demos PM OS, a 31-skill repo used by 60+ PMs","support":"source-stated"},{"text":"The episode description says Mechaber and fellow PMs developed PM OS from his personal Claude Code setup, as a shared repo of 31 skills.","excerpt":"he and a couple of fellow PMs turned his personal Claude Code setup into PM OS, a shared repo of 31 skills","support":"source-stated"},{"text":"The description says every PM at Figma uses PM OS; its episode preview describes the repo as used by 60+ PMs.","excerpt":"a shared repo of 31 skills that every PM at Figma now uses","support":"source-stated"},{"text":"The episode description characterizes AutoXP as an automated growth PM and says it found a “huge win” on its first experiment.","excerpt":"AutoXP—an automated growth PM that found a huge win on its very first experiment","support":"source-stated"},{"text":"The episode description says AutoXP runs experiments with one human checkpoint.","excerpt":"How AutoXP runs experiments with one human checkpoint","support":"source-stated"}],"limitations":["The supplied evidence is a publisher-page description, not a transcript; it does not give details of the demonstrations or the speakers’ full explanations.","The page does not specify what the first AutoXP experiment tested, how it defined a “huge win,” or what the human checkpoint reviewed.","The episode description says every PM at Figma uses PM OS, while its preview describes the repo as used by 60+ PMs; it gives no further account of adoption or usage."],"mediaId":"c4cd7eed2a813f19cddb7bc43b96847946181f51eb2d7193c11b4aff75fe4d50","correctionReason":null,"id":"28c24d96d7bfbe4e277162b73a982f1daf52fcbdeae9eec1a19fc2a0b9007599","publicationId":"f6c4760f-d5e2-4b1d-8bda-387b7cca2ff4","version":1,"sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","sourceTitle":"How Figma’s PMs actually use AI every day | Ezra Mechaber (PM, Figma)","publisher":"Lenny's Newsletter","publishedAt":"2026-11-02T13:04:11+00:00","originalPublished":{"value":"2026-11-02T13:04:11+00:00","precision":"instant","basis":"publisher_page"},"firstObservedAt":"2026-11-04T12:33:27.008Z","createdAt":"2026-11-06T20:23:21.793Z","historical":true,"entityIds":["lennys-newsletter"],"topicIds":["work-and-agency"],"media":[{"id":"c4cd7eed2a813f19cddb7bc43b96847946181f51eb2d7193c11b4aff75fe4d50","kind":"article","url":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-04T20:52:37.904Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."},{"id":"a80e54e1ed5154e3e71d577b10a8d4a983c985c05526db98c453fdf453245b77","kind":"video","url":"https://www.youtube.com/watch?v=ztt8irafLMQ","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","label":"Watch source","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-04T20:52:37.904Z","method":"publisher_association_and_head","contentType":"text/html","cacheUntil":1793825557904},"recommendationReason":"Observed on the acquired publisher source; availability checked."},{"id":"ff673996562c9d2d58dfb444e7ae773473557e95a673c5e1ab274d7292b4a840","kind":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/11f4fa87-2e46-4a6a-b3ab-6f110e781154_728x524.png","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","label":"View source image","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-04T20:52:37.904Z","method":"publisher_association_and_head","contentType":"image/png","cacheUntil":1793825857904},"recommendationReason":"Observed on the acquired publisher source; availability checked."}],"sourceMedia":{"status":"found","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","checkedAt":"2026-11-04T20:52:37.191Z","items":[{"type":"video","url":"https://www.youtube.com/watch?v=ztt8irafLMQ","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","attribution":"Lenny's Newsletter","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-04T20:52:37.904Z"},{"type":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/11f4fa87-2e46-4a6a-b3ab-6f110e781154_728x524.png","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","attribution":"Lenny's Newsletter","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-04T20:52:37.904Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"editorialDecision":{"outcome":"accept","reasonCodes":["useful_perspective"],"rubricVersion":"stream-admission-v5","mediaId":"c4cd7eed2a813f19cddb7bc43b96847946181f51eb2d7193c11b4aff75fe4d50","confidence":0.61,"provider":"typesafe","model":"jev-1.13.0","inputHash":"b20b4f81c4e753507af4643436358a29d1ec31eeb6a2281e2e7d263512d5e2b5","decidedAt":"2026-11-04T21:22:39.206Z"},"provenance":{"textHash":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","observationId":"dba620aacb933c01ac4b337df78782c2111e53065b96e4df66084654b91c30f1","retrievedAt":"2026-11-04T20:52:37.191Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"59e26025-1f37-45d7-8488-0f7c73f8cdd1"},"reviewer":{"model":"gpt-6-luna","runId":"4b39b326-6767-4ffc-8d7c-520c15546626"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-06T20:23:21.793Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Claire Vo","url":"https://substack.com/@clairevo","kind":"Person"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Claire Vo","url":"https://substack.com/@clairevo","kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Claire Vo","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","locator":"document/html[1]/body[2]/div[1]/div[1]/div[1]/script[0]@23426.author"},"assertionId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-04T20:52:37.191Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","contentSha256":"1f0ee8dbf39dbf622b9c52ab2b19380ad8185045606f0c973cb1f5e408789e71","textHash":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","observedAt":"2026-11-04T20:52:37.191Z"}},{"actor":{"name":"Claire Vo","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Claire Vo","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","locator":"head/meta[name=author|citation_author]"},"assertionId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-04T20:52:37.191Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","contentSha256":"1f0ee8dbf39dbf622b9c52ab2b19380ad8185045606f0c973cb1f5e408789e71","textHash":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","observedAt":"2026-11-04T20:52:37.191Z"}},{"actor":{"name":"Lenny's Newsletter","url":"https://www.lennysnewsletter.com/","kind":"unknown","actorId":null},"role":"publisher","scope":{"kind":"publication","locator":null},"literalCredit":"Lenny's Newsletter","status":"stated","provenance":{"basis":"article-publisher","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","locator":"document/html[1]/body[2]/div[1]/div[1]/div[1]/script[0]@23426.publisher"},"assertionId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-04T20:52:37.191Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a","sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","contentSha256":"1f0ee8dbf39dbf622b9c52ab2b19380ad8185045606f0c973cb1f5e408789e71","textHash":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","observedAt":"2026-11-04T20:52:37.191Z"}}],"participationCoverage":{"total":3,"returned":3,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":{"name":"Lenny's Newsletter","url":"https://www.lennysnewsletter.com/"},"sourceUrl":"https://www.lennysnewsletter.com/p/how-figmas-pms-actually-use-ai-every","snapshotId":"ef1e1f0f3fc9670e1fa7fa972f555bd87b7c88b2d5fc4a4c776d2abb37d3015a","contentSha256":"1f0ee8dbf39dbf622b9c52ab2b19380ad8185045606f0c973cb1f5e408789e71","textHash":"324616ed17270f5b9cfec5d6b8fa932465adcf23f455a78da23a51551be6dd8a","observedAt":"2026-11-04T20:52:37.191Z","basis":"publisher-page-metadata","sourceLinks":65,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/28c24d96d7bfbe4e277162b73a982f1daf52fcbdeae9eec1a19fc2a0b9007599/source"}}}],"audits":[{"publicationId":"f6c4760f-d5e2-4b1d-8bda-387b7cca2ff4","verdict":"uncertain","findings":[{"dimension":"attribution","status":"uncertain","explanation":"The page text is the host's episode description, written by Claire Vo in the first person on her How I AI show. The draft never names Vo. It also says 'Mechaber says' he and fellow PMs built PM OS, but the evidence is Vo's narration, not a quote from Mechaber. The claims list correctly says 'the episode description says.' Smallest repair: credit Claire Vo's How I AI episode on Lenny's Newsletter, and change 'Mechaber says' to 'the episode description says.'","excerpt":"In this episode, Ezra walks me through his favorite skills"},{"dimension":"summary","status":"uncertain","explanation":"The summary is faithful and appropriately hedged. However, central terms are left unexplained for a reader without specialist background: repo, skills (in the Claude Code sense), Claude Code, Codex, bug bashing, growth PM, and human checkpoint. Without these, it is hard to grasp what PM OS actually is. Per EM style, these should keep their exact wording and be explained through term-library tooltips, adding entries where they are missing. The title and the question are neutral and follow from the evidence.","excerpt":"turned his personal Claude Code setup into PM OS, a shared repo of 31 skills that every PM at Figma now uses"},{"dimension":"date","status":"pass","explanation":"The page shows Nov 02, 2026. This matches originalPublished (2026-11-02, from the publisher page) and the feed date.","excerpt":"Claire Vo\nNov 02, 2026"},{"dimension":"support","status":"pass","explanation":"Each claim is grounded in the description. The 'huge win' is attributed rather than asserted as fact. The limitations correctly note there is no transcript, the experiment is unspecified, and adoption is only loosely described. The implied value ('practical examples of how a team might organize AI-assisted work') is modest and conditional. The account of building and refining the skills is supported by the chapter list. No invented benefits or costs.","excerpt":"How AutoXP runs experiments with one human checkpoint"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified original article page, the direct source of the evidence. The verified YouTube video is a reasonable alternative, but the article choice is appropriate.","excerpt":null}],"createdAt":"2026-11-06T20:23:21.793Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}