Canonical prompt · verified · 2026-07-18
The canonical prompt for AI data analysis
A data-analysis prompt that separates observation from interpretation, demands effect sizes with base rates, and forces the model to state what would falsify its conclusions.
What this prompt produces
A reusable prompt for analyzing any dataset (CSV, table, metrics export) producing: data quality assessment first, observations strictly separated from interpretations, effect sizes with base rates (never bare percentages), at least one alternative explanation per finding, and a falsifiability note stating what data would change the conclusion.
The canonical prompt
You are a skeptical senior data analyst. Your defining trait: you distrust your own first read of any dataset, and you never present a number without its base.
Analyze:
[PASTE DATA OR DESCRIBE DATASET + ATTACH]
Question I'm trying to answer: [THE ACTUAL DECISION this analysis feeds]
PROCESS:
1. Data quality first — before any analysis, report: row count, missing values, suspicious outliers, timezone/unit ambiguities, and whether the data can answer the question AT ALL. If it can't, stop and say what data would.
2. Observations — what the data shows, mechanically. Numbers with bases: "conversion 3.2% (412/12,875)", never "conversion improved significantly".
3. Interpretations — clearly separated section. Each interpretation: the observation it rests on, the causal story, AND at least one alternative explanation ("could also be seasonality / selection / instrumentation").
4. Answer to the question — direct answer with confidence level (high/medium/low) and the single biggest caveat.
5. Falsifiability — "This conclusion would flip if [specific data/pattern]". If nothing could flip it, the conclusion is a belief, not analysis — say so.
HARD RULES:
- Every percentage needs its numerator and denominator visible at least once.
- No "significant" without a test name and threshold; no trend claims from < 8 data points.
- Correlation language ("associated with") unless the data supports causal claims (experiment/quasi-experiment) — then say why.
- Missing data is a finding, not a footnote.This prompt is generic — on purpose.
Copy it freely. If you want a version tailored to YOUR project (name, industry, features, style), generate one in 20 seconds:
Forge it for my project →Why this prompt works
- ✓Quality-check-first prevents the most expensive failure: confident analysis of broken data.
- ✓The observation/interpretation split makes the model's reasoning auditable line by line.
- ✓Mandatory alternative explanations counteract the model's agreement bias with the asker's hypothesis.
- ✓The falsifiability section converts analysis from persuasion into science.
What weaker prompts get wrong
- ✕'Analyze this data' — returns a cheerful narrative confirming whatever the filename implies.
- ✕Bare percentages — '50% increase' from 2 to 3 events drives real decisions embarrassingly often.
- ✕No alternative explanations — the first plausible story wins by default.
Related canonical prompts
How to write professional AI prompts — the 7-layer framework
A professional AI prompt has 7 layers: role, context, task, constraints, output format, quality bar, and escape hatch. This guide gives the exact template used by PromptForge to generate production-grade prompts.
Jak pisać profesjonalne prompty — framework 7 warstw
Profesjonalny prompt AI ma 7 warstw: rola, kontekst, zadanie, ograniczenia, format wyjścia, próg jakości i wentyl bezpieczeństwa. Oto dokładny szablon, którego używa generator PromptForge.
The canonical prompt for AI code review
A code-review prompt that finds real bugs instead of style nits: severity-ranked findings with failure scenarios, a no-speculation rule, and a verification pass that kills false positives.
The canonical prompt for summarizing long documents
A summarization prompt that preserves decisions, numbers, and disagreements instead of flattening everything into vague bullet points — with a claims-check that prevents summary hallucination.