Skip to content
~/agentops
← all factors
IIIBRIEF THE AGENT

One Agent, One Job

Give each job the smallest sufficient agent; a job one agent can finish gets no orchestration.

Rule

Give each job the smallest sufficient agent: one bounded job, one fresh context window, no more machinery than the job needs.

The corollary cuts the other way: a job one agent can finish gets no orchestration. If a single agent with a clear brief can do it, every coordination layer you add is one more thing that can fail. Scale the agent shape to the work: split when context needs differ; keep one agent when they don't.

Put It to Work

  • Scope each assignment tightly enough that completion is obvious.
  • Split research, implementation, review, and release work when their context needs differ.
  • Start a new session for a new phase instead of appending work to a saturated thread.
  • Reach for a single agent first; add coordination only when the work demonstrably exceeds one.

Failure Signal

  • A research-heavy session starts editing code from stale assumptions.
  • A five-minute fix acquires a plan, a queue, and three coordinating agents.
  • The task cannot be summarized in one sentence.
  • The session is kept alive because "it already knows the project."

Done Looks Like

The agent has one job, one owner, one workspace, and a clear stopping condition. The setup is no bigger than the job required.

In AgentOps 3.8: native execution needs zero AgentOps skills, and the primary entrypoints are independent choices: implement a clear request directly and reach for Plan only when behavior or scope is unclear.