DEVELOP

Targeted interventions, not generic training.

Every diagnosis points at a structural weakness. Every intervention declares a target metric, a measurement window, and an expected internal-metric delta. We test the repair, then re-measure.

See the re-measurement loop → Start from diagnosis
01 · DIAGNOSIS
02 · SELECT CLASS
03 · DECLARE TARGET
04 · INTERVENE
05 · RE-MEASURE
06 · CLASSIFY RESULT
Intervention system

Five classes of intervention.

Interventions are not a single bucket. They fall into five distinct classes, each with its own evidence base, ownership, and expected effect surface.

CLASS 01

Guides

Written operator guidance targeting specific structural weaknesses.

  • Context construction
  • Task decomposition
  • Project persistence
  • Iterative workflow
  • Verification
  • Model selection
  • Agent orchestration
CLASS 02

Tools

Systems and integrations that change what the operator can do.

  • MCP servers
  • Memory systems
  • Project templates
  • IDE tools
  • Routing systems
  • Context managers
  • Specialized agents
CLASS 03

Workflow changes

Structural changes to how AI work fits into the surrounding process.

  • Stage separation
  • Context handoff
  • Human checkpoints
  • Persistent project state
  • Review structures
CLASS 04

Training

Structured learning programs, internal or external.

  • Internal guides
  • Workshops
  • Role-specific programs
  • External courses
  • Manager coaching
CLASS 05

Human support

People-side support that complements the technical interventions.

  • Operator review
  • One-on-one coaching
  • Team redesign
  • Specialist consultation
SELECTION

Match to diagnosis

Class is chosen by matching the diagnostic hypothesis to the intervention surface. A context-construction weakness suggests a Guide. A persistence weakness may suggest a Tool. A verification gap may suggest a Workflow change. The diagnosis drives the class — not the other way around.

Intervention object

Every intervention is a declared, measurable object.

No intervention ships without a recorded object. The object carries the diagnosis it responds to, the metric it targets, the window it runs in, and the owner accountable for it.

intervention_014
Operator 031 · Context construction guide
ACTIVE DEVELOPMENTAL
intervention_id
intervention_014
target_type
operator
target_id
op_031
diagnosis_id
diag_007 — low context construction score
intervention_class
guides
intervention_name
Context construction playbook v1
start_date
2026-08-20
measurement_window
14 days post-start
expected_internal_metric
context_form: structured → composite (+1 grade)
optional_external_metric
PR review time (engineering cohort only)
owner
pilot team + operator
status
active — awaiting post-window re-measurement
notes
Operator reviewed the guide in a 30-min session. Voluntary. No employment consequence.

The object is the contract between diagnosis and verification. Without it, there is no re-measurement — only anecdote.

The intervention loop

Baseline → intervene → re-measure → classify.

The loop is the unit of evidence. Each pass produces a result classification, not a verdict on the operator.

1

BASELINE

Operator metrics recorded during the evaluation phase. This is the reference point for every delta.

2

INTERVENTION

Declared intervention object applied. Class, target metric, window, and owner recorded.

3

POST WINDOW

After the declared measurement window, telemetry is collected for the same operator over an equivalent span.

4

INTERNAL METRIC DELTA

Target and non-target internal metrics compared baseline vs post. Both are reported — not only the target.

5

OPTIONAL EXTERNAL OUTCOME DELTA

If an external outcome was declared, it is joined and compared. Always ASSOCIATION, never CAUSATION.

6

RESULT CLASSIFICATION

Improved / unchanged / degraded / inconclusive. The classification is about the intervention, not the person.

Guardrails

What interventions are NOT.

The intervention system is developmental. These guardrails are not soft preferences — they are structural constraints on how the product may be used.

NOT PUNITIVE

Interventions exist to improve operator structure. They are never used to rank, penalize, or compare employees for adverse purposes.

NOT SURVEILLANCE

Intervention tracking records the intervention object and the metric delta. It does not monitor employee behavior, content, or conduct.

NOT AUTOMATED ADVERSE ACTION

No intervention, metric, or classification triggers automated employment decisions. Adverse action is explicitly excluded from the pilot terms.

Decision-use labels

Every intervention declares its permitted use.

Decision-use labels govern who may act on an intervention result and for what purpose. They are set at creation and enforced by the pilot terms.

DEVELOPMENTAL

For developmental use

The default label. Results may be used to guide the operator's growth, refine the intervention, and inform coaching. Visible to the operator and the pilot team.

WORKFLOW_EXPERIMENTATION

For workflow experiments

Results may inform workflow design changes — stage separation, handoff structure, review checkpoints. Treated as experiments, not performance verdicts.

RESEARCH

For research

Results may be aggregated and used for methodology research, archetype refinement, and field comparison. Individual identity is governed separately.

PERSONNEL

Elevated governance — not in pilot

Any personnel-related use requires elevated governance, explicit consent, and review structures. This label is not available during the pilot. It exists to define the boundary, not to cross it.

The PERSONNEL label is defined so the product can name what it will not do in the pilot, rather than leaving the boundary implicit.

Next

Once the intervention runs, we re-measure.

The verify phase takes the intervention object and produces the result classification — internal metric delta first, external outcome separately.

Go to Verify →