RCA Diagnostician
Conduct or evaluate a root cause analysis using cross-disciplinary principles. Moves from symptom to systemic cause, selects appropriate methods, applies cognitive bias countermeasures, and produces corrective actions ranked by strength.
Setup
- If an incident description or RCA report is provided, read it completely.
- If no input is provided, ask what incident or failure to investigate.
- Determine the mode: INVESTIGATE (new RCA) or EVALUATE (review existing report).
Procedure
- Scope the problem. Define WHAT/WHERE/WHEN/SEVERITY and the counterfactual. Use
references/problem-definition.md.
- Collect and map evidence. Inventory sources, assess sufficiency (3-stream minimum), reconstruct the timeline. Use
references/evidence-timeline.md.
- Generate and test hypotheses. Produce candidates at mechanism, process, and organizational levels. Select the appropriate RCA method for the domain. Use
references/hypothesis-methods.md.
- Apply bias countermeasures. Check for confirmation bias, blame displacement, correlation-causation overreach, and early closure. Use
references/bias-countermeasures.md.
- Define corrective actions. Rank by strength (strong/intermediate/weak). Require at least one strong action. Define verification metrics. Use
references/action-hierarchy.md.
- Evaluate rigor. Apply the minimum viable rigor checklist. If AI tools were used, apply the AI governance checklist. Use
references/rigor-checklist.md.
- Produce the final report. Use
references/report-template.md.
For EVALUATE mode: read the existing report, extract the problem definition (step 1), then skip to step 6 (rigor evaluation), then produce the report. If the existing report is too thin for meaningful evaluation (fewer than 3 of 9 rigor criteria can be assessed), recommend switching to INVESTIGATE mode instead.
Rules
- Never promote correlation to causation without a causal model or explicit uncertainty.
- Never accept a single-cause narrative without testing alternatives.
- Never recommend only weak actions (retraining, reminders) when the system predictably creates the error.
- Every action must have a verification metric and monitoring period.
- Reference exact evidence from the input. Do not fabricate findings.
- This diagnostic is advisory — do not implement fixes during this session.
1---2name: rca-diagnostician3description: RCA Diagnostician4---5# RCA Diagnostician67Conduct or evaluate a root cause analysis using cross-disciplinary principles. Moves from symptom to systemic cause, selects appropriate methods, applies cognitive bias countermeasures, and produces corrective actions ranked by strength.89## Setup1011- If an incident description or RCA report is provided, read it completely.12- If no input is provided, ask what incident or failure to investigate.13- Determine the mode: INVESTIGATE (new RCA) or EVALUATE (review existing report).1415## Procedure16171. **Scope the problem.** Define WHAT/WHERE/WHEN/SEVERITY and the counterfactual. Use `references/problem-definition.md`.182. **Collect and map evidence.** Inventory sources, assess sufficiency (3-stream minimum), reconstruct the timeline. Use `references/evidence-timeline.md`.193. **Generate and test hypotheses.** Produce candidates at mechanism, process, and organizational levels. Select the appropriate RCA method for the domain. Use `references/hypothesis-methods.md`.204. **Apply bias countermeasures.** Check for confirmation bias, blame displacement, correlation-causation overreach, and early closure. Use `references/bias-countermeasures.md`.215. **Define corrective actions.** Rank by strength (strong/intermediate/weak). Require at least one strong action. Define verification metrics. Use `references/action-hierarchy.md`.226. **Evaluate rigor.** Apply the minimum viable rigor checklist. If AI tools were used, apply the AI governance checklist. Use `references/rigor-checklist.md`.237. **Produce the final report.** Use `references/report-template.md`.2425For EVALUATE mode: read the existing report, extract the problem definition (step 1), then skip to step 6 (rigor evaluation), then produce the report. If the existing report is too thin for meaningful evaluation (fewer than 3 of 9 rigor criteria can be assessed), recommend switching to INVESTIGATE mode instead.2627## Rules2829- Never promote correlation to causation without a causal model or explicit uncertainty.30- Never accept a single-cause narrative without testing alternatives.31- Never recommend only weak actions (retraining, reminders) when the system predictably creates the error.32- Every action must have a verification metric and monitoring period.33- Reference exact evidence from the input. Do not fabricate findings.34- This diagnostic is advisory — do not implement fixes during this session.
charly-vibes