I expected more AI agents to make coding faster. They didn’t. That was not the result I was looking...
Developer builds Sol-Luna orchestrator where AI decides whether to delegate tasks to agents. Benchmark: supervisor chose zero workers (parallelism 46-108% slower). Multi-agent coordination overhead exceeds benefits; optimize single reasoning before adding agents.
I expected more AI agents to make coding faster.
They didn’t.
That was not the result I was looking for, but it ended up being the most interesting result of the project.
Over the past few weeks, I have been building Sol-Luna Orchestrator, an open-source orchestration layer for OpenAI Codex.
The idea started with a simple question:
I thought running agent sessions in parallel would multiply productivity. What I actually got, in the space of one week, was a…
AI coding agents changed the way I work. When I started using them, the workflow was simple: Give...
I Built a "Production-Ready" AI Agent Framework. It Was a Lie. So I Fixed It. A story...
The Problem: Agent Workflows Are Still Hard To Share AI coding agents are getting better,...
I used to have one AI assistant. It did everything — coded, wrote docs, answered questions, monitored...
I Tried Building an AI Agent That Does Real Work. The Biggest Bottleneck Wasn't the...
