Optimize Agents
Measured improvements to agent loops — after analyze; never during thrash.
What it is
Section titled “What it is”Measured improvements to agent loops — after analyze; never during thrash. This practice is a skill-mapped TTP: when, why, and which command—not a full copy of the skill. Open the skill to execute.
Why it works
Section titled “Why it works”Optimize after measure (NIST AI RMF Measure → Manage). Cap steps/tools and simplify composition before adding models—Anthropic’s guidance favors simple, evaluable agent patterns over sprawling swarms.
When to use it
Section titled “When to use it”When the situation matches the one-liner above and Orientation (or your project path) says this is the fire to touch now.
- Invoke the skill; follow its safety rules
- Keep one write owner; collect evidence before claiming done
- Hand off to the next practice instead of boiling the ocean
- Skip orientation when you’re lost
- Spawn overlapping agents to “go faster”
- Treat the practice as done without evidence
Related concepts
Section titled “Related concepts”07-stop-conditions, 03-smallest-next-step
Further reading
Section titled “Further reading”See also the handbook Sources & grounding bibliography.
Agent skill
Section titled “Agent skill”agents optimize