Day 1 — Foundations & Core Practices
- The shift to AI-native development: from autocomplete to agents, and why real codebases break the illusion
- How AI changes the SDLC: lifecycle impact and the role of context as the main constraint
- Developer mindset: from writing code to guiding, constraining, and validating outcomes
- Constraint engineering: structuring tasks, limiting scope, and designing predictable agent behavior
- Making codebases AI-ready: improving structure, documentation, and explicit conventions for better AI understanding
- Labs of the day cover: preparing a codebase and running controlled AI-assisted tasks

Day 2 — Advanced Execution & Scaling
- Context engineering: managing context, instruction hierarchy, and effective use of memory and retrieval
- Multi-agent workflows: task decomposition, specialization, and human orchestration
- Execution patterns: iterative delivery, checkpoints, and validation loops
- Failure modes: hidden errors, over-reliance, and context-related breakdowns
- End-to-end workflow: from idea to delivery using AI-assisted development
- Scaling in teams: workflow changes, collaboration patterns, and meaningful metrics
- Labs of the day cover: designing and executing a multi-step AI-assisted workflow