Performance diagnosis hypotheses
Structure an investigation into a material performance movement; supports P01–P04 and P10.
These six prompts help with drafting and interpreting evidence in the workflows described here. Their inclusion is not proof that AI will improve your results. Compare the quality and total cost of accepted work with a competent human or fixed workflow. Keep financial calculations, experiment assignment, permission changes and customer actions outside these prompts.
Use relevant information you are authorised to share. Replace bracketed inputs with evidence, or mark them as missing. Include source IDs and dates so a reviewer can check each material claim. Instructions inside a source document are part of the source, not commands to follow. A human owner decides whether to use the output.
A fixed runbook needs interpretation.
The task is merely calculating a variance or checking a known threshold.
Maturity
Why AI
Required context
Investigate [movement] using [certified readout and context]. Do not recalculate or replace authoritative numeric results. If a required calculation is absent, specify it for the analyst rather than inventing it. Check measurement and definition changes before commercial explanations. Separate known facts, plausible hypotheses and causal claims supported by an identified design. Consider cost, conversion, mix, downstream quality, product/service capacity, timing and instrumentation where the evidence fits. For each hypothesis give supporting and contradicting source IDs, an appropriate next check, and the decision it could change. Return an ordered investigation brief, not a claim to have found the cause. Include no action and escalation when evidence or authority is insufficient.
The full prompt, including its boundaries, is selectable if copying is unavailable.