Narrow the agent’s
world to what matters.

Only material the agent needs to reason about this task is in scope; stale or adjacent context is pruned before invocation.

agent is pointed at the relevant subset of the codebase for a given task, not the whole surface area; boundaries are structurally enforced, not advisory

Work is broken into typed, scope-bounded units before an agent is pointed at it.

solution space is narrowed *before* coding starts

Authoritative source material sits in the repo, not in the training data; agents cite it rather than guess.

architecture and technology decisions captured with reasoning, alternatives considered, and context at time of decision; retrievable before related changes

Figma specs, design system docs, component library, and UX guidelines available as agent context for UI/UX work

operational and product docs** — runbooks (ops / infra), feature specs, user guides, admin and dev docs exist, are current, and are consumed by agents. Produced with the work that needs them, *and* retrievable as agent context for downstream work

per-client preferences, business constraints, IP boundaries, compliance posture, and relationship history captured and retrievable. Distinct from 1.8 (operational and product docs) — this is *relationship* knowledge

structured signal from user reviews, support tickets, bug reports, meeting notes, and app store ratings enters the agent's context pool. The focus is *signal quality*: bug reports enriched with environment / version / reproduction; meeting notes processed with participant / topic metadata; reviews classified by feature area. A raw "it's broken" note is noise; a structured repro is focus. Ingestion is the last boundary before external content becomes persistent agent context; both instruction-shaped content (`PL4-prompt-injection-defence`) and personal information (`PL4-pii-masking`) are sanitised here, not downstream. (Automation of the ingestion loop itself is scored in `PL5-signal-driven-tasks`.)