Today we are introducing AI Deboringifier by Krisp
by•
We reduced noise. We improved clarity. We even changed accents.
But sometimes the biggest meeting problem isn't background noise. It's Todd.
odd from Finance. Todd who turns a 30-second update into a 12-minute spoken-word essay about spreadsheets. Todd who says "just to piggyback off that" and then doesn't piggyback — he builds an entire second pig.
So we built AI Deboringifier™
A Voice AI feature that detects boring speech patterns and automatically makes them less boring.
https://x.com/krispHQ/status/2039388954902847648
54 views
Replies
The "Todd from Finance" archetype is universal 😂 Every team has at least one.
This is a genuinely interesting direction for Krisp — moving from technical noise removal (background sounds) to semantic noise removal (rambling content). That feels like a much harder and more subjective problem, and honestly a braver product decision.
Curious how you handle edge cases: someone slow to the point because they're building context vs. someone who's genuinely verbose with no signal. The former is frustrating to filter without losing substance.
Building Hello Aria — our AI productivity assistant for WhatsApp/Telegram/iOS (launching on PH April 10th) — we hit similar "what counts as signal vs noise" questions when summarizing long message threads. Context always matters. No clean answer.
Would love to try this on my next all-hands. Some meetings are 80% Todd.
"he builds an entire second pig" - that got me.
Honestly the hardest part of any meeting isn't the technical issues, it's the person who mistakes airtime for impact. Curious how the model was trained though - did you have to sit through thousands of hours of Todd to build this, and if so, is the team okay?