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: Architecture
A Production Harness for Claude Code: Six Layers From Slack to Merged MR
How a six-layer harness turns Slack tickets into merged code: event intake, gated agent loops, durable state, self-healing, observability and operator control.
42 min readAI Agent Foundations: Purpose, Prompt Design and Model Selection
How to lay the groundwork for a production AI agent: define purpose and success metrics, write prompts with goals and guardrails, then pick the right model.
21 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 readRebuilding a Claude Code-Style Agent With LangChain Deep Agents
How a coding agent's harness works, from the core loop to tools, planning, memory, subagents and sandboxed approvals, rebuilt step by step with deepagents.
16 min readWhen React Memoization Backfires: Why Fewer Renders Made the App Slower
When React memoization backfires: memo, useMemo and useCallback added cost and stale closures to a big page. Moving state and profiling the flow fixed it.
13 min readAI Architecture for Production Agents: Failure Modes and Control Layers
A layer-by-layer architecture guide for production agent systems: failure modes, guardrails, evals, observability, cost control, zero trust and governance.
12 min readEverything Is a Plugin: The Cordis Design Behind DeepSeek Harness
How DeepSeek Harness builds an agent runtime from plugins, using Cordis ideas like reversible effects, reactive dependencies and a replaceable agent loop.
19 min readA Sandbox for Claude Code: Isolated Agent Environments on a Laptop
How a local Kubernetes sandbox gives coding agents their own machine, scoped credentials, an egress allow-list and a fleet view, with build-versus-buy tradeoffs.
12 min readWhen the Dashboard Is Green and the Agent Is Wrong: Tracing State
The dashboard is green and the agent is wrong: failures hide in state passed between healthy steps. What tracing, routing records and evals must capture.
12 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.