Locus reads every conversation your agent has had, groups users by what they actually do, and shows the picture in one view. The first memo is free.
See who your users are by what they actually do. Cohorts that match behaviour, not plan tier.
Read every conversation. Auto-classify into intents and use cases. Find what they're really asking for.
Track value, not just volume. Get told when your agent is losing trust, before retention reflects it.
Locus groups every user by behaviour, surfaces their cohorts, and shows you which group is growing or shrinking week over week.
Locus auto-classifies every conversation into intents and use cases. You see what they're trying to do, not just what they did.
Locus watches whether your agent is creating user value and flags drift before it shows up in retention.
Six sections, every one something you can take into a roadmap meeting tomorrow. No traces, no token counts, no dashboards.
Of users who accepted the agent's draft on a first attempt, a third re-edited more than half the output before sending it. Acceptance was a politeness signal — not a value signal.
Each one is a real excerpt from a snapshot memo, names redacted. The shape of the pattern is what carries over to your team.
44% of completed runs ended with the user editing more than half the output before sending it.
Acceptance was a politeness signal, not a value signal. Users accepted, then redid the work elsewhere.
Code-first users dropped 36% in trust over 12 weeks, four weeks before retention reflected it.
An emerging ‘edit my email’ cluster grew 5x in three weeks. The team had no name for it yet.
High-usage users were not happy users. The strongest engagement scores tied to the highest rephrase rates.
Three product events would have caught the trust drop a month earlier. None of them existed in the codebase.
For most teams a sanitized sample is enough. For teams under stricter rules, the entire pipeline runs inside your VPC. Nothing ever leaves your network.
If you're past internal testing and have at least a few hundred real-user runs over the last month, the snapshot will work. Below that, we'll tell you on the call — there's not enough behaviour to read, and a memo would be guessing.
Two paths. We can do a structured discovery audit using only synthetic examples and your team's notes — narrower findings but still a usable read. Or we hand you a container image and you run the pipeline inside your VPC. Nothing leaves your network in either case.
100 to 500 sanitized runs is the sweet spot. Less and the patterns are noisy. More and we don't read the extra carefully — we cap at 500 to keep the memo specific.
If the snapshot is useful, we offer a four-week paid pilot — bigger sample, two follow-up memos, drift tracking, and a final read-out. Pricing depends on volume. We only suggest it if the first memo earned the next conversation.
You can. Most teams that try end up reading twenty conversations a week and calling that research. The snapshot exists because reading at the volume that produces real patterns takes a system, not a person.
Pick a time. We'll walk through what a snapshot would look like for your product, on your terms.