Measurement
Metrics and scoring.
What you measure determines what you optimize. Most teams measure the wrong things about their AI systems — total tokens consumed, response time, cost per API call — because those are the easiest to track. But easy metrics aren't always meaningful metrics. These terms define the measurements that actually matter: the ones that connect token spending to task outcomes, and that reveal whether your AI system is getting more efficient or just more expensive.
Context Efficiency
Useful retained state per token consumed.
Token ROI
The measurable value produced per token consumed. The business metric for Context Efficiency.
Context Utilization Rate
The percentage of input context that the model actually uses for its output. Low rate = waste.
Recall Cost Ratio
The cost of retrieving stored context vs. the cost of re-generating it from scratch.
Waste Ratio
The proportion of tokens consumed that produce no useful output. The metric behind Token Bleed and Token Burn.
Iteration Velocity
The speed at which a human-AI pair can move from idea to tested output.
Recovery Cost
The time and tokens required to get a session back on track after a failure — State Loss, Execution Hallucination, or Plan Drift.
Quality-Per-Token
A measure of output quality relative to tokens consumed. Distinct from Token ROI (value) — this measures correctness, completeness, and relevance per unit of cost.