Weekly insights on agentic systems, design patterns, tools, copilots, and productivity at scale.
The AI Native Medhavi blog collects practical essays for developers learning how to use AI coding agents well. Recent topics include context engineering, agent skills, MCP servers, code review, editor workflows, and the operational habits needed to keep AI-assisted software work reliable.
Use it as a field manual for evaluating new AI developer tools, designing better prompts and system instructions, setting up agent-friendly project conventions, and deciding which automation patterns are ready for real teams.
I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. There's a new programmable layer of abstraction to master involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering.
Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it.
This website is that manual. We help you navigate the complexity of AI-native development.
