From raw data to actionable insights — AI-accelerated analytics
Data Analytics Framework encodes senior data analyst and analytics engineer patterns into prompt sequences that generate production-quality SQL, Python analysis code, and business intelligence artifacts. From data model design to executive reporting, every prompt produces analytics work that drives decisions.
Full Access Unlocked
All 44 prompts · All 5 modules
"The dimensional modeling prompts produce schemas that our BI team can actually use. No more "what do..."
Nadia C. · Analytics Engineer
Need expert implementation?
Hire an OrchestratorConnect with a certified Prompt.Doctor Orchestrator to deploy this framework for you.
No coding required. You will use ChatGPT or Claude as your AI tool. Follow these steps in order — do not skip ahead.
Purchase & download the framework
Click the buy button on this page. After checkout, go to the and hit Download .zip. Unzip it — you'll get a .md file (the full framework) and a .pdf (easy to read reference). Keep both open.
Open your project — new or existing
This dashboard is designed to integrate into any existing project or be built as a standalone app. If you already have a site in Airo (or Cursor, Bolt, etc.), open that project. If you're starting fresh, create a new project. The Orchestrator Prompt handles both cases — it scans what's already there and adds only what's missing.
Paste the Orchestrator Prompt into your builder's chat
Open the on this page. Copy the Orchestrator Prompt and paste it into your AI builder's chat. It will scaffold the full admin system — secure login, email marketing module, booking engine, and CMS — on top of your existing codebase. This takes 2–5 minutes.
Add your API keys as secrets
Critical — Novice UsersIn your builder, go to Settings → Secrets and add the keys your app needs. For this framework: STRIPE_SECRET_KEY (for booking payments — get it from your Stripe dashboard), ANTHROPIC_API_KEY (for AI-assisted content — get it from console.anthropic.com), and DATABASE_URL (your MySQL connection string). No key is needed for the admin login, CMS, or email modules — those run on your existing infrastructure.
Don't have a MySQL server?
You can purchase a shared hosting plan with cPanel and MySQL at host.esgwon.dev. Once your account is set up, follow the step-by-step guide to create your database and connect it to your AI website builder.
How to set up cPanel MySQL & connect to your AI website →Need help with Stripe?
Get your STRIPE_SECRET_KEY and STRIPE_PUBLISHABLE_KEY from your Stripe dashboard. The guide covers test keys, webhook setup, and going live.
Need help with Anthropic?
Get your ANTHROPIC_API_KEY from console.anthropic.com. The guide covers model selection, cost management, and troubleshooting.
Prompting Airo after setup — always name the file
When asking Airo to add tables, columns, or features to the admin dashboard, always include src/server/lib/admin-db.ts in your prompt. Without it, Airo may target the wrong database. Example: "Add a bookings table in the admin database (src/server/lib/admin-db.ts) — do not touch any other database connection in this project."
Run the framework prompts inside your live app
Your app is now running in the builder's preview panel. Open the on this page, copy each prompt one at a time, and paste it into your builder's chat. Replace every [BRACKET] with your real data before sending. Work through the stages in order — each stage output feeds the next.
Test end-to-end, then publish or hand off to your client
Walk through the admin as a real user: log in, create a booking, send a test email campaign, update a CMS image, and run the Safe-to-Publish gate. Once everything passes, click Publish in your builder. Because this is a white-label dashboard, your client accesses it at /admin on their own domain — no Prompt.Doctor branding, no third-party login required.
5 modules · 44 prompts · 6 workflow stages
Data Model Design
Dimensional modeling prompts: fact and dimension table design, star schema, slowly changing dimensions, and dbt model architecture.
8 promptsSQL Query Library
Generate optimized SQL for common analytics patterns: cohort analysis, funnel analysis, retention, LTV calculation, and window function patterns.
10 promptsPython Analysis System
Pandas data manipulation, statistical testing (t-test, chi-square, ANOVA), A/B test analysis, and visualization with matplotlib/plotly.
9 promptsDashboard & Reporting
Dashboard specification prompts for Looker, Metabase, and Tableau. Executive summary generator that translates data into business language.
9 promptsData Quality System
Data validation rules, anomaly detection prompts, data lineage documentation, and dbt test generation.
8 promptsWrite a SQL query to calculate weekly cohort retention for [PRODUCT/APP]. Table: [TABLE NAME] with columns: [LIST COLUMNS]. Definition: A user is "retained" in week N if they performed [ACTION] at least once in that calendar week. Output: A cohort retention matrix showing cohort week (rows) × weeks since signup (columns) with retention % in each cell. Use CTEs for readability. Database: [PostgreSQL/BigQuery/Snowflake]. Add comments explaining each CTE.
Analyze the following A/B test results and provide a statistically rigorous recommendation. Test: [DESCRIBE TEST]. Control: [N] users, [METRIC] = [VALUE]. Treatment: [N] users, [METRIC] = [VALUE]. Provide: (1) Statistical significance (two-tailed t-test or chi-square as appropriate), (2) Confidence interval for the effect size, (3) Practical significance (is the effect size meaningful?), (4) Sample size adequacy check, (5) Potential confounders to investigate, (6) Clear recommendation with reasoning. Show your calculations.
Transform the following data analysis into an executive insights report for [AUDIENCE: CEO/Board/VP]. Data: [PASTE DATA OR SUMMARY]. Format: (1) One-sentence headline (the most important finding), (2) 3 key insights (each with: what happened, why it matters, what to do), (3) One risk or concern to watch, (4) Recommended next action. Rules: No jargon, no chart descriptions — insights only. Every statement must be actionable. Length: under 300 words.
system
8 prompts
prompts
10 prompts
workflow
9 prompts
architecture
9 prompts
templates
8 prompts
"The dimensional modeling prompts produce schemas that our BI team can actually use. No more "what does this column mean?" questions."
Nadia C.
Analytics Engineer
"The executive report generator is magic. I paste in analysis and get a board-ready summary in 2 minutes."
Kevin L.
Head of Data
All 44 prompts across 5 modules are unlocked for your account.
Lifetime access