An evidence-based look at the impact of AI on software development, covering productivity research, code security data, role changes, and what enterprise teams should do about it.
Context Engineering: What Your AI Assistant Sees Matters More Than What You Ask
Most of the advice I’ve seen about getting good code out of AI assistants like Claude Code is about writing better prompts. In my experience, that stopped being the main lever a while ago. What matters more is what the model can actually see when it reads your prompt: which files, which conventions, and how much noise is in the way.
People have started calling this context engineering. In this post, I’ll walk through what that means and three habits I’ve picked up, using Claude Code’s CLAUDE.md and subagent files as concrete examples.
Agentic AI in the Software Development Lifecycle: 2026 Adoption and Impact Data
Agentic AI has moved well past the pilot stage for code generation, but adoption remains uneven across the rest of the software development lifecycle. Coding assistants are now mainstream; testing, code review, CI/CD, and incident response are each at very different points on the adoption curve, with very different levels of measured payoff. This report compiles current 2026 data on …
AI Development Cost in 2026: What Businesses Actually Pay
How much does AI development cost in 2026? Explore real pricing from $5,000 to $2M, plus build-vs-buy, talent, compute, and total ownership costs
The Shift Toward Local AI: A Developer’s Perspective
AI has moved fast, faster than most of us expected, and the cost of keeping up is starting to show. What began as inexpensive, wide-open access to powerful cloud models has shifted into a landscape of rising token prices, stricter quotas, and unpredictable availability. More teams are starting to ask a question that would have sounded unrealistic a year ago: should we start hosting our AI models locally?
In this post, I’ll walk through why token costs and model access are becoming harder to rely on, why open models and local hardware are closing the gap, and what actually happened when I ran a full agentic workflow on my own machine, starting with the cost problem that kicked this off.