{"observation":{"id":"1c4f4fe3-3ed8-490d-992b-a25ddd604669","tool":"fathom","tool_name":"Fathom","criterion":"transcription-accuracy","criterion_name":"Transcription Accuracy","criterion_definition":"Word accuracy on the shared call, especially names, tools, numbers, and jargon.","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"If the transcript gets names, numbers, and jargon wrong, the note-taker has failed at the core job of capturing the call accurately. (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":"mixed","score":null,"score_total":null,"note":"Fathom's transcript mostly preserves the meeting's names and technical content, but the report records one confirmed name-level error: \"Mahreen\" was rendered as \"Meryl.\"","evidence_state":"verified","source":null,"artifacts":[{"url":"https://cdn.futuresmart.ai/public/aidemos/19b062d60f8e45a6a5fa364948287362.png?v=1","role":"output","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/13224c7d84ae47cf8f21b3b165e5fcf5.png?v=1","role":"context","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":"fathom","tool_url":"https://aidemos.com/tools/fathom","permalink":"https://aidemos.com/evidence/1c4f4fe3-3ed8-490d-992b-a25ddd604669","api_url":"https://ai.aidemos.com/v1/observations/1c4f4fe3-3ed8-490d-992b-a25ddd604669"},"peers":[{"id":"d4b52ad2-b536-4580-99fa-644f4b772a93","tool":"fellow","tool_name":"Fellow","verdict":"worked","score":null,"score_total":null,"note":"The transcript was near-clean: the tool captured nearly all names, technical jargon, and numbers correctly, with no significant misheard terms or hallucinations observed in the tested meeting.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/7476ae6a377e411094940f94f34b21f9.png?v=1","evidence_url":"https://aidemos.com/evidence/d4b52ad2-b536-4580-99fa-644f4b772a93"},{"id":"bac222c7-f7cf-4041-8449-df5aa22c88ac","tool":"fireflies-ai","tool_name":"Fireflies.ai","verdict":"worked","score":null,"score_total":null,"note":"Generated a timestamped transcript view, and the report says the full transcript was very accurate: nearly all names, tools, jargon, and numbers were captured correctly with no significant misheard terms or hallucinations.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/7aecac3bebb2479aa0f18cf6c9f1f0db.png?v=1","evidence_url":"https://aidemos.com/evidence/bac222c7-f7cf-4041-8449-df5aa22c88ac"},{"id":"87d23b55-bc59-4d3e-8547-9b80fc1107f6","tool":"granola","tool_name":"Granola","verdict":"failed","score":null,"score_total":null,"note":"On this 25-minute, multi-speaker standup, Granola’s transcript quality is unreliable: the published excerpt shows garbled phrasing and mistranscribed wording, and the report says the mishearing pattern recurs across early, middle, and late sections rather than being isolated to one moment.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/d3ec039f484d40328057665e51ba34de.png?v=1","evidence_url":"https://aidemos.com/evidence/87d23b55-bc59-4d3e-8547-9b80fc1107f6"},{"id":"624ffd2e-c9da-4fb4-acc3-041a5b115a50","tool":"happyscribe","tool_name":"HappyScribe","verdict":"mixed","score":null,"score_total":null,"note":"On this ~25-minute multi-speaker standup, HappyScribe captured the vast majority of names, tools, and jargon correctly, and the report records only 1–2 misheard words.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/768c8f926786411984134803cb5396a5.png?v=1","evidence_url":"https://aidemos.com/evidence/624ffd2e-c9da-4fb4-acc3-041a5b115a50"},{"id":"5a191ed7-02a9-4979-931d-9219e0b75fce","tool":"meetgeek","tool_name":"MeetGeek","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,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/f3fbc51e628c42c19595b82c5e481a25.png?v=1","evidence_url":"https://aidemos.com/evidence/5a191ed7-02a9-4979-931d-9219e0b75fce"},{"id":"893f5543-bd03-4e2a-ba30-f6426940628b","tool":"notta","tool_name":"Notta","verdict":"worked","score":null,"score_total":null,"note":"Notta’s transcript capture was accurate on the evaluated standup: the report says it correctly captured names, tool names, numbers, and engineering jargon with no significant word-level errors, silent hallucinations, or misheard terms.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/86173a6a33c7494b96de40392d0740b6.png?v=1","evidence_url":"https://aidemos.com/evidence/893f5543-bd03-4e2a-ba30-f6426940628b"},{"id":"0efa5738-c840-44ba-a72a-b35d289e70fb","tool":"otter-ai","tool_name":"Otter.ai","verdict":"worked","score":null,"score_total":null,"note":"Otter generated a full transcript for the standup and, per the report, captured names, tool names, jargon, and numbers correctly with minimal errors, making the transcript reliable for reference.","artifact_count":3,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/0db942cf24dd4c3f9383ac4f5208e840.png?v=1","evidence_url":"https://aidemos.com/evidence/0efa5738-c840-44ba-a72a-b35d289e70fb"}],"other_criteria":[{"id":"8340c79d-88de-4721-9c3e-c58e057071fb","criterion":"action-item-extraction","criterion_name":"Action-Item Extraction","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Fathom extracts real commitments into an ACTION ITEMS section with owner attribution; the published output shows timestamped tasks and a named owner on the item.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/8340c79d-88de-4721-9c3e-c58e057071fb"},{"id":"070f7f5f-046c-4139-a132-6e00a3b57acc","criterion":"chat-with-notes-ask-questions","criterion_name":"Chat with Notes / Ask Questions","rank_role":"context","verdict":"worked","score":null,"score_total":null,"note":"Ask Fathom answers direct factual questions from the meeting notes with grounded references; for one query it answered that a call was scheduled for 6th August and linked the supporting transcript mention.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/070f7f5f-046c-4139-a132-6e00a3b57acc"},{"id":"64cce11b-7973-439a-bcc1-68219903d5eb","criterion":"join-method-reliability","criterion_name":"Join Method & Reliability","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"The bot joined Google Meet successfully and stayed connected for the full ~25-minute call, with no mid-call disconnections or plan-limit cutoffs.","artifact_count":5,"evidence_url":"https://aidemos.com/evidence/64cce11b-7973-439a-bcc1-68219903d5eb"},{"id":"79d2b9bb-26b6-4b8e-858a-25c5849095c9","criterion":"search-across-notes","criterion_name":"Search Across Notes","rank_role":"context","verdict":"worked","score":null,"score_total":null,"note":"Transcript search supports keyword lookup and returns a matched snippet for \"API,\" surfacing the relevant moment and the linked action item \"Create subtasks for API benchmarking; tag Divya on completion.\"","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/79d2b9bb-26b6-4b8e-858a-25c5849095c9"},{"id":"e9695d25-df6e-448b-b185-4ad01e885bdf","criterion":"speaker-diarization","criterion_name":"Speaker Diarization","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"Fathom separates most speakers correctly in a busy multi-speaker standup, but the report observed one rapid-transition segment where two speakers' lines were merged into a single speaker block.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/e9695d25-df6e-448b-b185-4ad01e885bdf"},{"id":"53731c87-42c6-49f3-b19d-6a3ab5fe169e","criterion":"summary-quality","criterion_name":"Summary Quality","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Fathom produces a skimmable written recap with named sections such as Meeting Purpose, Key Takeaways, and Topics; the report describes the summary as structured and concise.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/53731c87-42c6-49f3-b19d-6a3ab5fe169e"},{"id":"46b5c695-1c28-461a-ad98-573516adf29f","criterion":"topic-segmentation","criterion_name":"Topic Segmentation","rank_role":"context","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,"evidence_url":"https://aidemos.com/evidence/46b5c695-1c28-461a-ad98-573516adf29f"}],"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":"d4b52ad2-b536-4580-99fa-644f4b772a93","tool":"fellow","tool_name":"Fellow","verdict":"worked","score":null,"score_total":null,"note":"The transcript was near-clean: the tool captured nearly all names, technical jargon, and numbers correctly, with no significant misheard terms or hallucinations observed in the tested meeting."},{"id":"bac222c7-f7cf-4041-8449-df5aa22c88ac","tool":"fireflies-ai","tool_name":"Fireflies.ai","verdict":"worked","score":null,"score_total":null,"note":"Generated a timestamped transcript view, and the report says the full transcript was very accurate: nearly all names, tools, jargon, and numbers were captured correctly with no significant misheard terms or hallucinations."},{"id":"87d23b55-bc59-4d3e-8547-9b80fc1107f6","tool":"granola","tool_name":"Granola","verdict":"failed","score":null,"score_total":null,"note":"On this 25-minute, multi-speaker standup, Granola’s transcript quality is unreliable: the published excerpt shows garbled phrasing and mistranscribed wording, and the report says the mishearing pattern recurs across early, middle, and late sections rather than being isolated to one moment."},{"id":"624ffd2e-c9da-4fb4-acc3-041a5b115a50","tool":"happyscribe","tool_name":"HappyScribe","verdict":"mixed","score":null,"score_total":null,"note":"On this ~25-minute multi-speaker standup, HappyScribe captured the vast majority of names, tools, and jargon correctly, and the report records only 1–2 misheard words."},{"id":"5a191ed7-02a9-4979-931d-9219e0b75fce","tool":"meetgeek","tool_name":"MeetGeek","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\"."},{"id":"893f5543-bd03-4e2a-ba30-f6426940628b","tool":"notta","tool_name":"Notta","verdict":"worked","score":null,"score_total":null,"note":"Notta’s transcript capture was accurate on the evaluated standup: the report says it correctly captured names, tool names, numbers, and engineering jargon with no significant word-level errors, silent hallucinations, or misheard terms."},{"id":"0efa5738-c840-44ba-a72a-b35d289e70fb","tool":"otter-ai","tool_name":"Otter.ai","verdict":"worked","score":null,"score_total":null,"note":"Otter generated a full transcript for the standup and, per the report, captured names, tool names, jargon, and numbers correctly with minimal errors, making the transcript reliable for reference."}]}