# How much of AI spending is paying a model to reread its job description?

> Source: <https://discuss.huggingface.co/t/how-much-of-ai-spending-is-paying-a-model-to-reread-its-job-description/191350#post_7>
> Published: 2026-11-18 20:00:25+00:00

**Recommendation:** Build each agent's stable role, authority, constraints and history deterministically once before inference, then pass only task-relevant context per call instead of re-serializing full state.
More in the playbook "Designing agent systems": <https://wpnews.pro/playbooks/agent-architecture>

The practical version of this question is not only “how much context can we compress?” but “which stable worker state should be assembled once before inference?” Paper 3 reports a bounded study of repeated state serialization versus pre-inference deterministic worker construction. It is a useful way to separate task-relevant context from repeatedly rebuilding role, authority, constraints, and history.
