The use case: how Exa deploys PostHog
Exa, an AI-powered semantic search engine company, centralized its previously scattered analytics into PostHog. Its engineers use product analytics, SQL with PostHog AI assistance, and session replay to debug errors, validate hypotheses and ship fixes.
In the customer’s words
The best thing for me is PostHog AI. It's really nice to have it help with SQL queries when you're like 80-90% of the way there and it can finish them for you. If I get something wrong with one of my SQL operations, PostHog AI can just fix it up for me.Other AI tools used by Exa
Other public relationships recorded on usedby.
Explore Exa’s AI stack
PostHog users in Artificial Intelligence
Companies in the same sector, with public evidence.
Arena (LMArena)Confirmed
ElevenLabsConfirmed
LovableConfirmed
DocsBotDeclared
FiniDeclared
InkeepDeclaredGo straight to the source
Based on PostHog’s published case study. We check the public evidence; the results are reported by the vendor.
posthog.com- Last checked
- Nov 12, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Exa.
- Exa uses PostHogChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Now, with analytics centralized into PostHog, the team can much more flexibly and reliably interrogate data from multiple sources using a mix of ready-made visualization tools (funnels, paths, etc.) and SQL when needed.