Context Engineering for AI-Assistant Development
A four-layer approach to organizing project knowledge, tools, hooks, and skills so they work across AI coding tools without maintaining parallel configs.
More issues
Signal Check: February 20, 2026
The psychological cost of AI adoption got a name this week, along with the data to back it up. Developers are using AI tools more than ever while trusting them less, and researchers are starting to explain why the gap keeps widening.
Deep Blue
Simon Willison
Willison and the Oxide
AI-Assisted Reviews with GitHub Copilot
In my last article, I argued that engineering teams should fix the review process before scaling code generation. AI review tools won’t solve the capacity problem, but they handle what humans struggle to sustain: speed, consistency, and pattern recognition.
This is the practical follow-up. Copilot code review has added
Signal Check: February 13, 2026
This week's signal in AI and engineering
AI-assisted Code Reviews
Improve the Review Bottleneck Before Scaling Code Generation
The Critical Thinking Paradox
AI erodes the very skills needed for success
MCPs, Agents, Skills. Oh My!
Understanding the emerging ecosystem of LLM building blocks
Avoiding the AI Complexity Cliff
Managing scope in AI-assisted development
AI Reality Check
The Forces Challenging the Future of AI
Pragmatic AI Adoption
Avoid the Slop and Amplify Innovation