LLM Operations

Token Budgets Are an Architecture Decision

A model call is a metered dependency with context limits, latency, and failure modes. Those constraints belong in the architecture from day one.

Yakir Yaacov · August 2026 · 4 min read

A workflow can be accurate in testing and still fail in production because a larger room, longer document, or richer search result pushes one request beyond its useful boundary.

Bound the unit of work

I prefer small, independently retryable batches over one enormous prompt. A room, a bounded group of line items, or a single document section provides a natural unit. If batch seven fails, the system retries batch seven—not the entire report.

Track the reason, not just the total

Total monthly tokens do not explain waste. Usage records should include the application, task type, model, claim or job, input tokens, output tokens, latency, retry count, and final status. That makes it possible to find expensive prompts and failures that repeatedly consume context.

The most expensive AI request is often the successful request whose output cannot be parsed or attributed.

Design the fallback explicitly

Retries need limits. Truncated JSON needs validation. A fallback value must never masquerade as a real result. If pricing fails, the UI should say pricing failed—not quietly write zero dollars. If evaluation is incomplete, the report should remain incomplete.

Optimize after observability

Once usage is attributable, optimization becomes concrete: reduce repeated reference material, cache stable descriptions, select only relevant examples, compress search results, or move deterministic transformations out of the model. Cost control is then an engineering exercise rather than guesswork.