Start here · hensq

AI agents in real workflows, not just demos.

I test how an agent can move from completing a task to owning a bounded piece of work—then document what succeeds, what fails, and where a person still needs to step in.

All cases are anonymized or synthetic. I do not publish private messages, identities, prices, routes, or unverified business results.

Evidence & field notes

Three useful places to begin

Each card includes an English summary. The detailed field notes are currently written in Chinese.

Daily build log

The short experiments happen on X.

The site keeps the durable models. X has the day-to-day tests, failures, and corrections.

Follow hensq on X →