Weekly Business Review from a Spreadsheet Using Data Analysis

Upload a CSV or XLSX and get a metrics review with variance explanations, data-quality flags, and a decision list for the week. Written for ChatGPT's Advanced Data Analysis.

You get: Headline, data quality notes and metrics table

More like this

The prompt

weekly-business-review-from-a-spreadsheet-using-data-analysis.md
Role: You are a business analyst preparing a weekly review for {audience}.Context: I am uploading a spreadsheet covering {time_period} for {business_area}. The decision this review should support is: {decision_to_make}.
Task: Analyze the file and produce a concise weekly business review with evidence, caveats, and recommended actions.Constraints: Use only the uploaded data and the context I provide. Do not guess causes as facts; label them as hypotheses. Show calculations for every headline number. Do not hide data problems.

Inputs:
- Uploaded file and sheet names: {file_description}
- Key metrics and definitions: {metric_definitions}
- Targets or prior-period baseline: {targets}
- Known events (campaigns, outages, holidays): {known_events}
- Audience and decision deadline: {audience}

Workflow:
1. Use the data analysis tool to inspect columns, row counts, date ranges, nulls, duplicates, and outliers. Report these before analysis.
2. List assumptions, such as how you interpreted ambiguous columns.
3. Compute each metric for the current period vs the baseline: absolute change, percent change, and rank of contributing segments.
4. Create up to 3 charts that directly support the decision. Label axes and units.
5. Separate observed facts from hypotheses. For each hypothesis, name the data that would confirm it.
6. Recommend actions with owner type, effort (S/M/L), and expected signal.

Output format:
- Headline (2 sentences)
- Data quality notes (table: issue, impact, suggested fix)
- Metrics table (metric, current, baseline, change, status)
- Drivers of change (facts vs hypotheses)
- Charts
- Risks and missing information
- Decisions for this week and next actions (table)

Acceptance criteria:
- Every number can be traced to a calculation or column.
- The review answers {decision_to_make} directly or says what data is missing.
- Data issues are listed before conclusions.

Quality checks:
- Recompute two headline numbers independently and show the check.
- Confirm that percent changes use the correct denominator.
- Flag any conclusion that relies on fewer than 30 rows or one outlier.

Example output

AI-written example

Weekly Business Review: DTC Store, Mar 10–16, 2025 vs Mar 3–9
Audience: VP Ecommerce, Marketing Director. Decision due Tuesday: extend the spring email promo budget one more week?

Headline
Revenue rose 13.7% ($162,300 → $184,600), but 6.0 percentage points of that comes from one $6,840 order; excluding it, growth is 9.5%. Spend rose faster (+29.8%) than revenue, so blended ROAS fell below the 6.0 target. I recommend a capped extension, not a full one.

Data quality notes

IssueImpactSuggested fix
14 duplicate order IDs (0.6% of rows)Removed; revenue would be overstated by $1,120Dedupe at export
212 orders with blank channel (9.2% = 212/2,310)Channel split is understatedRequire UTM capture at checkout
One $6,840 order (next largest: $610)Inflates growth by 4.2 ptsConfirm whether it is wholesale

Metrics

MetricCurrentBaselineChangeStatus
Revenue$184,600$162,300+$22,300 (+13.7%)On target ($175k)
Orders2,3102,045+265 (+13.0%)OK
AOV$79.91$79.36+$0.55 (+0.7%)Flat
Sessions71,40064,900+6,500 (+
Generated from this prompt by AI. Your results will vary.

Tips and common edits

Remove personal or sensitive customer data before uploading. If the file has several sheets, name the important one in the file description. Ask a follow-up for a slide-ready summary once the analysis is accepted.

Questions about this prompt

More in ChatGPT

Architecture Decision Record for a Technology Choice

Compares realistic options against your constraints and produces a decision record. The record has a weighted comparison, risks, a reversal plan, and a recommendation the team can approve or challenge.

Audience Research Source Discovery and Evidence Synthesis for Segment Prioritization

Guides you to plan source discovery, review the evidence you collect, build a citation table, and synthesize findings into a segment prioritization decision, without pretending the model browsed the web.

Competitor and Audience Evidence Review with Citation Table and Go/No-Go Brief

A research workflow that plans online source discovery, scores evidence, builds a citation table, and ends with a decision brief, without pretending live browsing happened.

Competitor Landscape Evidence Table with Source Tiers and Gaps

Builds a citation-backed competitor comparison for a specific market decision. It starts with source-discovery queries, tiers sources by reliability, and separates evidence from inference and open questions.

Competitor Landscape Research Plan with Source Discovery and Citation Table

Builds a source discovery plan, evidence review, citation table, and decision-ready synthesis for a competitor or market question, without pretending live browsing occurred.

Competitor Landscape Scan with Source-Backed Citation Table

Runs a structured competitor scan that starts with search queries, ranks sources by reliability, and ends with a cited comparison table and a positioning recommendation.

Competitor Research Plan with Source Discovery and Citation Table

Build a research plan that shows where to find competitor evidence, how to judge sources, and how to log citations. It never claims live browsing happened, so you can verify each source yourself.

Competitor UX Pattern Research Plan with Evidence Table and Design Recommendation

Builds a source discovery plan, evidence log, citation table, and synthesis for comparing UX patterns across competitors, without claiming live browsing.

Evidence Review Plan for a Classroom Teaching Strategy Decision

Guides source discovery, evidence review, a citation table, synthesis, and a recommendation on whether to adopt a teaching strategy. It does not claim live browsing and marks every unverified item for you to check.

Productivity Tool Selection: Source Discovery, Evidence Review, and Citation Table

A research workflow to choose between candidate productivity or automation tools. It plans online source discovery, structures evidence review in a citation table, and ends in a decision memo without claiming live browsing took place.

SQL Query from Schema and Question

Writes a SQL query that answers your question from your schema, explains each clause and suggests indexes worth adding.

Two-to-Three Model Comparison Test Plan with 10 Prompts and Scoring Rubric

Creates a side-by-side test plan for choosing an AI model for your use case, with 10 test prompts, a scoring rubric and a blank results table.