Analysis plans, insight reports, and data storytelling — AI-accelerated
Data Science & Analytics Framework encodes senior data scientist, analytics engineer, and data storytelling expertise into prompt sequences that generate complete analytics workflows. From analysis plans to executive dashboard specs, every prompt produces data artifacts that turn raw data into decisions.
Full Access Unlocked
All 46 prompts · All 4 modules
"The analysis plan prompts force the right structure before touching any data. My stakeholders now ge..."
Priya S. · Senior Data Scientist
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.
4 modules · 46 prompts · 6 workflow stages
Analysis Planning System
Business question to analysis plan, metric definition framework (north star, guardrails, diagnostics), and data availability assessment.
9 promptsSQL & Query Framework
Exploratory analysis queries, aggregation and segmentation patterns, cohort analysis framework, funnel analysis system, and query documentation prompts.
10 promptsInsight & Narrative System
Insight generation prompts (pattern → hypothesis → implication), insight narrative framework (finding, evidence, so what, now what), and anomaly investigation guide.
10 promptsDashboard & Experimentation System
Dashboard specification (metrics, dimensions, filters, layout), A/B test design (hypothesis, sample size, duration, analysis plan), and experiment results interpretation.
17 promptsBuild an analysis plan for the following business question: Company: [DESCRIBE]. Business question: [E.g., "Why did our 30-day retention drop 8% last quarter?"]. Available data: [DESCRIBE — tables, time range, granularity]. Create: (1) Restate the question as a precise analytical question (what exactly are we measuring?), (2) Hypotheses (3-5 hypotheses that could explain the pattern), (3) Analysis approach (for each hypothesis: what data to look at, what query/analysis to run, what result would confirm or reject it), (4) Key metrics and dimensions to examine, (5) Potential confounders to control for, (6) Expected output (what the deliverable looks like). Prioritize hypotheses by likelihood and ease of testing.
Design an A/B test for the following experiment: Company: [DESCRIBE]. What we're testing: [DESCRIBE THE CHANGE]. Hypothesis: We believe [CHANGE] will [IMPROVE METRIC] because [REASON]. Primary metric: [METRIC]. Secondary metrics: [LIST]. Guardrail metrics: [METRICS THAT MUST NOT DEGRADE]. Create: (1) Null and alternative hypothesis (formal statistical statement), (2) Sample size calculation (assume [BASELINE CONVERSION], [MINIMUM DETECTABLE EFFECT], 80% power, 95% confidence — show the math), (3) Test duration (based on traffic volume: [DAILY USERS]), (4) Randomization unit (user, session, device — and why), (5) Analysis plan (how to analyze results, including segment breakdowns), (6) Decision criteria (what result leads to ship / no-ship / iterate). Flag any threats to validity.
Write an insight narrative for the following analysis finding: Context: [COMPANY, PRODUCT, TIME PERIOD]. Finding: [DESCRIBE WHAT THE DATA SHOWS — be specific with numbers]. Structure the narrative as: (1) The finding (1 sentence — the most important thing the data shows, with the number), (2) The evidence (2-3 sentences — what data supports this, including any segmentation or cohort breakdown), (3) The "so what" (why this matters for the business — connect to a goal or metric that leadership cares about), (4) Hypotheses (2-3 possible explanations for why this is happening), (5) Recommended next steps (what analysis to do next, or what action to take). Write for a non-technical executive audience. No statistical jargon without plain-language explanation.
system
9 prompts
prompts
10 prompts
workflow
10 prompts
architecture
17 prompts
"The analysis plan prompts force the right structure before touching any data. My stakeholders now get clearer questions and faster answers."
Priya S.
Senior Data Scientist
"The A/B test design framework is the most rigorous I've seen in a prompt library. The validity threats section alone has saved us from bad decisions twice."
Tom L.
Analytics Engineer
All 46 prompts across 4 modules are unlocked for your account.
Lifetime access