Building software with AI, together
Experiments, research, and honest takes on using agents in production teams.
Writing
How We Actually Ship with AI
The concrete workflow we use to go from a vague idea to code running in production, with AI agents doing the heavy lifting. Three moves, one increment file, everything in git.
Read Post
Stop Being Your AI Agent's Assistant
When we launched code.umans.ai at the beginning of February, my cofounder Naji and I saw it as an opportunity to challenge ourselves. We had unlimited LLM access now. No more token anxiety. So we asked: what happens if we really let our agents work autonomously?
Read Post
GLM-5 vs Kimi-K2.5: Long-context serving at scale
Why GLM-5 is a real step forward compared to GLM-4.7 for serving long-context coding agents, and why we still keep Kimi-K2.5 as the default for the best experience.
Read Post
Shipping Solo With AI Agents Without Reading the Code
A new abstraction is emerging for solo building: iterate on intent with an AI agent, run, refine, and read little code. What enables it now, and where it breaks.
Read Post
The Claude Code experience, self-hosted
How to run Claude Code against a self-hosted DeepSeek V3.2–class model using vLLM + LiteLLM, so agentic coding stays inside your perimeter.
Read Post
Can coding agents actually follow your codebase’s rules?
We ran a reality check to see how well different coding agents follow a repo’s AGENTS.md in practice.
Read Post
Your AI Coding Agent Doesn’t Care About Your Conventions
(Updated on )
Exploring the challenges and strategies for maintaining codebase consistency in the age of AI coding agents.
Read Post