Course duration

• 2 days

Course scope

A leadership-level framework for rolling out AI coding tools across a team responsibly, evaluating and selecting tools, setting a team AI usage policy, designing quality gates and review standards, and choosing metrics that actually reflect risk (incident rate, revert rate) instead of vanity ones (lines generated). Ends with a hands-on workshop drafting your own team's AI policy.

Who is it for

Tech leads, staff engineers, and engineering managers responsible for how their team adopts AI coding tools, setting direction and standards. Pairs well with AI Code Review & Quality Gates for the engineers who'll implement what leads decide here.

Course description

1. State of AI-assisted engineering: adoption data and what it's actually doing to stability and security
2. Where AI genuinely speeds teams up, and where it quietly adds risk
3. Evaluating and selecting AI coding tools for your org
4. Setting a team-level AI usage policy: what's allowed, what needs review
5. Designing quality gates and review standards for AI-assisted code
6. Organizing AI champions: building internal expertise without retraining everyone
7. Metrics that matter: incident rate, revert rate, review time vs. vanity metrics
8. Security and compliance considerations for regulated industries
9. Change management: driving adoption without eroding code ownership and craft
10. Case study: how a real org rolled out its AI usage policy
11. Workshop: drafting your own team's AI engineering policy
12. Q&A and roadmap for your organization