Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: Context Engineering
Context Engineering for AI Agents: Curating What the Model Sees
Why agents degrade as their context grows, how context engineering differs from prompt wording, and a simple pipeline for choosing what each model call sees.
8 min readDesigning the Agent Harness: Policy, Sandboxing, Memory and Verification
Learn which runtime layers turn a tool-calling LLM into a dependable agent: execution policy, OS sandboxing, persistent state, verification, context control and cost.
19 min readFrom Writing Kotlin to Directing Agents: The Mobile Engineer's New Role
How coding agents shift an Android engineer's work toward specifications, context, architecture constraints and verification, and which fundamentals matter more than ever.
13 min readPrompt Engineering or Context, Harness, Loop? Debugging AI Agents by Layer
Prompt engineering, context engineering, harness engineering and loop engineering each fail in their own way. A trace-first routine finds the layer that broke.
14 min readCodeBuddy: Smarter Context Retrieval for AI Coding Agents
Explains how a dependency-graph-driven context retrieval system helps AI coding agents avoid both context starvation and context overload on large codebases.
8 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.