Principle
Use progressive disclosure for agent instructions
Do not make every future task pay the context cost of every past instruction.
When it fits
- A reusable agent has many procedures, references and edge cases.
When to avoid it
- Deferred context is useless if triggers are vague or search is weak; critical safety rules may need to remain always visible.
Why it matters
Keep the always-loaded layer small: purpose, trigger cues and essential constraints. Put task procedures in an invoked skill or workflow, and supporting references behind links or files that can be opened when needed. Design names and descriptions so the agent can discover the right material without preloading it all.
An example
A GitHub agent sees one short rule for release work; the detailed release checklist and rollback references load only when a release task is detected.
Check your result
Removing an unrelated skill's full text from a normal task does not reduce success.
Keep this limit in mind
- Deferred context is useless if triggers are vague or search is weak; critical safety rules may need to remain always visible.
Connected ideas
Useful withTurn a recurring AI workflow into a skill only when the trigger is clear
Evidence and sources
Anthropic describes progressive disclosure as letting agents discover relevant context incrementally instead of loading all available material up front.
Progressive retrieval depends on discoverability and can be slower than up-front loading.
Effective context engineering for AI agents · Agentic search and progressive disclosure