I don’t usually write hot takes. But StrongDM’s Software Factory post is worth it, so here goes. Their post is elegant, short, and well-written, so I’m going to just go through a bunch of pull quotes. Compounding correctness long-horizon agentic coding workflows [now] compound correctness rather than error This is a big, empirical claim. I’m already convinced by my own experiences that agents, suitably scaffolded, can form a Brownian ratchet, such that pouring on more compute helps, on balance.
Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study
As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or ``cleanliness'' of the underlying code affect an agent's ability to navigate and modify it? To isolate the effect of code cleanliness from agent capability, we introduce an evaluation protocol built around minimal pairs: repositories that match on architecture, dependencies, and external behaviour, but differ on static-analysis rule violations and cognitive complexity. The pairs are constructed in both directions, by agent pipelines that either degrade a clean repository or clean a messy one. We author 33 tasks across six such pairs, evaluated through hidden tests at the application's public surface. Across 660 trials with Claude Code, code cleanliness does not change the agent's pass rate. However, it substantially alters the agent's operational footprint: agents working on cleaner code use 7 to 8% fewer tokens and reduce file revisitations by 34%. Our findings suggest that traditional maintainability principles remain highly relevant in the era of AI-driven development, shaping the computational cost and navigational efficiency of coding agents. Code cleanliness joins model choice, harness, and prompting as a factor that materially affects agent behaviours.
Write-Only Code | Heavybit
AI may be accelerating software into a world of "write-only" code that forces a rethink of culture, processes, and tools. Heavybit’s Joseph Ruscio explains.
Improving My Hardware Workflow With CI and Nix
One thing you might notice if you read my blog is that I do a lot of hardware projects. Generally, these include a board, some software, and possibly some extraneous components (like CAD design, such as a case). Software tooling is quite mature, but I find that hardware had traditionally lagged quite a bit behind. For a while, I just lived with this, but over the last few months I've put in a bunch of effort to improve my workflow.
Writing code is cheap now - Agentic Engineering Patterns - Simon Willison's Weblog
The biggest challenge in adopting agentic engineering practices is getting comfortable with the consequences of the fact that writing code is cheap now.
PrimeIntellect-ai/prime-agent
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Managing Agent Skills with Your Package Manager | pavel.pink
AI coding agents use skills — markdown files that teach them domain-specific tasks. We publish ours as conda packages and manage them with pixi, getting versioning, lockfiles, and supply chain security for free.
How StrongDM’s AI team build serious software without even looking at the code
Last week I hinted at a demo I had seen from a team implementing what Dan Shapiro called the Dark Factory level of AI adoption, where no human even looks …
A sufficiently detailed spec is code
Specifications do not address the limitations of agentic coding
Agentic Engineering Patterns - Simon Willison's Weblog
Patterns for getting the best results out of coding agents like Claude Code and OpenAI Codex. See my introduction for more on this project.
How Generative and Agentic AI Shift Concern from Technical Debt to Cognitive Debt
The term technical debt is often used to refer to the accumulation of design or implementation choices that later make the software harder and more costly to understand, modify, or extend over time...
What Functional Programmers Get Wrong About Systems - Ian Duncan
Type systems verify properties of programs. Production correctness is a property of systems. The gap between these is where the interesting failures live.
What spec-driven development gets wrong
The most powerful AI software development platform with the industry-leading context engine.
Note on 24th September 2026
The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder. We can do amazing things with them, but unlocking …
Strix the Stateful Agent
Meet Strix. I built Strix initially just as a hack project, but it’s become a tremendous help. But also, it’s gotten a little weird at times. Strix is a stateful agent. An AI that remembers long after the conversation is finished.
