Skip to content
&Dolphin
Blog
AI

Treating the token budget as structure, not a feature

Growing the context window defers the problem. Decide what not to include first.

Contents

Growing it looks like a fix

Longer prompts cost more. But cost is not the real problem.

java
String prompt = systemInstruction + conversationHistory + retrievedDocuments;

As retrievedDocuments grows, the ratio of what the model must read to what it may ignore gets worse. Doubling the context does not double the answer quality; it doubles the room to blur.

Give each part a budget

A prompt that gains a paragraph per feature will not last. Fix the slots first, then let content compete inside them.

SlotCapOn overflow
System instructionfixedCannot overflow. If it does, the instruction is wrong
Conversation history30%Fold the oldest into a summary
Retrieved documents50%Drop the lowest scoring first
Headroom20%So the answer is never truncated

Keep the rule in config, not in code

Hard-coded caps mean a deploy every time the model changes. In config you can tune them in production and learn which cut actually hurts the answer from real traffic.

Finding what cannot be cut is the design work. Growing the window postpones it.

Treating the token budget as structure, not a feature | &Dolphin