Loading
A structured readiness checklist for teams about to run an experiment, pricing change, pilot or campaign test. Work through eleven design areas and find out whether the analysis could credibly answer “did it work?” (before money and credibility are committed to the answer).
A completed checklist returns one of four readiness verdicts: ready for a simple experiment; requires instrumentation first; requires an alternative, quasi-experimental design; or not currently identifiable, meaning no analysis of the current design could credibly isolate cause.
Alongside the verdict you see readiness by design domain, the main threats to validity in your set-up, the missing instrumentation or governance, and the minimum steps to complete before any analysis runs. A team planning a pricing pilot might find, for example, that the outcome metric is well defined but no comparison group exists, so the next step is design work, not launch.
You document the decision, intervention, outcome metric, comparison group, assignment, sample, timing, confounders, data lineage, ethics, implementation stability and analysis ownership. The checklist applies rule-based criteria to those answers to identify whether a simple test is feasible, whether a quasi-experimental approach may be required, or whether the current design cannot support a credible causal conclusion.
The result never claims that causality has been established. It assesses whether a credible causal answer is possible, not what that answer is.
Results are rule-based guidance generated from self-reported answers. They are directional, not accounting, legal or other professional advice, and a professional review working from evidence may reach different conclusions.
Your answers are saved against the decision or intervention you name in your Studio workspace, so the checklist can be updated before launch and again after data collection. Nothing you enter appears outside your workspace, and your analysis plan and decision context stay available to you if you later bring the question to professional work.
Usage is measured at a category level (intervention type, readiness verdict and principal validity threat) to improve the checklist and to route relevant recommendations inside Studio.
In Studio the checklist lives under Tools → Evidence & Experimentation, and is recommended whenever you create an experiment, pilot, pricing-change, campaign-test or product-intervention workspace. Each run is saved against a named decision or intervention, so the readiness record and the decision it serves stay together.
Missing requirements convert into an experiment-preparation checklist you can work through before launch. The checklist can be updated before the test starts and again after data collection, and the analysis plan and decision context are preserved, so if the question later needs an econometrician, the groundwork is already documented.
When the result points at a constraint that needs professional depth, these engagements pick it up.
Registration is free, no card required, and your results save to your workspace so the working stays in one place.