{"id":"182ef32915c08f1fd04e9f5d74b1b52e3210fdaea4a821af653781828e903caa","title":"Khan Academy’s Kristen DiCerbo: Student interests did not improve Khanmigo tutoring metrics","argument":"Khan Academy Chief Learning Officer Kristen DiCerbo reports that adding a list of student interests to Khanmigo’s instructions did not improve measured engagement, math solving, or conversation length in an A/B test of Tutor Me. The test ran for two weeks across 77,613 threads and included students whether or not they had interests. DiCerbo says the test measured prompting Khanmigo to use interests, but did not track when or how it actually used them. Cognitive engagement was not significantly improved; math solving and conversation length showed no measurable change. Cost per thread was lower without interests included. Khan Academy removed the feature, while DiCerbo stresses that this result concerns this particular approach, not whether interests matter in learning. She says future experiments could test different instructions and whether interests help particular students, content, or points in an instructional sequence.","topicIds":["intelligence-and-discovery","work-and-agency"],"domain":"work","claimType":"attributed reading","limits":"The test did not check implementation fidelity: it did not examine conversations to establish when Khanmigo actually used student interests. The test included students whether or not they had interests, and did not track when or how interests were used; its results concern prompting the tutor to use interests, not verified use in responses.","speaker":{"name":"Khan Academy","roleAtSource":"Article author"},"source":{"title":"Does Knowing a Student’s Interests Make AI More Engaging? Here’s What We Found","publisher":"Khan Academy","format":"Article","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","publishedAt":"2026-11-06T21:36:31+00:00","dateBasis":"Date stated by the publisher."},"evidence":[{"text":"Kristen DiCerbo reports that adding student interests to Khanmigo’s instructions did not improve engagement, math solving, or conversation length in the Tutor Me test.","excerpt":"Adding a list of student interests to the AI instructions did not improve engagement, math solving, or conversation length.","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"},{"text":"The A/B test ran for two weeks across 77,613 threads and included students whether or not they had interests.","excerpt":"The test ran for two weeks across 77,613 threads.","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"},{"text":"The test measured prompting Khanmigo to use interests, but did not track when or how it used them.","excerpt":"The test included all students (whether or not they had any interests), and we did not track when or how Khanmigo actually used the interests.","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"},{"text":"DiCerbo reports that cost per thread was lower without interests included.","excerpt":"Cost per thread: This was lower without interests included (0.072 vs. 0.069, which is small but adds up over hundreds of thousands of threads; 95% chance of no interest to win).","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"},{"text":"Khan Academy removed the interests feature based on the test results.","excerpt":"Based on these results, we removed the interests feature from Khanmigo.","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"},{"text":"DiCerbo limits the conclusion to this approach and says future experiments could test other ways of using interests.","excerpt":"It means that this particular approach—adding a list of interests to an AI tutor’s instructions and injecting them into prompts—did not help students engage more deeply or solve more problems.","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"}],"sourceMedia":{"status":"found","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","checkedAt":"2026-11-08T00:32:04.917Z","items":[{"type":"image","url":"https://blog.khanacademy.org/wp-content/uploads/2026/11/1024-x-678-1536x768.png","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","attribution":"Khan Academy","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-08T00:32:05.084Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Would testing different instructions or particular students, content, or points in an instructional sequence show that student interests help in some cases?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Khan Academy’s Kristen DiCerbo: Student interests did not improve Khanmigo tutoring metrics","summary":"Khan Academy Chief Learning Officer Kristen DiCerbo reports that adding a list of student interests to Khanmigo’s instructions did not improve measured engagement, math solving, or conversation length in an A/B test of Tutor Me. The test ran for two weeks across 77,613 threads and included students whether or not they had interests. DiCerbo says the test measured prompting Khanmigo to use interests, but did not track when or how it actually used them. Cognitive engagement was not significantly improved; math solving and conversation length showed no measurable change. Cost per thread was lower without interests included. Khan Academy removed the feature, while DiCerbo stresses that this result concerns this particular approach, not whether interests matter in learning. She says future experiments could test different instructions and whether interests help particular students, content, or points in an instructional sequence.","question":"Would testing different instructions or particular students, content, or points in an instructional sequence show that student interests help in some cases?","claims":[{"text":"Kristen DiCerbo reports that adding student interests to Khanmigo’s instructions did not improve engagement, math solving, or conversation length in the Tutor Me test.","excerpt":"Adding a list of student interests to the AI instructions did not improve engagement, math solving, or conversation length.","support":"source-stated"},{"text":"The A/B test ran for two weeks across 77,613 threads and included students whether or not they had interests.","excerpt":"The test ran for two weeks across 77,613 threads.","support":"source-stated"},{"text":"The test measured prompting Khanmigo to use interests, but did not track when or how it used them.","excerpt":"The test included all students (whether or not they had any interests), and we did not track when or how Khanmigo actually used the interests.","support":"source-stated"},{"text":"DiCerbo reports that cost per thread was lower without interests included.","excerpt":"Cost per thread: This was lower without interests included (0.072 vs. 0.069, which is small but adds up over hundreds of thousands of threads; 95% chance of no interest to win).","support":"source-stated"},{"text":"Khan Academy removed the interests feature based on the test results.","excerpt":"Based on these results, we removed the interests feature from Khanmigo.","support":"source-stated"},{"text":"DiCerbo limits the conclusion to this approach and says future experiments could test other ways of using interests.","excerpt":"It means that this particular approach—adding a list of interests to an AI tutor’s instructions and injecting them into prompts—did not help students engage more deeply or solve more problems.","support":"source-stated"}],"limitations":["The test did not check implementation fidelity: it did not examine conversations to establish when Khanmigo actually used student interests.","The test included students whether or not they had interests, and did not track when or how interests were used; its results concern prompting the tutor to use interests, not verified use in responses."],"mediaId":"75b86bdbb7cbeeaec2f7101d7a5e61ba53699fe1e03e4af846de38ddaf7f812f","correctionReason":null,"id":"182ef32915c08f1fd04e9f5d74b1b52e3210fdaea4a821af653781828e903caa","publicationId":"2e16d3ad-6eb6-49e1-85b4-feb8e0dd4cd5","version":1,"sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","sourceTitle":"Does Knowing a Student’s Interests Make AI More Engaging? Here’s What We Found","publisher":"Khan Academy","publishedAt":"2026-11-06T21:36:31+00:00","originalPublished":{"value":"2026-11-06T21:36:31+00:00","precision":"instant","basis":"publisher_page"},"firstObservedAt":"2026-11-06T21:45:23.134Z","createdAt":"2026-11-08T00:32:51.302Z","historical":false,"entityIds":["khan-academy"],"topicIds":["intelligence-and-discovery","work-and-agency"],"media":[{"id":"75b86bdbb7cbeeaec2f7101d7a5e61ba53699fe1e03e4af846de38ddaf7f812f","kind":"article","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-08T00:32:05.084Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."},{"id":"fceb1f9e1835b820956c1222566421128add391bd05f72a6ea3f16639dc23ca8","kind":"image","url":"https://blog.khanacademy.org/wp-content/uploads/2026/11/1024-x-678-1536x768.png","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","label":"View source image","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-08T00:32:05.084Z","method":"publisher_association_and_head","contentType":"image/png","cacheUntil":1794098225084},"recommendationReason":"Observed on the acquired publisher source; availability checked."}],"sourceMedia":{"status":"found","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","checkedAt":"2026-11-08T00:32:04.917Z","items":[{"type":"image","url":"https://blog.khanacademy.org/wp-content/uploads/2026/11/1024-x-678-1536x768.png","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","attribution":"Khan Academy","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-08T00:32:05.084Z"}],"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":"75b86bdbb7cbeeaec2f7101d7a5e61ba53699fe1e03e4af846de38ddaf7f812f","confidence":0.9100000000000001,"provider":"typesafe","model":"jev-1.13.0","inputHash":"3242bd120ebea16fb929b5b767bb5beac72f251d70195e76e3e88cc9affab899","decidedAt":"2026-11-08T00:32:06.316Z"},"provenance":{"textHash":"be6e5e5022087248a535aeb84094441b2399bec6017e006ab7f9f26d77b80070","observationId":"7c7b4d5575c5c52e03cba8663e745b5aa273098c6a171033073485d7196740be","retrievedAt":"2026-11-08T00:32:04.917Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"7a903ef4-70f2-4af0-8655-d3e218d56cad"},"reviewer":{"model":"gpt-6-luna","runId":"8462f4ae-c578-4f5b-8b3f-d4409da34404"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-08T00:32:51.302Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Khan Academy","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Khan Academy","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Khan Academy","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","locator":"document/html[1]/head[0]/script[62]@2639.@graph[0].author"},"assertionId":"f02654dd5908229cf1f44c87017afd509ef385c481afecf2783f729f788e2dc1:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-08T00:32:04.917Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"f02654dd5908229cf1f44c87017afd509ef385c481afecf2783f729f788e2dc1","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","contentSha256":"0d3be56de77360dab331fc72107f1e5d92d2b146f71faa75c1ce5fe6384d1327","textHash":"be6e5e5022087248a535aeb84094441b2399bec6017e006ab7f9f26d77b80070","observedAt":"2026-11-08T00:32:04.917Z"}}],"participationCoverage":{"total":2,"returned":1,"complete":false,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","snapshotId":"f02654dd5908229cf1f44c87017afd509ef385c481afecf2783f729f788e2dc1","contentSha256":"0d3be56de77360dab331fc72107f1e5d92d2b146f71faa75c1ce5fe6384d1327","textHash":"be6e5e5022087248a535aeb84094441b2399bec6017e006ab7f9f26d77b80070","observedAt":"2026-11-08T00:32:04.917Z","basis":"publisher-page-metadata","sourceLinks":7,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/182ef32915c08f1fd04e9f5d74b1b52e3210fdaea4a821af653781828e903caa/source"}},"canonicalUrl":"https://escapemeridian.com/readings/khan-academy-s-kristen-dicerbo-student-interests-did-not-182ef329","formats":{"html":"/readings/khan-academy-s-kristen-dicerbo-student-interests-did-not-182ef329","markdown":"/readings/khan-academy-s-kristen-dicerbo-student-interests-did-not-182ef329.md","json":"/readings/khan-academy-s-kristen-dicerbo-student-interests-did-not-182ef329.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":"khan-academy","name":"Khan Academy","kind":"organization","context":"Education deployment with explicit evaluation and implementation limitations.","referenceUrls":["https://www.dwarkesh.com/p/andrej-karpathy","https://lexfridman.com/marc-andreessen-2-transcript","https://www.dwarkesh.com/p/tony-blair","https://blog.khanacademy.org/four-things-to-look-for-in-edtech-and-how-khan-academy-measures-up/","https://blog.khanacademy.org/"],"path":"/entities/khan-academy","json":"/entities/khan-academy.json","markdown":"/entities/khan-academy.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"182ef32915c08f1fd04e9f5d74b1b52e3210fdaea4a821af653781828e903caa","revision":"2e16d3ad-6eb6-49e1-85b4-feb8e0dd4cd5","revisionKind":"publication-id","title":"Khan Academy’s Kristen DiCerbo: Student interests did not improve Khanmigo tutoring metrics","url":"https://escapemeridian.com/readings/khan-academy-s-kristen-dicerbo-student-interests-did-not-182ef329"},"source":{"type":"source","id":"https://blog.khanacademy.org/student-interests-ai-tutoring/","revision":"be6e5e5022087248a535aeb84094441b2399bec6017e006ab7f9f26d77b80070","revisionKind":"sha256-source-text","title":"Does Knowing a Student’s Interests Make AI More Engaging? Here’s What We Found","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/"},"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":"182ef32915c08f1fd04e9f5d74b1b52e3210fdaea4a821af653781828e903caa","title":"Khan Academy’s Kristen DiCerbo: Student interests did not improve Khanmigo tutoring metrics","argument":"Khan Academy Chief Learning Officer Kristen DiCerbo reports that adding a list of student interests to Khanmigo’s instructions did not improve measured engagement, math solving, or conversation length in an A/B test of Tutor Me. The test ran for two weeks across 77,613 threads and included students whether or not they had interests. DiCerbo says the test measured prompting Khanmigo to use interests, but did not track when or how it actually used them. Cognitive engagement was not significantly improved; math solving and conversation length showed no measurable change. Cost per thread was lower without interests included. Khan Academy removed the feature, while DiCerbo stresses that this result concerns this particular approach, not whether interests matter in learning. She says future experiments could test different instructions and whether interests help particular students, content, or points in an instructional sequence.","topicIds":["intelligence-and-discovery","work-and-agency"],"domain":"work","claimType":"attributed reading","limits":"The test did not check implementation fidelity: it did not examine conversations to establish when Khanmigo actually used student interests. The test included students whether or not they had interests, and did not track when or how interests were used; its results concern prompting the tutor to use interests, not verified use in responses.","speaker":{"name":"Khan Academy","roleAtSource":"Article author"},"source":{"title":"Does Knowing a Student’s Interests Make AI More Engaging? Here’s What We Found","publisher":"Khan Academy","format":"Article","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","publishedAt":"2026-11-06T21:36:31+00:00","dateBasis":"Date stated by the publisher."},"evidence":[{"text":"Kristen DiCerbo reports that adding student interests to Khanmigo’s instructions did not improve engagement, math solving, or conversation length in the Tutor Me test.","excerpt":"Adding a list of student interests to the AI instructions did not improve engagement, math solving, or conversation length.","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"},{"text":"The A/B test ran for two weeks across 77,613 threads and included students whether or not they had interests.","excerpt":"The test ran for two weeks across 77,613 threads.","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"},{"text":"The test measured prompting Khanmigo to use interests, but did not track when or how it used them.","excerpt":"The test included all students (whether or not they had any interests), and we did not track when or how Khanmigo actually used the interests.","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"},{"text":"DiCerbo reports that cost per thread was lower without interests included.","excerpt":"Cost per thread: This was lower without interests included (0.072 vs. 0.069, which is small but adds up over hundreds of thousands of threads; 95% chance of no interest to win).","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"},{"text":"Khan Academy removed the interests feature based on the test results.","excerpt":"Based on these results, we removed the interests feature from Khanmigo.","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"},{"text":"DiCerbo limits the conclusion to this approach and says future experiments could test other ways of using interests.","excerpt":"It means that this particular approach—adding a list of interests to an AI tutor’s instructions and injecting them into prompts—did not help students engage more deeply or solve more problems.","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","relationship":"Source-stated"}],"sourceMedia":{"status":"found","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","checkedAt":"2026-11-08T00:32:04.917Z","items":[{"type":"image","url":"https://blog.khanacademy.org/wp-content/uploads/2026/11/1024-x-678-1536x768.png","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","attribution":"Khan Academy","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-08T00:32:05.084Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Would testing different instructions or particular students, content, or points in an instructional sequence show that student interests help in some cases?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Khan Academy’s Kristen DiCerbo: Student interests did not improve Khanmigo tutoring metrics","summary":"Khan Academy Chief Learning Officer Kristen DiCerbo reports that adding a list of student interests to Khanmigo’s instructions did not improve measured engagement, math solving, or conversation length in an A/B test of Tutor Me. The test ran for two weeks across 77,613 threads and included students whether or not they had interests. DiCerbo says the test measured prompting Khanmigo to use interests, but did not track when or how it actually used them. Cognitive engagement was not significantly improved; math solving and conversation length showed no measurable change. Cost per thread was lower without interests included. Khan Academy removed the feature, while DiCerbo stresses that this result concerns this particular approach, not whether interests matter in learning. She says future experiments could test different instructions and whether interests help particular students, content, or points in an instructional sequence.","question":"Would testing different instructions or particular students, content, or points in an instructional sequence show that student interests help in some cases?","claims":[{"text":"Kristen DiCerbo reports that adding student interests to Khanmigo’s instructions did not improve engagement, math solving, or conversation length in the Tutor Me test.","excerpt":"Adding a list of student interests to the AI instructions did not improve engagement, math solving, or conversation length.","support":"source-stated"},{"text":"The A/B test ran for two weeks across 77,613 threads and included students whether or not they had interests.","excerpt":"The test ran for two weeks across 77,613 threads.","support":"source-stated"},{"text":"The test measured prompting Khanmigo to use interests, but did not track when or how it used them.","excerpt":"The test included all students (whether or not they had any interests), and we did not track when or how Khanmigo actually used the interests.","support":"source-stated"},{"text":"DiCerbo reports that cost per thread was lower without interests included.","excerpt":"Cost per thread: This was lower without interests included (0.072 vs. 0.069, which is small but adds up over hundreds of thousands of threads; 95% chance of no interest to win).","support":"source-stated"},{"text":"Khan Academy removed the interests feature based on the test results.","excerpt":"Based on these results, we removed the interests feature from Khanmigo.","support":"source-stated"},{"text":"DiCerbo limits the conclusion to this approach and says future experiments could test other ways of using interests.","excerpt":"It means that this particular approach—adding a list of interests to an AI tutor’s instructions and injecting them into prompts—did not help students engage more deeply or solve more problems.","support":"source-stated"}],"limitations":["The test did not check implementation fidelity: it did not examine conversations to establish when Khanmigo actually used student interests.","The test included students whether or not they had interests, and did not track when or how interests were used; its results concern prompting the tutor to use interests, not verified use in responses."],"mediaId":"75b86bdbb7cbeeaec2f7101d7a5e61ba53699fe1e03e4af846de38ddaf7f812f","correctionReason":null,"id":"182ef32915c08f1fd04e9f5d74b1b52e3210fdaea4a821af653781828e903caa","publicationId":"2e16d3ad-6eb6-49e1-85b4-feb8e0dd4cd5","version":1,"sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","sourceTitle":"Does Knowing a Student’s Interests Make AI More Engaging? Here’s What We Found","publisher":"Khan Academy","publishedAt":"2026-11-06T21:36:31+00:00","originalPublished":{"value":"2026-11-06T21:36:31+00:00","precision":"instant","basis":"publisher_page"},"firstObservedAt":"2026-11-06T21:45:23.134Z","createdAt":"2026-11-08T00:32:51.302Z","historical":false,"entityIds":["khan-academy"],"topicIds":["intelligence-and-discovery","work-and-agency"],"media":[{"id":"75b86bdbb7cbeeaec2f7101d7a5e61ba53699fe1e03e4af846de38ddaf7f812f","kind":"article","url":"https://blog.khanacademy.org/student-interests-ai-tutoring/","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-08T00:32:05.084Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."},{"id":"fceb1f9e1835b820956c1222566421128add391bd05f72a6ea3f16639dc23ca8","kind":"image","url":"https://blog.khanacademy.org/wp-content/uploads/2026/11/1024-x-678-1536x768.png","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","label":"View source image","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-08T00:32:05.084Z","method":"publisher_association_and_head","contentType":"image/png","cacheUntil":1794098225084},"recommendationReason":"Observed on the acquired publisher source; availability checked."}],"sourceMedia":{"status":"found","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","checkedAt":"2026-11-08T00:32:04.917Z","items":[{"type":"image","url":"https://blog.khanacademy.org/wp-content/uploads/2026/11/1024-x-678-1536x768.png","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","attribution":"Khan Academy","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-08T00:32:05.084Z"}],"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":"75b86bdbb7cbeeaec2f7101d7a5e61ba53699fe1e03e4af846de38ddaf7f812f","confidence":0.9100000000000001,"provider":"typesafe","model":"jev-1.13.0","inputHash":"3242bd120ebea16fb929b5b767bb5beac72f251d70195e76e3e88cc9affab899","decidedAt":"2026-11-08T00:32:06.316Z"},"provenance":{"textHash":"be6e5e5022087248a535aeb84094441b2399bec6017e006ab7f9f26d77b80070","observationId":"7c7b4d5575c5c52e03cba8663e745b5aa273098c6a171033073485d7196740be","retrievedAt":"2026-11-08T00:32:04.917Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"7a903ef4-70f2-4af0-8655-d3e218d56cad"},"reviewer":{"model":"gpt-6-luna","runId":"8462f4ae-c578-4f5b-8b3f-d4409da34404"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-08T00:32:51.302Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Khan Academy","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Khan Academy","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Khan Academy","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","locator":"document/html[1]/head[0]/script[62]@2639.@graph[0].author"},"assertionId":"f02654dd5908229cf1f44c87017afd509ef385c481afecf2783f729f788e2dc1:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-08T00:32:04.917Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"f02654dd5908229cf1f44c87017afd509ef385c481afecf2783f729f788e2dc1","sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","contentSha256":"0d3be56de77360dab331fc72107f1e5d92d2b146f71faa75c1ce5fe6384d1327","textHash":"be6e5e5022087248a535aeb84094441b2399bec6017e006ab7f9f26d77b80070","observedAt":"2026-11-08T00:32:04.917Z"}}],"participationCoverage":{"total":2,"returned":1,"complete":false,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://blog.khanacademy.org/student-interests-ai-tutoring/","snapshotId":"f02654dd5908229cf1f44c87017afd509ef385c481afecf2783f729f788e2dc1","contentSha256":"0d3be56de77360dab331fc72107f1e5d92d2b146f71faa75c1ce5fe6384d1327","textHash":"be6e5e5022087248a535aeb84094441b2399bec6017e006ab7f9f26d77b80070","observedAt":"2026-11-08T00:32:04.917Z","basis":"publisher-page-metadata","sourceLinks":7,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/182ef32915c08f1fd04e9f5d74b1b52e3210fdaea4a821af653781828e903caa/source"}}}],"audits":[{"publicationId":"2e16d3ad-6eb6-49e1-85b4-feb8e0dd4cd5","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly attributes the post to Kristen DiCerbo, Khan Academy Chief Learning Officer, and keeps the findings and conclusions framed as her and Khan Academy's report rather than as established fact.","excerpt":"By Kristen DiCerbo, Khan Academy Chief Learning Officer"},{"dimension":"summary","status":"uncertain","explanation":"The facts are accurate, but a reader without background may not follow it. Khanmigo is never identified as Khan Academy's AI tutor. Tutor Me, A/B test and threads are not explained. The draft also drops the source's central framing: personalizing to student interests is a common hope for AI tutors, and DiCerbo calls the result counterintuitive. Smallest repair: identify Khanmigo as Khan Academy's AI tutor, add that common-hope framing, and gloss A/B test as the source does.","excerpt":"Our findings were counterintuitive to the common wisdom: using student interests didn’t increase engagement or make it more likely that a student would solve a problem."},{"dimension":"date","status":"pass","explanation":"originalPublished (2026-11-06T21:36:31Z, from the publisher page) matches the feed entry. Nothing indicates an earlier first publication.","excerpt":null},{"dimension":"support","status":"pass","explanation":"Each claim has a verbatim, source-stated excerpt. That covers the null results, the two-week test across 77,613 threads, the lower cost, the feature's removal, the limitation on implementation fidelity and the scoped conclusion. The question follows from the source's future-work section without asserting an answer. No unsupported benefits or costs are implied.","excerpt":"In particular, we did not check implementation fidelity."},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct link to the original Khan Academy blog post. It is the most direct way to access the source.","excerpt":null}],"createdAt":"2026-11-08T00:32:51.302Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}