Context Engineering: Working with AI in Real-World Software
summary
Martí Cristóbal explains how to integrate AI into real software engineering by teaching “context engineering”: structuring the information sent to models so they make better development decisions. The talk covers practical techniques—phase-by-phase planning, living documentation as the single source of truth, separating models for research vs implementation, and incremental testing—to produce consistent, maintainable code and reduce wasted iterations.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 7:02Vibe coding problems
- 13:38Managing context window
- 20:39Practical AI tips
- 23:07Spec Driven Development
- 31:14AI-driven development changes
- 38:54Team collaboration with AI
- 42:26Q&A
related talks
18mContext Engineering — Reliable AI Instead of Hallucinations
19mContext-Aware AI Dev : Next Wave of Engineering Productivity
15mUnderstanding Context Engineering for Agentic Systems
31mBuild Intelligent AI Agents With Context Engineering
35mFrom Prompt Engineering to Context Engineering: Lessons from an AI Code Review Product
01h 07mThe EiC Problem: Junior Devs, AI Agents & the Missing Context Layer
37mThe Context Flywheel for AI Coding Teams
37mAI Under Control: accelerating safely