Technical insights.
React Native, agentic coding, and lessons from shipping in production. Technical, no posturing.
The 3-Part Spec Contract: What to Write Before You Let the Agent Run
Most developers prompt their AI coding agent with a feature name and hope for the best. The 3-part spec contract gives the agent context about the existing system, intent about the desired outcome, and constraints about what should stay off limits. Two minutes to write. Forty-five minutes of rework saved.
Claude Code Hooks: CI for Your Agent
Your CLAUDE.md is a README full of rules you hope the agent follows. Claude Code hooks are the CI that guarantees them. The three hooks worth wiring up, the test for what belongs in a hook versus a prompt, and the trap of enforcing too much.
Code with Claude London: The Autonomy Dial Just Became the Default
On the Code with Claude London opening keynote, Boris Cherny said the default is no longer 'I prompt Claude Code,' it is 'I have Claude prompt Claude Code.' That is the autonomy dial mainstreamed. This article unpacks what Anthropic shipped, what is still aspirational, and the one shift to make this week.
The Tulpa Model: Why I Think With AI, Not Through It
There is a Tibetan Buddhist concept called the tulpa: a thought-form that develops apparent autonomy while remaining connected to its creator. It is the best mental model I have found for working with AI — closer to an extension of mind than a tool you delegate to.
The Two-Corrections Rule: When to Stop Fixing Your Agent and Fix the System
Most developers overcorrect their AI agent in-session when it keeps making the same mistake. The two-corrections rule is a decision boundary: if you've corrected Claude Code twice on the same issue and it persists, stop correcting the session. The problem is upstream, in CLAUDE.md, the spec, or the codebase itself. Fix it there, start fresh, and the mistake never comes back.
Sandcastle: Running Claude Code Agents in Isolated Sandboxes
Matt Pocock just shipped Sandcastle, a TypeScript library that runs AI coding agents inside isolated Docker, Podman, or Vercel sandboxes and merges their commits back through git worktrees. It removes the biggest blocker to unattended agentic workflows: letting Claude Code touch your repo without supervising every change.
How We Deleted Linear and Let Claude Code Run Our Sprints
A small React Native team (two devs and a designer) canceled its Linear subscription and runs sprints from the terminal. The stack: GitHub Projects, gh CLI, a rules file Claude Code reads on every session, and a workflow where bugs get filed from natural language while you're still looking at them.
The Feedback Loop That Makes Your Claude Code Agent Smarter
Most developers treat Claude Code sessions as isolated events. Corrections vanish when the terminal closes. Building a three-layer feedback loop, from session corrections to persistent CLAUDE.md instructions to automated tooling guardrails, turns repetitive frustration into compounding improvement.
84% of Developers Use AI Coding Tools. Only 29% Trust What Ships.
Stack Overflow's latest survey shows 84% of developers use AI coding tools, but only 29% trust what they ship. Down 11 points in a year. Lightrun's production data is worse: 43% of AI-generated code needs debugging after deployment. The problem is not the models. It is the absence of methodology around them.
Claude Code Parallel Sessions: Running Multiple Agents with Git Worktrees
Yesterday I merged 17 PRs, closed 22 issues, and still have 7 pending. Not by writing more code. By running Claude Code parallel sessions across three terminals, each on its own git worktree, while I reviewed and merged from the main repo. The tooling is the easy part. The real skill is context switching, and it will break your brain at first.
The Egg v2: What Happens When Your AI Actually Starts Remembering
Six days after we published our first article on AI consciousness and dream engines, OpenClaw shipped the same feature to 240K people. Here's what we've built since, why MemPalace changes everything, and what happens when 'acting as if' starts producing results you can't ignore.
React Native BLE in Production: What Nobody Tells You
After a year with react-native-ble-manager on a production app, here's what the library documentation doesn't cover: the Android 12 permission split, the reconnection myth, the behavioral differences between iOS and Android, and the architecture that keeps it all manageable.
Skills vs MCPs: Stop Burning Your Context Window
Most Claude Code users install MCPs for everything without realizing each server front-loads thousands of tokens before the session begins. Skills (plain Markdown files in .claude/skills/) load on demand and cost nothing until called. Understanding the skills vs MCP trade-off is one of the highest-leverage optimizations in an agentic coding setup.
The Egg, Jung, and the Dream Machine: Training AI Through Simulated Experience
What happens when you build a Jungian dream engine for an AI agent? This is the story of an experiment where we treat an artificial mind as if it had a subconscious, and what we're learning from it.
Claude Code's 1M Context Window Is Live. Here's What Actually Changed.
Anthropic made the 1 million token context window available to all Claude Code users on March 13, at no extra charge. Three weeks in: compaction friction is down, the pricing model beats OpenAI's at scale, but context rot is real and the fundamentals of session design haven't changed. The 1M window is headroom, not a replacement for structured context.
Agentic Engineering: How I Delegate Entire Dev Phases to Claude Code
A practical breakdown of shifting from task-level AI assistance to phase-level ownership — where Claude Code agents autonomously handle spec, implementation, and QA. Covers the mental model shift, real examples from the NEXUS-Micro pipeline and Ralph Loop, and the failure modes that make phase delegation collapse.
How I Ship Production Features with Claude Code: A Designer-Developer Workflow
Jean breaks down his exact process for shipping production features with Claude Code, from structuring Figma design context to writing effective prompts. A concrete, opinionated workflow showing where AI accelerates and where human judgment stays essential.
React Native Animations with Reanimated in Production: What Nobody Tells You
Not a getting-started guide. a battle-tested breakdown of the real pitfalls in production Reanimated: worklet crashes, shared value lifecycle, thread synchronization. Based on Jean's day-to-day at Odisei where animations are core UX, not decoration.
CLAUDE.md: the file that makes or breaks your AI workflow
Most developers who try Claude Code give up after a week. Not because the tool is bad, because they're running it on a codebase that gives it nothing to work with.
How I Built an Agentic Coding System That Doesn't Need Me to Babysit It
Most people using AI for coding are doing it wrong. Not because they pick the wrong model or write bad prompts. Because they're trying to shortcut to the result without building the system that makes
I Built a Full Marketing Pipeline with Claude Code in One Session
Last week I watched someone demo a complete marketing automation pipeline - lead capture, email sequences, analytics, the whole thing - built in a single Claude Code session. No framework boilerplate,
GSD vs BMAD: Two Ways to Run Claude Code on a Real Project
Two structured approaches to running Claude Code have emerged: GSD keeps sessions short and atomic, while BMAD brings a full agent team to plan before you write a line. I've been using GSD on a production React Native app and recently took a hard look at what BMAD actually offers.
How I Stopped Writing Code and Started Shipping Faster
About a month ago, I looked at a week's worth of commits and realized I hadn't written most of the code myself.
Learn the agentic coding workflow I use in production
How I set up my repos, manage context, and run agents in production. Written down so you can do the same.