Prompt stuffing

Cramming every rule, example, and document into a single prompt instead of selecting the information the model actually needs for the current task.

Prompt stuffing is adding rules, examples, and documents without a selection or maintenance strategy. The prompt can accumulate stale and contradictory instructions even while staying inside the context limit. Length alone is not the failure; a long relevant source may be appropriate. The problem is that each addition lacks a demonstrated job and ownership.

Builder example

Unused context can add cost and latency, obscure which instruction caused a behavior, and complicate updates. Stable reference data might belong in retrieval, a configuration file, a tool, or a shorter maintained instruction, depending on how it is used. Compare the revised design with the original on the same cases rather than assuming shorter is always better.

You paste every rule, example, and edge case into one prompt. The model gives a confused answer because two of the instructions say opposite things.

Select the rules that apply to this specific task. Move rarely-used rules into a reference the model can pull only when needed.

Common confusion: Prompt stuffing is different from deliberately using long context. Long-context use means carefully providing a large, relevant document for the model to work with. Prompt stuffing means throwing everything in without selecting or organizing it.