This is probably how AI-native product analytics should work.

Dashboards was for humans. For AI agents, they're a pretty bad interface.

That's the direction Human Behavior is taking.

It watches sessions, funnels and errors continuously, works out what changed and why, then hands that context to agents that can act on it: open a PR, file the ticket, post it in Slack, pull the numbers.

Its SDK captures sessions, clicks, network calls, and errors.

You can ask questions like "why did signups drop?" and its agents work across the available product context rather than treating the question as a standalone prompt. The same context can then flow into tickets, PRs, Slack messages, reports, or follow-up investigations.