Otter does not show a direct transcript keyword-search workflow in the transcript view; lookup is routed through AI Chat instead, where a natural-language timestamp question returned a specific answer at 0:07:06.

◐ Mixed🧾 artifact-verifiedinput + output shownTest date not recordedOtter.ai
What was measured
Search Across Notes

Finds a moment or decision by keyword or question.

context, not decisivecapability

Search helps users find past moments and decisions, but it is a retrieval feature rather than proof that the tool captured the meeting well. (3 of 3 judges)

What was given, what came back

Test input: AI Demos Daily Standup — 31 July 2026 · image · group: ai-meeting-notetaker
Input — what we sent
AI Demos Daily Standup — 31 July 2026
AI Demos Daily Standup — 31 July 2026

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.

Why this input is hard
  • · 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
Output — unretouched
Output 1
Output 1
Output 2
Output 2
Output 3
Output 3
Also checked on this input — same tool, 9 other criteria
Action-Item Extraction⚠ StruggledOtter extracted action items, including at least one due-today API-related task with an assignee, but the report says most items were left without an owner and duplicate entries also appeared, so the output needed manual cleanup before delegation.Chat with Notes / Ask Questions✓ WorkedOtter’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.Editability✓ WorkedOtter exposes inline editing controls for transcript and summary outputs before sharing, so wrong content can be corrected in-product rather than only exported as-is.Join Method & Reliability✓ WorkedOtter’s bot joined Google Meet successfully and stayed connected through the full ~25-minute call with no mid-call dropout or ejection, so the meeting was captured end to end.Sharing Without Registration✓ WorkedA shared meeting transcript opened without requiring sign-in, exposing the meeting title, metadata, and transcript snippets; the share dialog also offers restricted access and link-copy controls.Speaker Diarization✗ FailedOtter’s diarization was effectively unusable in this multi-speaker standup: only 1 of about 10 active speakers was identified by name, while the other 9 were left as generic labels or unattributed, which the report summarizes as a 90% failure rate.Summary Quality✓ WorkedOtter produced a clear, structured meeting summary that the report says covered the key decisions and discussion points without dropping anything important, and the summary page loaded with organized sections like Overview and Action Items.Topic Segmentation✓ WorkedOtter 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.Transcription Accuracy✓ WorkedOtter 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.
Provenance
Observation
68c18886-3c73-4ed3-bd68-92814dc4b10b
Evidence run
ace58582-3d1e-48ee-996c-9b3cd03f27a2
Study
AI Meeting Notetakers — Capture Accurate Transcripts, Summaries & Action Items From Live Calls
Research task
86baxegnv
Tested at
not recorded
Source
first-party
Evidence state
verified
Proof shown
input + output shown
Cost / latency
not captured
Repeat run
not captured
Tester
not captured

The last three rows are honest blanks, not placeholders — our capture has no field for them yet.

Query this
get_evidence({
  tool: "otter-ai",
  scenario: "ai-meeting-notetaker"
})
MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 7 other tools
measured on Search Across Notes
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com