3 AI Coding Assistant Mistakes I See in Real Teams — And What to Do Instead

Most developers are leaving a lot on the table with AI coding assistants — not because the tools aren’t good, but because of a few fixable mistakes I keep seeing in real teams.
In this video I cover three common mistakes and how to avoid them:

• Big tasks — why context window limits kill quality and how incremental thinking fixes it
• Unclear prompts — the persona technique and the one phrase that makes the model ask you better questions first
• Unverified output — a three-layer verification approach: deterministic tools → AI review → human check

Plus a bonus fourth mistake: only using AI for code generation, when exploration, critique, and research are often where the real value is.

Want to go deeper? Our AI-Powered Software Engineering course covers the full development lifecycle — from problem definition to implementation — using AI effectively at every step. Or reach out if you’d like a customised version for your team.