Clean messy data: how to do it with AI
Last checked 2026-10-15
IntermediateBot with human review 📊 Data analysis
Normalize names, dates and duplicates with code execution.
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
Clean this CSV: standardize dates, dedupe emails, report changes.
Beginner-friendly
Clean this CSV: standardize dates, dedupe emails, report changes. I'm new to this: explain each step in plain words and ask me for anything you need before starting.
Check-your-work
Clean this CSV: standardize dates, dedupe emails, report changes. 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). Others: check plan.
4. Step-by-step
- Back up the original file.
- Describe the cleaning rules: date format, casing, dedupe key, how to treat blanks.
- Ask the bot to run code and output a cleaned file plus a change log (rows changed/removed).
- Spot-check 20 random rows against the original.
- Save the cleaning code so you can rerun it next time.
5. Which bots and plans can do it
| Tool | What's different here | Plan limits | Source |
|---|---|---|---|
| ChatGPT (incl. Work & Codex) | Runs code over uploaded files. | 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 |
| Claude (incl. Claude Code) | Code execution creates and edits files. | Claude Code and Research need Pro or higher; computer use is Pro/Max only (research preview). | code.claude.com/docs/en/desktop |
| Google Gemini | Can generate and explain cleaning code. | Free tier includes Deep Research, Canvas, Gems; video generation needs AI Plus or higher. | gemini.google/overview/deep-research/ |
Free or paid?
- 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.
- 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.
- Google Gemini: Free plan: yes. Flash-Lite model, image generation, Deep Research, Live, Canvas, Gems. Video needs AI Plus or higher. Paid: the lowest price we could verify on the official pricing page is $99.99/month (other plans may exist). For this task, check the plan.
6. Risks and what to double-check
- Dedupe rules can drop legitimate records — review the removed rows.
- Keep the change log for audit.
- 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.