{"observation":{"id":"b58378a0-5d37-4751-a711-f2d028fa4401","tool":"notta","tool_name":"Notta","criterion":"chat-with-notes-ask-questions","criterion_name":"Chat with Notes / Ask Questions","criterion_definition":"Gives grounded answers with the cited moment and admits when unknown.","criterion_evidence_type":"transformation","criterion_rank_role":"context","criterion_rank_role_reason":"Q&A over notes is useful, but it is an add-on to the capture and summarization job rather than a core measure of it. (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":"The Q&A interface answered a natural-language question with a grounded response from the meeting record, including the specific date \"6th August,\" and the report observed no hallucinations.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://cdn.futuresmart.ai/public/aidemos/a822259cb8bf403a96a2d5814c1b7036.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":"notta","tool_url":"https://aidemos.com/tools/notta","permalink":"https://aidemos.com/evidence/b58378a0-5d37-4751-a711-f2d028fa4401","api_url":"https://ai.aidemos.com/v1/observations/b58378a0-5d37-4751-a711-f2d028fa4401"},"peers":[{"id":"070f7f5f-046c-4139-a132-6e00a3b57acc","tool":"fathom","tool_name":"Fathom","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,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/cc0b830d51cd48a2a6c9121c331b1626.png?v=1","evidence_url":"https://aidemos.com/evidence/070f7f5f-046c-4139-a132-6e00a3b57acc"},{"id":"b8fe3f78-ae35-4ccf-b887-6188bac5ad2f","tool":"fellow","tool_name":"Fellow","verdict":"worked","score":null,"score_total":null,"note":"Ask Fellow returned grounded answers to natural-language questions against the meeting notes, and the tested query produced a cited response rather than an unsupported hallucination.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/553c970153974fc9a12d999ec7a3b888.png?v=1","evidence_url":"https://aidemos.com/evidence/b8fe3f78-ae35-4ccf-b887-6188bac5ad2f"},{"id":"9080d7d0-7707-4182-b68c-0e1f61c09488","tool":"fireflies-ai","tool_name":"Fireflies.ai","verdict":"worked","score":null,"score_total":null,"note":"AskFred answered a natural-language question with a specific grounded response ('August 6th') and relevant context, with no hallucination reported in the tested query.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/5d6339008cea4142b2733ccea5fe3c23.png?v=1","evidence_url":"https://aidemos.com/evidence/9080d7d0-7707-4182-b68c-0e1f61c09488"},{"id":"633e805b-8efa-4b9f-8667-7b79bb93072c","tool":"granola","tool_name":"Granola","verdict":"worked","score":null,"score_total":null,"note":"The chat/Q&A surface gives grounded answers from the meeting record: on the tool-access question it says access was confirmed that day, cites both the notes and transcript, and identifies rerunning testing as the next step.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/8b17d8ed350645bfb4a942128365177f.png?v=1","evidence_url":"https://aidemos.com/evidence/633e805b-8efa-4b9f-8667-7b79bb93072c"},{"id":"09e56c77-5be8-4485-90bc-76a453f3197a","tool":"happyscribe","tool_name":"HappyScribe","verdict":"worked","score":null,"score_total":null,"note":"AI chat answers a meeting question with a grounded transcript-backed response, returning that the call was scheduled for '6th August' and explicitly indicating it is reading the transcription.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/04410e535a0e4f95add9df3c5cd7e79c.png?v=1","evidence_url":"https://aidemos.com/evidence/09e56c77-5be8-4485-90bc-76a453f3197a"},{"id":"75aaf0b0-c9d5-4376-8b81-5b6f2574c0fb","tool":"meetgeek","tool_name":"MeetGeek","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,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/e84f2cebcccd4af092aff8637baab736.png?v=1","evidence_url":"https://aidemos.com/evidence/75aaf0b0-c9d5-4376-8b81-5b6f2574c0fb"},{"id":"295ea299-5f4d-480e-8ff7-36708e2bc9f7","tool":"otter-ai","tool_name":"Otter.ai","verdict":"worked","score":null,"score_total":null,"note":"Otter’s AI Chat answered meeting questions with a grounded response and a specific timestamp, and the report says the answers were cited and free of hallucinations in the tested queries.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/e5aefd3684124771a718737d9c8d1754.png?v=1","evidence_url":"https://aidemos.com/evidence/295ea299-5f4d-480e-8ff7-36708e2bc9f7"}],"other_criteria":[{"id":"1b0800ea-3b02-4159-88c1-ed437a0b12a7","criterion":"action-item-extraction","criterion_name":"Action-Item Extraction","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"The action-item list extracted the real commitments from the call, formatted them as checkbox items with @mentions, and the report says owner assignment was correct with no false positives.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/1b0800ea-3b02-4159-88c1-ed437a0b12a7"},{"id":"d31ec8ee-e1f2-4d37-8cd5-9eeaf5e99255","criterion":"join-method-reliability","criterion_name":"Join Method & Reliability","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"The bot-based Google Meet join was reliable in the tested call: Notta Bot appeared in the meeting list, admitted/managed normally, and the capture ran through the end of the session without disconnects or plan-limit cutoffs.","artifact_count":4,"evidence_url":"https://aidemos.com/evidence/d31ec8ee-e1f2-4d37-8cd5-9eeaf5e99255"},{"id":"3e05ffd9-05fd-44d7-914a-1e1bbb24c13c","criterion":"search-across-notes","criterion_name":"Search Across Notes","rank_role":"context","verdict":"mixed","score":null,"score_total":null,"note":"Search works inside a meeting transcript through AI Chat and returns exact timestamps in plain text, but the timestamps are not clickable, and the report says this was not tested across meetings.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/3e05ffd9-05fd-44d7-914a-1e1bbb24c13c"},{"id":"089aaaff-2da4-4739-8045-46df7a2f1e6b","criterion":"speaker-diarization","criterion_name":"Speaker Diarization","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"Speaker attribution was mostly correct, with nearly all speakers identified by name, but the transcript still showed some misattributed lines, so diarization was not fully reliable for every turn.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/089aaaff-2da4-4739-8045-46df7a2f1e6b"},{"id":"c1fc0701-9a26-4f73-a1f2-d4dfae6a7109","criterion":"speaker-diarization","criterion_name":"Speaker Diarization","rank_role":"decisive","verdict":"struggled","score":null,"score_total":null,"note":"The transcript contained a line labeled with another notetaker’s name (HappyScribe), which indicates cross-tool contamination or labeling error and breaks speaker attribution for that segment.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/c1fc0701-9a26-4f73-a1f2-d4dfae6a7109"},{"id":"aa85bfe2-42ee-4df2-b89f-831056fd4fc3","criterion":"summary-quality","criterion_name":"Summary Quality","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"The generated meeting summary was comprehensive and skimmable, with structured sections such as Task & Issue Management and a mindmap-style organization that reflected the meeting flow.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/aa85bfe2-42ee-4df2-b89f-831056fd4fc3"},{"id":"dacc4361-09c8-4791-8895-8a8095e21fe8","criterion":"topic-segmentation","criterion_name":"Topic Segmentation","rank_role":"context","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,"evidence_url":"https://aidemos.com/evidence/dacc4361-09c8-4791-8895-8a8095e21fe8"},{"id":"893f5543-bd03-4e2a-ba30-f6426940628b","criterion":"transcription-accuracy","criterion_name":"Transcription Accuracy","rank_role":"decisive","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,"evidence_url":"https://aidemos.com/evidence/893f5543-bd03-4e2a-ba30-f6426940628b"}],"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":"070f7f5f-046c-4139-a132-6e00a3b57acc","tool":"fathom","tool_name":"Fathom","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."},{"id":"b8fe3f78-ae35-4ccf-b887-6188bac5ad2f","tool":"fellow","tool_name":"Fellow","verdict":"worked","score":null,"score_total":null,"note":"Ask Fellow returned grounded answers to natural-language questions against the meeting notes, and the tested query produced a cited response rather than an unsupported hallucination."},{"id":"9080d7d0-7707-4182-b68c-0e1f61c09488","tool":"fireflies-ai","tool_name":"Fireflies.ai","verdict":"worked","score":null,"score_total":null,"note":"AskFred answered a natural-language question with a specific grounded response ('August 6th') and relevant context, with no hallucination reported in the tested query."},{"id":"633e805b-8efa-4b9f-8667-7b79bb93072c","tool":"granola","tool_name":"Granola","verdict":"worked","score":null,"score_total":null,"note":"The chat/Q&A surface gives grounded answers from the meeting record: on the tool-access question it says access was confirmed that day, cites both the notes and transcript, and identifies rerunning testing as the next step."},{"id":"09e56c77-5be8-4485-90bc-76a453f3197a","tool":"happyscribe","tool_name":"HappyScribe","verdict":"worked","score":null,"score_total":null,"note":"AI chat answers a meeting question with a grounded transcript-backed response, returning that the call was scheduled for '6th August' and explicitly indicating it is reading the transcription."},{"id":"75aaf0b0-c9d5-4376-8b81-5b6f2574c0fb","tool":"meetgeek","tool_name":"MeetGeek","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."},{"id":"295ea299-5f4d-480e-8ff7-36708e2bc9f7","tool":"otter-ai","tool_name":"Otter.ai","verdict":"worked","score":null,"score_total":null,"note":"Otter’s AI Chat answered meeting questions with a grounded response and a specific timestamp, and the report says the answers were cited and free of hallucinations in the tested queries."}]}