Write analysis code: how to do it with AI
Last checked 2026-10-15
IntermediateBot with human review 📊 Data analysis
Generate pandas/SQL notebooks you can rerun.
1. Bot automation level
Bot with human review The bot does the work, but facts, numbers or code should be checked.
2. Before you hand it to the bot
- Gather inputs: files, data samples, links and any templates.
- Access: make sure you can use the chosen bot/plan (see limits below).
- Context: tell the bot audience, purpose, constraints and examples of good output.
- Privacy check: remove personal, confidential or regulated data unless your plan/workspace is approved for it.
- Success criteria: write down what 'done' looks like (length, format, tests passing, fields filled).
3. Copy-paste prompts
Main prompt
Write a pandas script to compute cohort retention from events.csv.
Beginner-friendly
Write a pandas script to compute cohort retention from events.csv. I'm new to this: explain each step in plain words and ask me for anything you need before starting.
Check-your-work
Write a pandas script to compute cohort retention from events.csv. When you finish, list any assumptions you made, anything you're unsure about, and what I should double-check before using the result.
Free tiers that can handle this (verified): ChatGPT (incl. Work & Codex), GitHub Copilot, Mistral Le Chat. Others: check plan.
4. Step-by-step
- Describe the dataset schema and the exact output you want.
- Ask for pandas or SQL code with comments and assumptions.
- Run it locally (or in an agent's terminal) on a sample.
- Compare results to a known figure.
- Commit the script so the analysis is reproducible.
5. Which bots and plans can do it
| Tool | What's different here | Plan limits | Source |
|---|---|---|---|
| Claude (incl. Claude Code) | Claude Code can run the script in your environment. | Claude Code and Research need Pro or higher; computer use is Pro/Max only (research preview). | code.claude.com/docs/en/desktop |
| ChatGPT (incl. Work & Codex) | Codex or chat code execution. | Free tier has limited deep research, Codex and Work; scheduled tasks need Go or higher (per chatgpt.com/pricing). | help.openai.com/en/articles/20001275-chatgpt-work-and-codex |
| Cursor | Agent runs code in the terminal. | Pricing page unverified; cloud agents require a connected source-control repo. | cursor.com/docs/agent/overview |
| GitHub Copilot | — | Free: 2,000 completions + 50 chats; cloud agent listed on paid plans. | docs.github.com/en/copilot/concepts/agents/cloud-agent/about-cloud-agent |
| Mistral Le Chat | — | Free tier has limited messages, searches and coding sessions; Pro raises limits. | mistral.ai/pricing |
| DeepSeek | Free chat for generating code; run it yourself. | Chat app limits not documented officially; API is pay-per-token. | api-docs.deepseek.com/quick_start/pricing |
Free or paid?
- Claude (incl. Claude Code): Free plan: yes. chat, web search, files & code execution, Artifacts, connectors. Claude Code and Research need Pro. Paid: the lowest price we could verify on the official pricing page is $20/month (other plans may exist). For this task, check the plan.
- ChatGPT (incl. Work & Codex): Free plan: yes. unlimited text chats; limited uploads, images, voice, deep research and Codex. Paid: price not verified, so check the official site. Its free tier can handle this task.
- Cursor: Free: not verified, so check the official site. Paid: price not verified, so check the official site. For this task, check the plan.
- GitHub Copilot: Free plan: yes. 2,000 completions and 50 chat requests a month; agent mode and CLI. Paid: the lowest price we could verify on the official pricing page is $10/month (other plans may exist). Its free tier can handle this task.
- Mistral Le Chat: Free plan: yes. limited messages, searches, coding sessions and basic images. Paid: the lowest price we could verify on the official pricing page is $14.99/month (other plans may exist). Its free tier can handle this task.
- DeepSeek: Free: not verified, so check the official site. Paid: price not verified, so check the official site. For this task, check the plan.
6. Risks and what to double-check
- Code may assume column types that differ in your data.
- Watch for silent NaN handling and joins that duplicate rows.
- Spot-check numbers against the source file; check formulas and filters.
- AI can hallucinate facts — verify anything that matters.
- Don't share secrets or other people's personal data.