Evaluate

Measure the operating system, not the conversation.

We do not read prompts. We do not read responses. We measure the structure of AI operation — input, output, cache, context, leverage, yield, stability, and trajectory. The operating system is observable without reading the conversation.

Design a 30-Day Evaluation See How We Diagnose
INPUT
OUTPUT
CACHE READ
CACHE WRITE
LEVERAGE
YIELD
OPERATOR PROFILE
Canonical primitives

Four primitives. Everything else is derived.

Every AI interaction reduces to four measurable primitives. All higher-order metrics — leverage, yield, token SNR, context reuse — are constructed from these. Nothing else is required to measure operation.

01

INPUT

Tokens submitted to the model in a given turn. Includes prompt, context, attachments, and reused prior output.

measured
02

OUTPUT

Tokens returned by the model in a given turn. The generated response, before any downstream use.

measured
03

CACHE READ

Tokens retrieved from context cache — prior context reused without re-submission. Indicates context persistence.

measured
04

CACHE WRITE

Tokens written to context cache for future reuse. Indicates deliberate context construction.

measured

These four primitives are content-free. No prompt text. No response content. No code. The structure of operation is fully observable from token counts and cache behavior alone.

Core metrics

Five metrics. Each derived from the primitives.

From four primitives we construct five core metrics. Each has a construct definition, a mathematical definition, and a valid domain. Each is labeled MEASURED because it is computed directly from telemetry — not inferred.

MetricDefinitionStatus
leverage Output tokens relative to net new input tokens. How much value the operator extracts per unit of input they author. High leverage = the operator makes the model do more with less new prompting. measured
yield Usable output tokens relative to total output tokens. How much of what the model generates is actually retained, committed, or carried forward. High yield = low waste. measured
token_snr Signal-to-noise ratio across the token stream. Distinguishes productive tokens from redundant or discarded ones. High SNR = the operator's token budget is spent on signal. measured
log_leverage Log-scaled leverage to normalize heavy-tailed distributions. Compresses extreme values so a few high-leverage sessions do not dominate the operator's profile. measured
construction Ratio of cache writes to total input. Measures how deliberately the operator builds reusable context versus re-prompting from scratch each turn. measured

Every metric is traceable to the primitives. Every score is reproducible from the telemetry. No metric is inferred from behavior, personality, or self-report.

Operator profile module

Every operator becomes a profile. Every label is traceable.

The operator profile is the core deliverable of evaluation. It aggregates the five core metrics plus derived fields — context reuse, stability, trajectory, volatility, and operating pattern — into a single traceable record.

OPERATOR 031
measured
Field Position
84th percentile
Leverage
43.2x
Yield
8.7
Context Reuse
HIGH
Stability
82
30-Day Movement
+14%
Volatility
LOW
Operating Pattern
RECURSIVE / BUILD-HEAVY

Every diagnostic label must be traceable to underlying measures. "RECURSIVE / BUILD-HEAVY" is not a personality assessment — it is a pattern derived from high construction, high context reuse, and stable yield across sessions. Show the measures, then the label.

Data discipline

What we do NOT measure.

Measurement discipline means knowing what to exclude. We collect the minimum evidence required to answer the measurement question. The following are explicitly NOT required for core evaluation.

Not required

  • Prompt content — the text of what operators type
  • Response content — the text the model returns
  • Code content — the source code in inputs or outputs
  • Email content — the body text of messages
  • Slack content — the text of channel messages
not required

Core

  • Token telemetry — input, output, cache read, cache write counts
  • Cache behavior — read/write ratios, reuse patterns
  • Session structure — turn count, session length, provider, model
  • Temporal patterns — cadence, gaps, burstiness
core
We do not collect everything because it exists. We collect the minimum evidence required to answer the measurement question. Token telemetry is core. Content is not.
Measurement science

Twelve requirements before a metric ships.

A number is not a metric. A metric is not a measure. A measure is not a construct. Before any metric enters the operator profile, it must satisfy twelve requirements. This is what separates measurement from dashboarding.

01

Construct definition

What does the metric claim to represent? Named, defined, and bounded in plain language.

02

Mathematical definition

The exact formula. Reproducible from the primitives by anyone with the telemetry.

03

Valid domain

The range of inputs over which the metric is defined and meaningful. Where it breaks.

04

Unit

The unit of measurement. Tokens, ratios, percentiles, log-scaled values.

05

Directionality

Which direction is better? Explicitly stated. No metric is "good" without a defined polarity.

06

Distribution

The expected distribution across operators. Heavy-tailed, normal, bimodal — known and accounted for.

07

Normalization

How the metric is normalized across providers, models, and session types. Comparable across contexts.

08

Reliability

Does the metric produce the same score for the same telemetry? Test-retest consistency.

09

Validity

Does the metric measure what it claims to measure? Construct validity, not face validity.

10

Sensitivity

Does the metric detect meaningful change? Not so coarse that real improvement is invisible.

11

Decomposability

Can the metric be broken down by provider, model, session type, and time window? Diagnosable, not opaque.

12

Traceability

Every score traces back to the primitives and the telemetry that produced it. No black boxes.

Canonical labels

Every claim in the system carries a canonical status label. The label tells you how much trust the claim has earned — and what would be required to promote it.

StatusPROVEN proven
StatusMEASURED measured
StatusOBSERVED observed
StatusDERIVED derived
StatusHYPOTHESIS hypothesis
StatusPILOT pilot
StatusVALIDATION REQUIRED validation required

No claim is promoted without evidence. A HYPOTHESIS becomes VALIDATION REQUIRED before it becomes PROVEN. The label is the contract.

Next

Profiles become diagnoses. Diagnoses become interventions.

Evaluation produces the operator profile. Diagnosis turns the profile into actionable strengths, weaknesses, and hypotheses.

See How We Diagnose Workflow Fit