Early Career
At this stage, you're learning to work with AI tools—and learning not to lean on them. You use AI to explore codebases, draft code, and understand unfamiliar patterns. But the core skill you're building is the ability to read AI-generated output critically, even before you've fully internalized the patterns yourself.
Nobody feels fluent yet, and that's normal. The landscape is new for everyone. What matters most right now isn't mastering any particular tool—it's staying curious, asking questions, and building the habit of verifying what AI gives you rather than accepting it at face value.
What This Looks Like
You use AI tools to get unstuck, explore unfamiliar parts of the codebase, and generate first drafts of code. You're developing a workflow that involves AI naturally, but you're also starting to catch moments where the output looks right but isn't quite. You ask questions about AI suggestions the same way you'd ask questions about any code you didn't write. You're building the instinct to pause and verify rather than accept and move on.
The struggles at this stage are honest ones. You might accept output that compiles and passes tests without fully understanding what it does. You might miss subtle issues—cargo-culted patterns, hallucinated APIs, logic that works for the happy path but breaks at the edges. Before AI, the slowness of writing code by hand built understanding even when you weren't aware of it. That built-in learning isn't automatic anymore, which means you have to pursue it deliberately.
The Shift
The shift at this stage moves from "AI gives me the answer" to "AI gives me a starting point that I need to understand and evaluate." This doesn't mean you stop using AI—it means you start treating its output the way you'd treat code from a colleague who doesn't know your codebase. Helpful, but requiring your judgment before it's ready.
You're succeeding when you review AI-generated code before committing it, when you can explain why the code works and not just that it does, when you pursue understanding even when AI makes it tempting to skip ahead, and when you ask for help distinguishing good suggestions from plausible-but-wrong ones.
How to Grow
Ask yourself regularly: do I understand why this code works, or just that it works? Would I be able to explain this approach to someone else? Am I building real knowledge, or just getting things done faster? These questions keep you honest about whether AI is helping you learn or helping you avoid learning.
Build habits that protect your growth. Read AI-generated code line by line before using it. Try writing code yourself first, then compare with AI suggestions to see what you missed or what AI got wrong. When AI suggests something unfamiliar, look it up independently rather than taking it on faith. Use AI to explore a new part of the codebase, then verify what you learned by reading the actual code.
You'll know you're ready to move to the next stage when you catch errors in AI output before they reach review, when you can explain why AI suggestions work rather than just that they do, and when you use AI to learn faster without skipping the learning itself.
At this stage, curiosity matters more than command of any specific tool. The engineers who grow fastest are the ones who stay curious about what AI gets right, what it gets wrong, and why.