Now
I'm learning this in the open. Coming from years of frontend, frontend build systems, and Node.js backends, I'm focused on what makes a tool actually usable by an agent: schema-first discovery, deterministic output, structured errors it can recover from. Sol is where I'm working it out.
Building
Sol — the agent toolset for Upsun. The tool layer an agent or harness calls to operate the platform. Schema-first, token-efficient, built to be called, not read. → heysol.dev
More agent-tooling work landing through 2026.
Background
Years across frontend, frontend build systems, and Node.js backends. The build-tooling side maps closely to agent tooling; the Node and TypeScript side to MCP and SDK work; the frontend to the product layer — so the plan is to build AI products end to end, the tooling and the interface people actually use.