3 Developer Skills to Strengthen as AI Transforms Software Work

Share

Learn to direct AI agents, critically review their output, and keep technical judgment at the center of your workflow.

Decorative header image with a Copilot logo and the phrase 'Branching Out_'



Gwen Davis@purpledragon85

|
3 minutes


  • Share:

AI is reshaping how developers work and apply their skills. Writing code still matters, but the job increasingly involves directing AI, evaluating its output, communicating tradeoffs, and making sound technical calls.

The good news: you can start preparing today. Here’s where to focus.

Tip #1: Learn to direct AI, not just use it

Execution itself is shifting. More and more, strong execution means framing the problem clearly, supplying the right context, judging AI-generated code, and deciding what is ready to ship. As AI agents handle more of the implementation, those skills carry more weight—not less.

Say you’re asked to add a new authentication flow.

A traditional workflow might look like this:

Task: Add authentication  

→ Create branch  
→ Write code  
→ Run tests  
→ Open pull request

As AI tools grow more capable and more embedded in daily workflows, the same skills help you coordinate multiple agents at once. Your workflow might look more like this:

Workspace: Add authentication  

Agent 1 ✓ Authentication ready for review 
Agent 2 ✓ Documentation draft ready  
Agent 3 ✓ Test suite ready

Notice what changed. You’re still accountable for the outcome, but you spend less time implementing every piece yourself. Instead, you define the work, review the outputs, and make the technical decisions that pull everything together.

Takeaway: Learn to direct AI agents.

Start your first agent session >

Tip #2: Don’t trust AI’s first answer

AI can produce impressive solutions in seconds, but the first answer isn’t always the best one. Your experience writing clean, maintainable code is what lets you judge what the model returns.

One practical approach: ask a second AI model to critique the first model’s work, then use your own judgment to weigh both responses.

Here’s a prompt that shows what that looks like in practice:

"Write a SQL query that returns each customer's most recent order." 
↓ 
AI Model #1 
✓ Generates the query 
↓ 
AI Model #2 (Critique) 
⚠ Doesn't handle duplicate timestamps 
⚠ Missing index recommendation 
⚠ May perform poorly on large tables

Different AI models have different strengths and blind spots. That’s why GitHub Copilot’s built-in Rubber Duck agent uses a second model to critique plans, code, and tests before you move forward. A second perspective often catches issues the first model misses.

Takeaway: Trust AI enough to use it, but not enough to skip review.

Tip #3: Use AI to solve bigger problems

When AI cuts down implementation time, you can reinvest that time in broader work: understanding customer needs, weighing tradeoffs, designing better systems, and making the technical decisions AI can’t make for you.

For example:

Issue #4821 
Title: Add dark mode 

AI 

✓ Build implementation 
✓ Generate tests 
✓ Update documentation 

Developer checklist 

☐ Validate customer problem 
☐ Review architectural tradeoffs 
☐ Check accessibility 
☐ Define success metrics 
☐ Approve solution 

As AI absorbs more implementation work, the skills that set great engineers apart matter more: sound judgment, balancing tradeoffs, and solving the right problems.

Takeaway: Let AI handle more of the implementation so you can spend more time building the judgment that helps teams make better decisions.

The bottom line

As developer workflows evolve, learning to work effectively with AI—and sharpening your own technical judgment—can help you adapt.

Put these ideas in practice >


Tags:

Written by

Gwen Davis

Gwen Davis

@purpledragon85

Gwen Davis is a senior content strategist at GitHub, where she writes about developer experience, AI-powered workflows, and career growth in tech.

Related posts

Read more