30 posts shown
swamp emits OTLP traces and logs natively. This is how I ship the traces through a Caddy auth gateway into Tempo and turn them into a RED dashboard I actually look at.
I stood up 'swamp serve' as its own FreeIPA service account using nothing but swamp models. The tool configured the host that runs the tool, and then my own OAuth flow spent an afternoon trying to…
Over twelve thousand agent-written unit tests, all green, and the boundary is still where we find out the code is wrong. Agent-written tests are specification, not verification — a map for the next…
An engineering note on how repeatable Jev is — what we replicated, what surprised us, what didn't hold up, and the one check worth adding.
A worked example of turning an opaque Heroku estate into a versioned, queryable inventory that can actually drive a migration.
TypeSafe AI screens. Swamp routes. Claude gets the work worth paying for.
When an agent owns the verification-and-repair loop, what record of that process survives? The attestation captures the terminal state. The iterations that preceded it — the failures, the fixes, the…
Swamp World is an interactive 3D WebGL experience that lets users explore Swamp Club's real production infrastructure by navigating districts, tracing requests, and discovering services to earn a…
This week on The Business of Open Source, I spoke with Adam Jacob , co-founder and CEO of the Swamp Club. The first thing we talked about was When To Quit. System Initiative, Adam’s second…
A developer reflects on overengineering an AI-orchestrated "Software Factory," where excessive verification contracts and receipt-checking slowed delivery more than they helped, leading to a…
Building a swamp extension that lets an agent explore your Minecraft world, find structures, and plan a vacation route
My seven-year-old daughter used GPT Astra to create a 3D game this weekend. She loves it. Everyone can create software now; your platform's job is to contain the brutality within.
How AI coding agents changed how I write Django.
In my first experiments with AI agents, I quickly learned that there are certain things you should not use them for. Scripts are still king for deterministic tasks, even one-offs. Instead of asking…
made various cleanups, tweaks to make the app make a bit more sense, even though it's still crude. i find it quite helpful to navigate my "swamp things", in particular models and workflows. data an...
TUI interface built for swamp. Contribute to Dieterbe/lazyswamp development by creating an account on GitHub.
Paul Hammant pointed out that Google separated verification from merge coordination more than fifteen years ago. He was right. What actually changed is who owns the feedback-and-repair loop — and…
CI conflated two jobs: executing verification and coordinating merges. Agents change the equation. If you can verify before the PR opens and fix failures in context, why should CI discover them first?
A developer describes shipping their first independent SaaS app by separating agentic work (handled by Amp) from deterministic, typed automation (handled by Swamp), explaining why this division…
Let AI agents be the reasoning glue around deterministic scripts. Make repetitive work faster, cheaper, auditable, and reusable with Swamp.
Discover how to overcome Git's one-tree problem by leveraging worktrees for parallel AI execution, enhancing your agents' efficiency.
Learn how to prevent coding mishaps by implementing a structured planning process before AI agents make changes to your codebase.
How I built sfalcon.dev using swamp
Where I stand on using AI for Mere Linux
Mature organisations monitor CI/CD efficiency and PR bounce-back rates. In the agentic world, how can you measure the performance and efficiency of your software factory?
No AI was harmed in the writing of this blog (or, ironically, used at all)
When an agent writes the code and the tests, passing doesn't tell you much. Black box acceptance tests are the independent verification boundary that actually matters.
Last week, a former coworker of mine shared an essay he wrote called Everyone’s Building the Outer Loop. I completely agree with his solution in the ideal case, but I’m not sure that will work for…
I’ve been feeling frustrated the last few weeks about how agentskills.io style skills aren’t providing the repeatable processes that I’ve come to expect from computers doing work.
Discover why 'Loop Engineering' may just be a repackaged approach to software development and how to leverage LLMs more effectively.