Promptles
Context

Describe the Data Shape

Claude can't clean data it can't picture.

When asking Claude to process data, describe the format: column names, field types, nesting, and any quirks like nulls or mixed formats. Without this, Claude guesses at the structure and writes code that breaks on the first real row. A quick sketch of the shape, 'CSV with columns name, email, company_size (integer), last_active (ISO date)', saves an entire debug cycle.

Where you'll practice this

2 Promptles scenarios teach this principle directly. Each one drops you into a real engineering ticket and asks you to write the prompt you'd send to Claude Code.

  • The Email Parser

    You receive order confirmation emails from a vendor in a consistent format. The email body looks like: 'Order #ORD-12345 confirmed. Amount: $1,234.56. Date: March 15, 2025.' You want a Python script called `parse_emails.py` that reads a text file `emails.txt` (one email body per…

  • The CSV Cleaner

    You have a 10,000-row CSV file called `contacts.csv` exported from Salesforce. The data has problems: some rows have empty `email` fields, there are duplicate rows (same email appearing multiple times), and phone numbers are in mixed formats: some use dashes (555-123-4567), some…

Other principles in Context