Agents that work for days without a person watching.
Agents can now keep working on one task for longer. Practices that work for a ten-minute run fail over a week. Posts cover what the measurements show about long runs. They also cover what an operator has to set before a long run starts: the context the agent gets, the steering it runs under, and the record it leaves.
Agents raise questions, CI fails at night, and results pile up for review. The Console asks each decision as a choice, and the Work board turns a drag into the action it means.
An auditor should not have to trust the vendor that kept an agent's record. Oxagen 5.5.0 checks evidence offline, maps AIUC-1 control by control, and scores operators from the record.
A long run hides its failures in hundreds of steps. The Run page now lists the run's loops, refusals, setup failures, and failing tools, and tells a wrapped agent when it loops.
An agent can write a change in minutes. Then the change waits for a person to read it. This post measures that wait, what eight companies changed about it, and how Oxagen ships at every hour.
When a long run goes wrong, most teams can stop it or type at it. Both work badly. A steer is a third option. It is a message with a delivery mode, a status, and a record.
METR measures how long a task an agent can finish on its own. That length has doubled about every seven months since 2019. This post covers what week-long runs mean for supervision.
The worry about AI slop is about output quality. The measurements point to a different cause. Teams give an agent a workflow built for people and expect it to work.
A prompt file has no owner, no date, no scope, and no record that the agent read it. So it is a poor place for a standing rule. Steering records give each rule those things.
