Engineering at Chipp
How we build the platform
for AI builders
Architecture, performance, postmortems, and the decisions behind Chipp. Written by the team that ships 20–30 production deploys a day.
Latest posts
Distillation Is Your Moat
Anthropic owns the best coding model. If you build your business on top of Claude (like we do) Anthropic eventually owns your margin. The defense is distillation: training your own smaller model on the outputs of the frontier. It's the most consequential AI policy debate of the decade, and almost nobody is paying attention.
Hunter Hodnett · May 12, 2026
The Bash Harness: Determinism Wraps Non-Determinism
An autonomous Claude session without a wrapper is a brilliant intern with no manager, no deadline, and an unlimited API budget. The bash harness is the manager. Here's what it enforces, why it has to be deterministic, and the specific failure modes it prevents.
Hunter Hodnett · May 12, 2026
The Opinionated Stack: Why Autonomous Coding Needs Deno, Svelte, and Cloudflare
Most autonomous-coding platforms try to support every language, every framework, every host. That's exactly why they don't work. We picked Deno, Svelte, and Cloudflare, locked the choices, and got autonomy at a scale that makes outside observers incredulous. The constraint is the feature.
Hunter Hodnett · May 10, 2026
Beyond AI Pair Programming: From Copilot to Coworker to Autonomous Engineer
Copilot was the start, not the destination. Three roles for AI in your engineering org, pair programmer, coworker, autonomous engineer, and the org-chart implications when you move from one to the next. Plus how to upgrade your own job description through the curve.
Hunter Hodnett · May 7, 2026
Vibe Coding vs Autonomous Development: The Maturity Curve from Prompt to Production
Vibe coding is the second-best place to be in 2026. Autonomous development is the best. The two get conflated constantly, they're separated by one hard architectural step. Here's the maturity curve, what each stage actually means, and how to climb from one to the other in 90 days.
Hunter Hodnett · May 6, 2026
The Autonomous Development Manifesto
Why we're building Alchemist AI: a working theory of how autonomous coding agents change the unit economics of software, who wins, who's at risk, and what the next three years look like from the inside.
Hunter Hodnett · May 6, 2026
MCP Is the USB-C of AI: Building Your First MCP Server in 30 Minutes
The Model Context Protocol is what gives an AI agent senses, the ability to read your database, drive a browser, hit your production logs. This is the tutorial. Thirty minutes from a blank file to a working custom MCP server your Claude Code agent can call. Plus the gotchas that wasted a thousand dollars of our token spend.
Hunter Hodnett · May 5, 2026
Skills vs Sub-Agents: When to Use Each in Claude Code
Skills and sub-agents are the two tools you reach for when CLAUDE.md and hub-and-spoke aren't enough. They look similar, both give Claude specialized capability, but they're architecturally different in a way that determines whether they save your context budget or burn it.
Hunter Hodnett · May 4, 2026
How to Make Your Business Discoverable and Sellable to AI Agents
A practical guide to ACP and the Machine Payments Protocol. What they are, how they're layered, and how to make your service discoverable and payable by autonomous agents.
Hunter Hodnett · May 3, 2026
Agentic Design Patterns for Production: 7 Patterns We Battle-Tested at Chipp
Design Patterns named the moves OOP engineers were already using ad-hoc, and naming them made them transferable. Agentic systems need the same treatment now. Seven patterns we've battle-tested across two years of running autonomous development at Chipp, what each one solves, when to use it, and how to know you've gotten it wrong.
Hunter Hodnett · May 3, 2026
CLAUDE.md Architecture: A Hub-and-Spoke Pattern for Autonomous Codebases
Your CLAUDE.md is the highest-leverage file in your codebase. It survives compaction, loads in every session, and accumulates the rules that turn a generic Claude into your codebase's senior engineer. Here's the full architecture, root file, directory hub-and-spoke, scar-tissue practice, auto-load tables, and the anti-patterns that wreck it.
Hunter Hodnett · May 2, 2026
Building a Self-Healing Bug Bot: The Autonomous Dev System We Use at Chipp
The implementation post. Five components, real bash, real Claude Code, and the system that ships 20-30 production changes a day at Chipp without a pull request in sight. Includes the harness skeleton you can copy, the MCP fleet we run, and an honest accounting of cost and failure modes.
Hunter Hodnett · May 1, 2026
Context Engineering: The Skill That Turns Claude Into a Production Co-Developer
Context engineering is the foundational discipline of autonomous development, and the source of most of your hallucinations, token bills, and pipeline failures. Four core moves, the patterns we run every day at Chipp, and how to know it's working.
Hunter Hodnett · April 30, 2026
The Autonomous Development Manifesto: Why We're Building Alchemist
An engineering team of two. 20-30 production deploys a day. No PR queue, no on-call rotation. This is the case for autonomous development, the discipline, the architecture, the maturity curve, and ADaaS as a category. Plus the system we run at Chipp and the product we're building from it.
Hunter Hodnett · April 29, 2026
What Is Autonomous Development as a Service (ADaaS)?
ADaaS is a category, not a feature. It productizes the engineering practice itself, the pipeline, the harness, the verification loop, the documentation system, the whole apparatus. Here's what you're actually buying, what it isn't, how to evaluate a provider, and why this is the next -aaS to reshape an industry.
Hunter Hodnett · April 28, 2026
What is Autonomous Software Development?
A working definition of autonomous software development, how it differs from coding assistants like Copilot, and where the technology actually delivers today.
The Alchemist Team · April 27, 2026
Welcome to Chipp Engineering
An index of what you'll find here: system design, postmortems, performance work, and the reasoning behind our architectural decisions.
Hunter Hodnett · April 21, 2026
Follow along
New posts land every few weeks. Grab the RSS feed, or point your agent at /engineering/rss.xml for full content.