Prompting AI to Write Regular Expressions (Regex)

Regex is the single best AI use case in development: tedious to write, error-prone to read, and easy to test with examples. The trick is to brief the AI with the right kind of examples so its regex actually matches what you mean — and rejects what you don't.

1. Introduction

Writing a regular expression by hand is rarely about cleverness — it's about not forgetting an edge case. AI is excellent at this exact kind of task, provided you steer it with examples instead of descriptions. This tutorial walks through the example-first prompt pattern and shows you how to test the resulting regex before it ever touches production data.

2. The Concept Explained

A regex has four parts you have to nail down: flavour (PCRE, JavaScript, Python re, POSIX), anchors (whole-string match vs find-in-text), character classes (ASCII vs Unicode), and flags (case sensitivity, dotall, multiline). Most regex bugs trace back to one of these being wrong by accident.

Think of regex prompts as test-driven specification: give the examples first, then describe the rule. The AI is then writing to a contract you can verify.

3. The Problem Without This Technique

The instinctive prompt is "regex for email" or "regex for phone number". The AI returns a one-liner that is either too strict (rejects valid input) or too loose (accepts garbage).

give me a regex to match indian phone numbers

4. The Solution

Write a regular expression for the JavaScript regex flavour (RegExp).

What it should match:
- Indian mobile numbers as they appear in user-submitted forms.
- Match the WHOLE input string (anchor both ends).
- Case-insensitive flag not needed.

SHOULD MATCH (positive examples):
  9876543210
  +919876543210
  +91 98765 43210
  +91-98765-43210
  09876543210

MUST NOT MATCH (negative examples):
  98765                    (too short)
  98765432101              (too long)
  +9298765432              (wrong country code)
  abc9876543210            (non-digit prefix)
  +91 1234567890           (mobile must start with 6, 7, 8, or 9 after country code)
  +91 (98765) 43210        (we don't accept parentheses)

Rules:
- Only digits (0–9), single optional '+91' or '91' prefix, optional spaces
  or single hyphens as separators, mobile number is exactly 10 digits and
  starts with 6, 7, 8, or 9.
- A leading '0' is allowed in place of '+91'.

Output:
1. The regex as a single JavaScript literal: /…/u
2. A 1-line description of what it does.
3. A table of all the example inputs above and whether your regex matches
   each, so I can verify before using it.

5. Step-by-Step Breakdown

1. Name the regex flavour. JavaScript, Python re, PCRE, POSIX, .NET. Each has different syntax for lookaheads, named groups, and Unicode.
2. State the anchoring. Whole string match (^…$) vs find-substring. Without this, the AI defaults to "find" and accepts inputs with garbage prefixes.
3. Provide positive examples. Five to ten that cover the realistic variations users will send.
4. Provide negative examples. Critical: equally important as positives. They prevent over-matching.
5. Write the rule in plain English. Even with examples, an explicit rule helps. Examples teach the AI the pattern; the rule confirms the intent.
6. Demand a verification table. The AI matches every example against its own regex and reports the result. This is your test suite, generated for free.

Tip: When the AI's regex fails on a new edge case, don't ask it to "fix" the regex from scratch — paste the new failing example into the same chat and ask it to update the regex while keeping all previous examples correct. This iterative tightening is much more reliable than rewrites.

6. Practice Exercises

Generate 10 inputs this regex should match and 10 it should reject. Then test the regex against each and show me the result.

7. Key Takeaways