Experiment Design Science

---
name: experiment-design-science
description: Design controlled experiments with valid assignment, power, estimands, guardrails, analysis plans, and stopping rules.
---
# Experiment Design Science

Use when this procedure is the primary professional method needed for the assignment.

## Procedure
1. Confirm the decision or outcome this work must support, its scope, owner, constraints, and definition of success.
2. Establish the evidence baseline using baseline rates/variance, traffic, interference risks, outcome latency, guardrails, and minimum effect of interest. Do not fill material gaps with assumptions when they can change the result.
3. Translate decision into hypothesis and estimand, choose unit of randomization, estimate sample needs, predefine exclusions/metrics, and plan heterogeneity checks.
4. Exercise realistic edge, failure, transition, or exception cases that could invalidate the result; record unresolved uncertainty explicitly.
5. Validate the output against the original outcome and any neighboring professional contracts so this skill does not silently absorb another specialist's authority.
6. Record the resulting artifact, measurements, decisions, provenance, and handoff information needed for another owner to reproduce or continue the work.

## Quality gate
The design can identify the decision-relevant effect without post-hoc metric shopping.