AI by Hand ✍️

AI by Hand ✍️

Search Rounds

Three searches, three unknown sizes

Prof. Tom Yeh's avatar
Prof. Tom Yeh
Aug 19, 2026
∙ Paid

Library › Context Problems

  1. The Context Window

  2. Window Occupancy

  3. Growth per Turn

  4. Remaining Space

  5. Turn Budget

  6. Retrieval Footprint

  7. Retrieval per Turn

  8. Search Rounds

  9. Window Sizing

  10. Truncation

  11. Compaction

  12. The Compaction Bill

  13. Compacted Retrieval

  14. The Compaction Threshold

  15. Verbatim Tail

  16. Stateless API

  17. Retrieval Cost

  18. Context Tax

  19. Quadratic Cost

  20. Cost Forecast

An agent that searches does not know in advance what it will get back. A query that finds nothing still costs a query, an empty result and an answer, and the window keeps all three: nothing is thrown away between rounds. So the cost of searching is not the cost of the search that worked, it is the cost of every search that came before it as well. Watch what one successful retrieval does to a window that two failed ones had barely touched.

Paid members: the worksheet and its printable PDF are below ↓

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2026 Tom Yeh · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture