{"observation":{"id":"b45a857b-9306-4a29-a568-dcdf9f79fdf2","tool":"meetgeek","tool_name":"MeetGeek","criterion":"topic-segmentation","criterion_name":"Topic Segmentation","criterion_definition":"Breaks long multi-topic meetings into useful sections instead of one blob.","criterion_evidence_type":"transformation","criterion_rank_role":"context","criterion_rank_role_reason":"Breaking long meetings into sections makes notes easier to use, but a tool can still succeed at core note-taking without perfect segmentation. (3 of 3 judges)","scenario":"ai-demos-daily-standup-31-july-2026","scenario_name":"AI Demos Daily Standup — 31 July 2026","group_tag":"ai-meeting-notetaker","scenario_description":"A real 25-minute technical engineering daily standup with 14 attendees and about 10 active speakers, used as the single parallel-capture meeting for evaluating AI meeting notetakers on transcription, diarization, summaries, action items, search/chat, and collaboration features.","modality":"image","input_text":null,"input_artifact_refs":[{"alt":null,"url":"https://cdn.futuresmart.ai/public/aidemos/547dd6f13e4a420fa8ad7bf2c88c7612.png?v=1","role":"input","filename":"31-july-meeting-screenshot.png"}],"stresses":["Transcription accuracy for real names, tool names, numbers, and technical jargon","Speaker diarization across multiple active speakers","Robustness to overlapping speech, crosstalk, and rapid turn-taking","Join reliability for bot-based and botless capture","Summary quality on identical source material","Action-item extraction with correct owners and commitments","Topic segmentation of standup updates","Search and chat grounded in the meeting content","Sharing, API, MCP, integrations, plan limits, languages, and privacy feature coverage"],"verdict":"worked","score":null,"score_total":null,"note":"It breaks the meeting into useful numbered topic sections instead of one blob, with a visible hierarchy under \"Topics & Highlights\" and the report also noting an Insights tab alongside the segmentation.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://cdn.futuresmart.ai/public/aidemos/802e2202df02459b9fe81b754b08212f.png?v=1","role":"output","alt":null}],"run_id":"ace58582-3d1e-48ee-996c-9b3cd03f27a2","study_title":"AI Meeting Notetakers — Capture Accurate Transcripts, Summaries & Action Items From Live Calls","study_kind":"generation","research_task":"86baxegnv","tested_at":null,"completeness":"input-and-output","input":{"state":"files","text":null,"files":[{"url":"https://cdn.futuresmart.ai/public/aidemos/547dd6f13e4a420fa8ad7bf2c88c7612.png?v=1","filename":"31-july-meeting-screenshot.png","alt":"AI Demos Daily Standup — 31 July 2026","role":"input"}],"modality":"image","stresses":["Transcription accuracy for real names, tool names, numbers, and technical jargon","Speaker diarization across multiple active speakers","Robustness to overlapping speech, crosstalk, and rapid turn-taking","Join reliability for bot-based and botless capture","Summary quality on identical source material","Action-item extraction with correct owners and commitments","Topic segmentation of standup updates","Search and chat grounded in the meeting content","Sharing, API, MCP, integrations, plan limits, languages, and privacy feature coverage"]},"tool_page_slug":"meetgeek","tool_url":"https://aidemos.com/tools/meetgeek","permalink":"https://aidemos.com/evidence/b45a857b-9306-4a29-a568-dcdf9f79fdf2","api_url":"https://ai.aidemos.com/v1/observations/b45a857b-9306-4a29-a568-dcdf9f79fdf2"},"peers":[{"id":"46b5c695-1c28-461a-ad98-573516adf29f","tool":"fathom","tool_name":"Fathom","verdict":"worked","score":null,"score_total":null,"note":"Fathom breaks the standup into named topical sections instead of one blob, including headers like \"Process & System Blockers\" and \"Content Quality & Review Process.\"","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/1d727e487573413ab4068646f67ff0af.png?v=1","evidence_url":"https://aidemos.com/evidence/46b5c695-1c28-461a-ad98-573516adf29f"},{"id":"b69458f2-5b1d-4915-bf53-39ab59f059d2","tool":"fellow","tool_name":"Fellow","verdict":"worked","score":null,"score_total":null,"note":"The tool broke the standup into logical topic sections with clear headers and separated discussion points, rather than leaving the meeting as one undifferentiated blob.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/e9cfe1cbf2b543a3a9ce3c67d83d21ff.png?v=1","evidence_url":"https://aidemos.com/evidence/b69458f2-5b1d-4915-bf53-39ab59f059d2"},{"id":"cc75e1cb-8718-41a2-9065-0ad7df27d332","tool":"fireflies-ai","tool_name":"Fireflies.ai","verdict":"worked","score":null,"score_total":null,"note":"Broke the meeting notes into named sections with descriptive headers and short recap paragraphs, making the output skimmable instead of one undifferentiated block.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/3146d83f0f2d4913ba1acc44c5a24530.png?v=1","evidence_url":"https://aidemos.com/evidence/cc75e1cb-8718-41a2-9065-0ad7df27d332"},{"id":"e10b1e9f-289c-4e45-bb24-24d7b3063e1e","tool":"granola","tool_name":"Granola","verdict":"worked","score":null,"score_total":null,"note":"The notes are split into named topic sections instead of one long blob; the published section header 'Diagram Animation and Other Use Cases' and the report’s multi-section summary structure show logical breakpoints for navigation.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/5343a488a2ad46a48618165dac495d7c.png?v=1","evidence_url":"https://aidemos.com/evidence/e10b1e9f-289c-4e45-bb24-24d7b3063e1e"},{"id":"35b58400-b0b9-4e04-851c-9c0c51b07e1b","tool":"happyscribe","tool_name":"HappyScribe","verdict":"worked","score":null,"score_total":null,"note":"It breaks the standup into logical topic sections that reflect meeting flow, instead of presenting the notes as a single undifferentiated block.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/bf864a8106ca4c3db1b8e79103b8e4f2.png?v=1","evidence_url":"https://aidemos.com/evidence/35b58400-b0b9-4e04-851c-9c0c51b07e1b"},{"id":"dacc4361-09c8-4791-8895-8a8095e21fe8","tool":"notta","tool_name":"Notta","verdict":"worked","score":null,"score_total":null,"note":"The meeting was segmented into useful topic blocks rather than one blob; the report names three sections, including Task & Issue Management, Individual Progress Updates, and API Benchmarking Task.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/84691bb3ad6d4ac19dec1c5f25f3a0a9.png?v=1","evidence_url":"https://aidemos.com/evidence/dacc4361-09c8-4791-8895-8a8095e21fe8"},{"id":"eedc69a7-0929-4cbd-a001-6122eed42379","tool":"otter-ai","tool_name":"Otter.ai","verdict":"worked","score":null,"score_total":null,"note":"Otter broke the standup into useful topic sections rather than one blob, with named headings such as Issue Task Assignments and Status Updates and Error Resolution and Task Link Sharing, making the summary skimmable.","artifact_count":3,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/22a79c0f848e403c82d0a767e9e00914.png?v=1","evidence_url":"https://aidemos.com/evidence/eedc69a7-0929-4cbd-a001-6122eed42379"}],"other_criteria":[{"id":"dfeacb85-baa0-4c8b-a44e-e4a7b005d54f","criterion":"action-item-extraction","criterion_name":"Action-Item Extraction","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"It extracts real commitments as action items rather than noise; the report says all extracted items had correct ownership and timing, and the visible note includes an owned action item with timestamp 19:51.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/dfeacb85-baa0-4c8b-a44e-e4a7b005d54f"},{"id":"75aaf0b0-c9d5-4376-8b81-5b6f2574c0fb","criterion":"chat-with-notes-ask-questions","criterion_name":"Chat with Notes / Ask Questions","rank_role":"context","verdict":"mixed","score":null,"score_total":null,"note":"It answers direct grounded questions correctly, but the report records an incorrect answer on a speaker-dependent scheduling question, so chat is reliable for simple queries but weaker when attribution/context matters.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/75aaf0b0-c9d5-4376-8b81-5b6f2574c0fb"},{"id":"0a57537c-4ad4-4b2f-8115-4281f671bd30","criterion":"editability","criterion_name":"Editability","rank_role":"context","verdict":"worked","score":null,"score_total":null,"note":"Users can edit generated outputs inline before sharing; the report says summary, action items, and the full transcript are all editable, and the UI shows editable summary text.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/0a57537c-4ad4-4b2f-8115-4281f671bd30"},{"id":"9ebe6fbe-6f09-440e-afde-66593a710483","criterion":"join-method-reliability","criterion_name":"Join Method & Reliability","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"The bot successfully joined a Google Meet call and the report says it captured the full ~30-minute meeting with zero disconnections or data loss.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/9ebe6fbe-6f09-440e-afde-66593a710483"},{"id":"e8929c90-b25d-47cf-ab27-f340ed881ef4","criterion":"search-across-notes","criterion_name":"Search Across Notes","rank_role":"context","verdict":"worked","score":null,"score_total":null,"note":"It supports transcript search with precise retrieval: searching for \"api\" surfaces the matching text in context and the report says timestamps are returned to within a few seconds.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/e8929c90-b25d-47cf-ab27-f340ed881ef4"},{"id":"4f7e5b21-ff4f-4846-9a07-3219c0659681","criterion":"speaker-diarization","criterion_name":"Speaker Diarization","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"It identifies most speakers in a multi-speaker standup, but leaves at least one utterance as \"Unknown speaker\" and misattributes some lines to the wrong speaker, so attribution is not fully reliable.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/4f7e5b21-ff4f-4846-9a07-3219c0659681"},{"id":"b482399a-b91b-4aaa-b6f1-a56363792548","criterion":"summary-quality","criterion_name":"Summary Quality","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"It produces a clear, skimmable meeting summary with topic organization and a Next Steps section, and the report says it preserved the major decisions and discussion points.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/b482399a-b91b-4aaa-b6f1-a56363792548"},{"id":"5a191ed7-02a9-4979-931d-9219e0b75fce","criterion":"transcription-accuracy","criterion_name":"Transcription Accuracy","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"It transcribes a normal ~25-minute, ~10-active-speaker engineering standup mostly accurately, with only minor proper-noun/term drift noted in the report; one example given is \"Madin\" being misheard for \"Mahreen\".","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/5a191ed7-02a9-4979-931d-9219e0b75fce"}],"appears_in":[{"page_type":"ranking","slug":"ai-meeting-notetakers","title":"Best AI Meeting Notetakers for Accurate Transcripts, Summaries, and Action Items","url":"https://aidemos.com/best/ai-meeting-notetakers","binding":"run"}],"same_scenario":[{"id":"46b5c695-1c28-461a-ad98-573516adf29f","tool":"fathom","tool_name":"Fathom","verdict":"worked","score":null,"score_total":null,"note":"Fathom breaks the standup into named topical sections instead of one blob, including headers like \"Process & System Blockers\" and \"Content Quality & Review Process.\""},{"id":"b69458f2-5b1d-4915-bf53-39ab59f059d2","tool":"fellow","tool_name":"Fellow","verdict":"worked","score":null,"score_total":null,"note":"The tool broke the standup into logical topic sections with clear headers and separated discussion points, rather than leaving the meeting as one undifferentiated blob."},{"id":"cc75e1cb-8718-41a2-9065-0ad7df27d332","tool":"fireflies-ai","tool_name":"Fireflies.ai","verdict":"worked","score":null,"score_total":null,"note":"Broke the meeting notes into named sections with descriptive headers and short recap paragraphs, making the output skimmable instead of one undifferentiated block."},{"id":"e10b1e9f-289c-4e45-bb24-24d7b3063e1e","tool":"granola","tool_name":"Granola","verdict":"worked","score":null,"score_total":null,"note":"The notes are split into named topic sections instead of one long blob; the published section header 'Diagram Animation and Other Use Cases' and the report’s multi-section summary structure show logical breakpoints for navigation."},{"id":"35b58400-b0b9-4e04-851c-9c0c51b07e1b","tool":"happyscribe","tool_name":"HappyScribe","verdict":"worked","score":null,"score_total":null,"note":"It breaks the standup into logical topic sections that reflect meeting flow, instead of presenting the notes as a single undifferentiated block."},{"id":"dacc4361-09c8-4791-8895-8a8095e21fe8","tool":"notta","tool_name":"Notta","verdict":"worked","score":null,"score_total":null,"note":"The meeting was segmented into useful topic blocks rather than one blob; the report names three sections, including Task & Issue Management, Individual Progress Updates, and API Benchmarking Task."},{"id":"eedc69a7-0929-4cbd-a001-6122eed42379","tool":"otter-ai","tool_name":"Otter.ai","verdict":"worked","score":null,"score_total":null,"note":"Otter broke the standup into useful topic sections rather than one blob, with named headings such as Issue Task Assignments and Status Updates and Error Resolution and Task Link Sharing, making the summary skimmable."}]}