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: claude-code
From prompt tweaking to feedback loops: DSPy, GEPA and Claude Code
Learn how DSPy, MIPRO, STORM, GEPA, Claude Code and MCP shift AI work from rewriting prompts to building measurable programs with executable feedback loops.
10 min readA 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 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 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 readHow Subagents and Multi-Agent Systems Split Work and Cost Tokens
Subagents vs multi-agent systems: the orchestrator-worker design, four topologies, what each costs in tokens, and the cases where a single agent does better.
12 min readHow Claude Code Fits Together: Skills, Subagents, MCP, Hooks, Plugins
How Claude Code fits together: CLAUDE.md, skills, subagents, MCP, hooks, slash commands and plugins, what each building block does and when to reach for it.
10 min readAn Eight-Layer Claude Code Setup: CLAUDE.md, Memory, Hooks and Guardrails
How eight configuration layers, from scoped CLAUDE.md files and hooks to device verification and reversibility rules, make a Claude Code workflow trustworthy.
9 min readSeven AI Coding Agents Worth Comparing Before 2026 Ends
Claude Code, Cursor, Copilot, Codex, OpenCode, Devin and Antigravity CLI compared: what each does best, how it's priced as of August 2026, and how to mix them.
9 min readWriting Down the Loops an AI Agent Runs on a Mobile App
Writing down the loops AI agents run on a mobile app: four questions each loop must answer, six nested loops from tap to slice, and checks that catch nothing.
9 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.