Orion finds friction in your UX and product.
Connect your PostHog session replays and instantly find 2x as many issues.
Try it yourself: https://t.co/zR4pg9qzwu
Introducing Orion, a foundation model that predicts where you look. Orion finds twice as many UX bugs as frontier models, cuts computer-use latency by 31%, and even won a drone race.
Introducing Orion, a foundation model that predicts where you look. Orion finds twice as many UX bugs as frontier models, cuts computer-use latency by 31%, and even won a drone race.
@gregpr07@jeffreyhuber For example we have companies with thousands of hours of meetings
Semantic search is essential to answer many queries for this use case
@gregpr07@jeffreyhuber Depends what you are searching on
But an agent with really good semantic search and having to IR on a complex enough dataset can get massive efficiency gains from a well configured vector DB
I think the way 90% of devs use vector DBs are pretty much useless though
@maxkolysh Think Codex can do this now as of a few days ago
Also for meeting recorders my startup handles this very well as we work lots of fractional CROs
@natetucker Not ours! We detect meetings live not via calendar. We only look at calendar to optionally enrich data post call which would be unaffected in this case
Would love to talk Nate