FEED

Talking with Stephen O'Grady about AI and building the machine that builds the machine

How teaching your Claw about Swamp can help avoid the lethal trifecta

Engineering with AI Agents doesn't mean you get to skip the fundamentals

Building the machine that builds the machine, in order to learn what I believe about the future of my profession

Step-by-step guide: install Swamp from scratch, set up @magistr/jscad-cad extensions, configure the Claude Code skill, and generate 3D models from text descriptions.

How we built a CAD generation pipeline using JSCAD, Swamp extension models, and Claude — from choosing the right CAD system, through 7 iterations of debugging a genie lamp with 6-view projections, to…

Deploying Cozystack on a Talos Kubernetes cluster using Swamp extension models, with claude-code handling the execution while the author approves steps.

A 10-hour technical post-mortem of attempting to virtualize macOS Tiger 10.4 on QEMU with OpenCore, managed by claude-code and Swamp on Unraid.

Example42 delivers Puppet training, consulting and development services. It provides consulting on automation and DevOps practices

Your team's workflow and your agent's lifecycle want different things

This week I'm talking with Adam Jacob, founder of System Initiative and creator of Swamp, about what happens when AI agents change the entire shape of software development. We discuss how he went…

Every codebase has the rearchitecture that never gets prioritised. We split ours into six parallel workstreams and shipped it in eight days, start to finish. The hard part wasn't speed. It was…

When agents can build anything in an afternoon, the temptation is to build everything. The products that survive are the ones where someone had the discipline to say no.

Five of us build swamp. None of us write code. Agents write it, review it, test the binary. The work didn't shrink — it shifted to the decisions that were always the most valuable.

Five people, $3,000/month, zero lines written manually. GitHub just moved to per-token billing. The era of flat-rate pricing absorbing your agent's inefficiency is ending. Your agent isn't the…

The PR-as-contribution model was built for a world where writing code was the bottleneck. AI agents broke that assumption. GitHub shipped a kill switch on PRs. Hashimoto built Vouch. We closed the…

Encoding judgment the agent lacks into AWS operations

Mechanical friction is dissolving, but do not mistake easy for simple

We use swamp to build swamp. That sounds like marketing until you look at how an issue actually moves through our process — not as a GitHub thread with comments piling up, but as a state machine with…

Skills are context. They're the thing an agent reads before it decides how to use swamp. If the skills are wrong, everything downstream is wrong — so we test them in CI the same way we test code,…

Agents open PRs in our repo. Other agents review them. That means untrusted input flowing through models with merge authority — so we built a pipeline with four independent AI reviews, scoped tools,…

Every release binary gets dispatched to a separate repo running CLI tests, adversarial security tests, and benchmarks. Three recent bugs — all with full unit test suites passing — never reached a…

Most people hit "always allow" within the first hour. Agent trust is a system design problem, not a containment problem. Three layers of permissions, conventions, and context let the agent work…