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: Workflow
A Local LLM Agent Workflow Built From Folders and Markdown Files
Build a gated, multi-stage local agent pipeline where each stage is a folder, prompts are editable markdown, and a human reviews output before the costly step.
25 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 readWhy Coding Agents Like Claude Code Need a Governance Layer, Not Better Prompts
A prompt shapes one exchange, not a workflow. How a governance layer of rules, scoped context, authority limits and proof of done make Claude Code dependable.
11 min readAI Video Needs Orchestration: Lessons From the VideoAgent Pipeline Design
AI video needs orchestration more than a better generator: global planning, coarse-to-fine retrieval, executable graphs, repair loops and VideoAgent's gaps.
8 min readSpec-Driven Development With AI Coding Agents: A Practical Guide
Spec-driven development with AI coding agents: a four-phase workflow, AGENTS.md and SPEC.md files, multi-agent roles, maturity levels and how to catch drift.
16 min readSelf-Improving Agents Through Skills: Reuse, Selection, Repair and Verification
A four-part design for agents that improve their own skills: save working code, sharpen descriptions, propose reviewed fixes and verify output before handoff.
15 min readA Headless Two-Agent Coding Loop With OpenCode and Ollama
How to split planning and review between two agents in OpenCode with Ollama, with permissions, skills, redaction rules, screenshots and human-only commits.
11 min readStop Handing AI Agents Wishes: A Spec-First Process for Small Teams
Stop handing AI agents wishes: a spec-first process for small teams with adversarial review by two model families, runtime tests, human merges and memory.
7 min readSpec-First Development: Agree on Intent Before AI Writes the Code
When code is cheap, intent is the bottleneck. A practical spec-driven workflow with OpenSpec, scenarios to review before coding, and tips to roll it out on a team.
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.