Alright, I need to vent about Otter.ai. I've been using it for a year to transcribe my team's post-incident reviews and on-call handoff meetings. The transcription itself is decent, but the **search functionality is actively painful.**
My workflow depends on finding specific mentions of services, error codes, or actions from past discussions. Otter's search feels like it's doing a simple text match with no understanding of context. If I search for "pod crash loop," it will dutifully find every instance of "pod" and "crash" and "loop," but not necessarily in that order or proximity. It's like querying logs without regex or filters.
Here’s a concrete example from a recent incident post-mortem:
* The transcript clearly contained: "We saw elevated latency on the **checkout-api** service around 02:00 UTC."
* Searching for `"checkout-api"` returned the result.
* Searching for `"checkout api"` (without the hyphen) returned **nothing**. No fuzzy matching, no leeway for a common typo.
For someone who lives in tools where search is powerful and precise (PromQL, Loki, etc.), this is a major bottleneck. It turns what should be a quick data retrieval task into a manual scanning chore.
I've resorted to exporting all transcripts and dumping them into a separate search tool, which defeats the purpose. Has anyone else built a better pipeline for this? I'm considering writing a script to sync Otter exports into an observability stack just to get proper log-like search.
— zzz
Sleep is for the weak
That's a really specific and frustrating example. I've found the same kind of rigidity in search across a few platforms, not just transcription tools. It's like they're built for perfect, typed input, not for the messy way people actually talk or make notes.
The lack of fuzzy or proximity search in a knowledge retrieval tool is a real problem, especially for incident reviews where terminology gets tossed around loosely. Have you submitted this as direct feedback to them? Sometimes that specific use case you described - searching with and without a hyphen - can be the kind of concrete example that gets a feature request prioritized.
Stay constructive
Exactly! The mismatch between how people search and how the tool expects the input is the core issue. I run into this all the time with marketing planning sessions - people say "Q2 promo" in the meeting, but I might search for "second quarter promotion" later. A simple text matcher fails completely.
Have you found any tools that handle this decently? I've been testing a few and their search is almost as big a decision factor as the transcription accuracy for me now.
Data > opinions