Agents

We did not turn OpenAdapt into an agent. We admitted who already drives the loop. If you have been watching platform engineering this year, the shift is not subtle. Salesforce spent two and a half years exposing Headless 360 so an agent can call the product without a browser. Stripe and others built payment rails the same way. Arthur Frayman’s line at SCaLE is the one I keep: the human you used to build for is becoming an agent operated by a human. Agents do not need a pretty cockpit. They need constraints, typed actions, and an escalation path that is designed rather than an error dialog. ...

I like computer-use agents for a practical reason: I can give one a goal instead of a script. It can inspect an unfamiliar screen, decide what to do next, and recover from situations I didn’t predict. That flexibility has a cost. The model has to inspect and decide again on every run, even when the task has become routine. The useful OpenAdapt vs. computer-use-agent question is about the shape of the work: should each run interpret the task again, or should it replay a reviewed program and stop when reality differs? ...

A team I would recognize anywhere runs four hundred UI automations against a system somebody else owns. The dashboard is green. The success rate has been 98-point-something for a year. Then a reconciliation turns up eleven records that were updated with values belonging to a different account, all in the same month, all in runs the dashboard counted as successes. Nothing crashed. No exception was thrown. Every one of those runs saw a confirmation banner and believed it. ...

Most software robots re-read the manual every single time they run. A person who has done a task a hundred times does not re-derive it on attempt 101. The robot does. A general computer-use agent looks at the screen, thinks, picks an action, looks again, thinks again, all the way to the end, every run. For a task nobody has seen before, that is exactly right. For the tenth-thousandth triage note in the same clinic, it is a strange thing to pay for: latency, model cost, and a plan that comes out slightly different each time. ...