reWritable Is Harness Engineering You Can Do in an HTML File
A reWritable is a complete harness..The HTML file ships with its own loop, its own memory, its own persistence and its own model call.
Tag: Agents
The shell is a better LLM endpoint than your protocol
This piece is about why CLIs are the right endpoint for LLM-callable services and what the architecture looks like.
Unix Already Solved Agent Isolation
Why are we buying hardware for a problem the operating system handles?Operating systems like Unix have had multi-user isolation since the 1970s.
Skills Are Harness Engineering You Can Do in a Markdown File
A skill is a packaged set of instructions that gets injected into a context when it is relevant. In its simplest form, it is a SKILL.md file.
The Agent Harness: Everything Except the Model
Harness.is everything in an AI agent that is not the model itself.:"If you're not the model, you're the harness."
tmux as Agent Habitat
tmux is a terminal multiplexer built for humans managing remote servers. It splits a terminal into panes, keeps sessions alive across disconnections, and…
reWritable: Software that knows how to change itself
When I built clive , the core insight was deceptively simple: don't give the agent a list of tools. Give it an environment.An API is a call-response…
Departments Are Albums: Agentic AI and the Coming Corporate Unbundling
In 2000, the music industry had a problem it misdiagnosed. Napster was stealing albums. The fix was obvious: stop the theft, protect the bundle.
Vercel’s Eval Data Suggests Static Context Beats Skill Retrieval for AI Coding Agents
There's a recurring theme in AI engineering that never gets old: the "dumb" approach beating the sophisticated one.
The Web Has No API for Agents – Agentic Microformats
In February 2026, we pointed a browser-embedded AI agent at a demo e-commerce store and asked it to buy a laptop stand.