Agents A1 and Qwen: coding-workflow observations
A coding-workflow comparison of Agents A1 and Qwen finds different failure modes across Go, Zig and Next.js, and a useful response to QA feedback.
Lynn Cole / Projects
Software, research projects, repositories, and published work.
A coding-workflow comparison of Agents A1 and Qwen finds different failure modes across Go, Zig and Next.js, and a useful response to QA feedback.
A product name is a micro-value proposition. A memorable conversation about naming came back to me while looking through 230 poetically named repositories.
Lines of code mean more when read alongside completed features, deletions, commit hygiene and the conversion of activity into working software.
Coding agents confuse code volume with productivity. My experiments use explicit coding culture and a local definition of engineering quality to challenge that bias.
A new planning loop helped the coding swarm, then conflicting tickets melted the benchmark. The next fix is backlog validation before implementation.
Kilo separates durable, auditable memory state from replaceable retrieval projections. The architectural boundary keeps truth in the mutation history.
Pizza Empire tests a long-horizon coding swarm against a whole product: ordering, kitchen workflow, delivery and the constraints that make them coherent.
Being an AI generalist was not always a comfortable professional identity. Computer vision and agents remain some of the most creatively satisfying engineering work I do.
You build in public to share your notes with like-minded developers, collaborators, and potential employers.
A coding-agent demo can complete a task. A product needs to understand arbitrary codebases, resolve ambiguity and recover without constant babysitting.
An evaluation stopped to announce that it had started. Restarting it exposed a concurrency failure in the project’s database architecture.
Hardening a coding agent means fixing integration seams, recertifying models and making the same workflow hold across providers.