Track T07
Follow this capability from individual use to systems other people can depend on.
At Level 3 Builder, other people may rely on what you build. Your first agent therefore needs less freedom than the demonstrations that make agents look impressive: one job, two or three narrow tools, a hard stopping condition, visible traces, and a person who approves the proposed result.
At Level 4 Integrator, a routine triage run is about to meet a sentence written for the agent rather than for its human reader. You will test whether that sentence can redirect a synthetic action, then produce evidence that the corrected design stops it.
The agent from T07-L04 · Agents with real credentials has a narrow identity, read-only inputs, no arbitrary network access, and no authority to publish. It can safely propose a disposition for one synthetic document. Now the queue is growing. You split the job into a retrieval agent, an extraction agent, and a...