Agents earn autonomy from your review history

Task Machine can now learn from the approvals, rejections, and corrections you already make. When an agent has built a clear track record, it suggests whether that agent should receive more independence or closer supervision. We built this because every review you make already teaches an agent something, and that record should count.

Task Machine looks for a consistent pattern across past decisions rather than reacting to one good or bad result. When the pattern is clear, a proposal appears in the Inbox explaining the suggested change and what the agent would be allowed to do differently.

You decide whether to apply or dismiss it. An agent never raises or lowers its own autonomy.

Fix the instructions instead of repeating the correction

A pattern of similar corrections can also show that the agent's standing instructions need to change.

In that case, Task Machine can propose revised instructions. The Inbox shows the pattern it found, examples from earlier decisions, the expected effect, and the exact wording before and after the change. You can approve the replacement or keep the current instructions.

After an approved change, the agent starts building a new track record for the revised behavior. Budgets, approval steps, company rules, and required reviews continue to apply at every autonomy level.

Read Autonomy levels in practice for how each level changes the work that comes back to you.