AI hasn't replaced engineers — it's raised the bar. Practice on deliberately vague problems. Get scored on how well you think, not just what you ask.
Your Prompt
Before we design anything — what are the core requirements? Do users need custom aliases, expiry, or analytics? What's the expected read/write ratio and scale?
AI Response
Good start. Core requirement: shorten a URL and redirect reliably. Custom aliases and analytics are optional. Reads outweigh writes 100:1. Target: 100M URLs, peak ~10K req/s redirects...
The shift
For decades, the ability to write code was the scarce skill. Now AI can write the code. What it can't do is think clearly about the problem.
The new leverage point is upstream: defining constraints, surfacing tradeoffs, asking the right questions. In other words — prompting well.
Before AI
Write the implementation
Now
Define the requirements precisely
Before AI
Know every API
Now
Know what to ask for
Before AI
Debug line by line
Now
Narrow the problem space quickly
How it works
Every problem is deliberately under-specified — just like real engineering work. No hand-holding.
Ask clarifying questions, define constraints, explore tradeoffs. The AI mirrors the quality of your thinking.
Your prompts are evaluated — not the AI's answers. Better questions unlock better scores and deeper insights.