AI by Hand ✍️

AI by Hand ✍️

Usage Forecast

From three calls to a day

Prof. Tom Yeh's avatar
Prof. Tom Yeh
May 28, 2026
∙ Paid

Library › Token Problems

  1. Tokenization

  2. Subword Tokens

  3. Non-Word Tokens

  4. Token Ratio

  5. Headroom

  6. Token Pricing

  7. Prompt and Completion

  8. The Billing Line

  9. Asymmetric Pricing

  10. Words to Cents

  11. Token Mix

  12. Usage Forecast

  13. Standing Instructions

  14. Fixed Overhead

  15. Budget Ceiling

  16. Token Allowance

  17. Two Speeds

  18. Output Bound

  19. Rate Cards

  20. Usage Audit

How do you estimate total usage when every call is different? Average a sample of recent calls to get a representative size, then multiply by the expected volume. Plans and budgets scale from the average, not from any single call. Agents running at production scale need this estimate to set daily budgets and catch cost spikes early.

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