The AI Taxonomy.
Terms  /  Context Quality  /  Signal Density
01 · Context Quality

Signal Density

The ratio of useful information to total tokens in a prompt. High signal density = low reasoning tax.

Signal Density is the metric behind Context Clarity. It answers a simple question: of all the tokens in this prompt, what percentage is the model actually going to use? A prompt with 90% Signal Density means 9 out of 10 tokens are doing useful work. A prompt with 20% Signal Density means the model is wading through 4 tokens of noise for every 1 token of value. Low Signal Density is the primary driver of Reasoning Tax — the model is literally paying to read things it doesn't need.

Example
Two teams send the same coding task to the same model. Team A's prompt is 5,000 tokens with Signal Density of ~25% — it includes the full README, the entire config file, and three pages of API docs, when only the endpoint signature matters. Team B's prompt is 1,500 tokens with Signal Density of ~85% — just the function to modify, the relevant type definitions, and the specific requirement. Team B gets better results at 30% of the cost. The model didn't get smarter for Team B; it just had less noise to filter.

More in Context Quality

Context Debt

Accumulated ambiguity, redundancy, and disorder in a conversation or prompt.

Context Load

The total volume and complexity of context a model must process in a single call.

Prompt Bloat

Oversized, redundant context that forces unnecessary reasoning.

Context Clarity

A state where the prompt contains only what the model needs — no ambiguity, no redundancy, high signal. The opposite of Context Debt.

Prompt Hygiene

The practice of keeping prompts clean, structured, and free of accumulated noise. Preventive maintenance against Context Debt.

Context Freshness

How current and relevant the context is to the task at hand. Stale context — old instructions, outdated facts — increases reasoning cost even when well-structured.

Structured Context

Context organized with clear hierarchy, roles, and boundaries — making it machine-parseable, not just human-readable. The architectural practice behind Context Clarity.