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
Cutting Agent Token Costs: Caching, Routing and Context Hygiene
Shrink LLM agent bills with prompt caching and semantic caching, lazy-loaded tools, model routing and cascades, subagents, and plain old context hygiene.
16 min readContext Engineering in Practice: A Claude Agent SDK Research Agent
Build a Python research agent with the Claude Agent SDK using write, select, compress and isolate patterns, then compare it against a naive baseline in measured runs.
20 min readContext Engineering for LLM Apps: Structured Output, Tools and Agent Limits
How to build model input deliberately: context selection, prompt templates, JSON schemas, constrained decoding, tool calling, agent loops and bounded autonomy.
13 min readContext Engineering for a Quant Research Agent: Proof Levels and Data Stores
Context engineering for a WorldQuant research agent: rules, observations and beliefs at separate proof levels, spread across a ledger, event store and graph.
12 min readVibe Coding vs Agentic Engineering: What Google's New SDLC Paper Argues
A summary of Google's whitepaper on the new SDLC: verification as the dividing line, harness over model, context engineering, the 80% trap and conductor versus orchestrator.
9 min readWhy the Modular Monorepo Suits Coding Agents: See Everything, Touch Little
Polyrepos blind agents and unstructured monorepos flood them. Open context, encapsulation and a real dependency graph make the modular monorepo work for agents.
7 min readSandboxing a Coding Agent and Keeping Its Context Window Lean
Sandbox a coding agent with Seatbelt or Bubblewrap, then keep its context window lean with spill files, stubs, compaction and prefix-cache friendly injection.
10 min readWhy Long-Horizon Agents Need a Harness: How Deep Agents Manages State and Context
Why long-horizon agents need a harness: how LangChain Deep Agents fights context rot with four pillars, middleware, filesystem backends and isolated subagents.
12 min readCLAUDE.md, SKILL.md and MCP: Which Layer Holds Which Instructions
Why one giant CLAUDE.md fails coding agents, what belongs in rules, skills and MCP connections, scopes and paths, a decision tree and the AGENTS.md naming trap.
11 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.