Turn a plain-English question into SQL
A working query with an explanation, so you can check it, not just run it.
What most people type
Short prompts like this get generic answers, because the AI has to guess who you are and what you need.
A better prompt
Fill in the blanks
Swap each highlighted part for your own details. Here’s an example.
- [YOUR DATABASE OR TOOL]
PostgreSQL - [THE TABLES AND COLUMNS]
orders(order_id, order_date, region, amount, status) - [YOUR QUESTION]
monthly revenue by region for the last 6 months, completed orders only
What a good answer looks like
This is a sample answer for the example above. Yours will be different, so check it against your own facts.
Make it even better
Paste a few rows of fake sample data and the expected result so it can test its own query.
Stay safe
Learn the skill behind it
This prompt comes from the course AI for data analysts. The next lesson to watch is “Write formulas and SQL from plain English”.
Try this in Tau
In Tau, you can fill in the blanks, run the prompt and get feedback, then watch the one-minute lesson that explains why it works. Join the waitlist for early access.
We’ll only email you about Tau, and you can unsubscribe any time. Privacy policy.
We’ll email you as soon as Tau opens.
More prompts like this
Turn a messy client email into an issues list
Walk into the first call with the issues mapped and the right questions ready.
Go from error message to fix, fast
Ranked likely causes and a quick test for each, instead of guess-and-check.
Draft a method statement from your site notes
A structured first draft in minutes, so your time goes on the engineering checks.
Prepare a one-page brief for a client meeting
Walk in with the client's likely needs and sharp questions, in 5 minutes.