Skip to content
How to ThinkIn the Age of AI

Fine-grained notes for frequent precise lookups, coarse…

Match note granularity to retrieval frequency and question complexity: create fine-grained atomic notes (single claims) for domains where you need precise retrieval, and coarser aggregated notes for domains where you need high-level orientation.

When This Fires

  • Designing the structure of a new knowledge domain in your system
  • Noticing that some domains have too many tiny notes to navigate while others have too few to search
  • Deciding how finely to decompose notes about a new topic
  • Balancing depth (atomic notes) against navigability (summary notes)

Common Failure Mode

Making everything atomic. A domain where you only need quarterly orientation now has 200 atomic notes that you scroll through without finding a high-level summary. Or making everything coarse: a domain where you need precise daily lookups buries the answer inside 2,000-word summary notes. The mismatch between granularity and use pattern is where the friction lives.

The Protocol

For each domain in your knowledge base: (1) Assess retrieval frequency: daily, weekly, monthly, rarely? (2) Assess typical question complexity: simple lookups or complex reasoning? (3) Map: high-frequency + simple questions → fine-grained atomic notes. Low-frequency + complex questions → coarse aggregated summaries. Mixed → maintain both levels (atomic notes linked from summary hub notes). (4) Review granularity when your use pattern changes — a domain that shifts from peripheral to core needs granularity refinement.