Notes from the team.
How to read AI conversations at scale, why behavioural groups matter, and what to do with the five that actually explain the rest.
- § 01The whole picture8 min read
What Locus is, and why we built it.
Locus is product analytics for AI agents. It reads every conversation your agent has had, groups users by what they actually do, and shows the picture in one page.
Read - § 02Product analytics4 min read
The data is already there. Your team just can't read it.
Every AI agent logs every conversation. The volume is unreadable by hand, and no existing analytics tool can parse free text. Here's what that costs product teams — and how Locus changes it.
Read - § 03Segmentation3 min read
Plan tier is not a behaviour.
The user groups that matter for product decisions aren't demographic — they're behavioural. Here's why plan-tier segmentation misses the point, and what to use instead.
Read - § 04Method5 min read
Why the sample of twenty fails.
A human can read maybe twenty AI conversations a week. Most product decisions are made on that sample. Here's why the sample is biased, and what a team can do about it.
Read