Writing from the Barkan team.

Field notes on activation, onboarding and support from the team building an AI Customer Success Manager that lives inside your product.

• When your AI support agent should stop talking — The useful support agent is not the one that keeps every conversation automated. It is the one that recognizes its limit and hands over the work without making the customer start again.
• Your AI agent's approval prompt is a permission boundary — Confirm everything and users stop reading. Confirm only the goal and consent becomes dangerously broad. The useful boundary sits at the exact action that changes the world.
• The second-workflow problem: why activation dies after the first win — Signup is instrumented to death. The moment that decides retention happens later, when a user tries the real thing your product is for — and nobody is watching.
• Why Barkan reads the screen, not the docs — Documentation describes the product in general. The DOM describes it for this user, right now. A look inside how Barkan turns a live page into something a model can act on.
• Nobody reads your documentation — and your activation rate proves it — Your docs are not bad. They are in the wrong place, written at the wrong altitude, and read at the wrong moment. Here is the anatomy of the gap — and the four behaviors that close it.