Category
7 posts
MCP standardizes how AI agents talk to tools and data. What it actually solves, how the pieces fit together, and where it fits next to n8n-style automation.
AI features moved from developer tools into photo, video, and banking apps in 2026. Here is what that shift means for building consumer-facing products.
Lighthouse now scores sites for AI agents reading them, not just human visitors. Here is what the Agentic Browsing checks actually measure and how to pass them.
AI coding assistants stopped being autocomplete once they could read a codebase and plan multi-file changes. Here is what actually changed in how I work.
Local LLMs via Ollama trade raw capability for privacy, cost, and offline access. Here is how I actually decide between local and API-based models.
AI writes implementations faster, but that raises the value of tests instead of lowering it. Here is the testing discipline I apply to AI-generated changes.
Vibe coding gets code running fast, but running and correct are different claims. Here's the gap I actually check before shipping AI-generated code.