Blog
Writing
Notes on agents, harness design, AI infrastructure, and shipping fast.
-
AI agent access and control: a field guide
One map of the agent stack: access through one OAuth, built-in tools, memory, plain-English control, and portability across hosts — and where CoreSpeed fits.
Read → -
The setup tax: why connecting AI agents to apps is hard
Connecting AI agents to apps means OAuth, token refresh, scopes, rate limits, pagination, and webhooks per service. Here's why that work stalls agent projects.
Read → -
Building AI products fast: my stack and patterns
The stack and patterns I use for building AI products fast — Vercel AI SDK, Deno + Hono, Supabase, Drizzle, Stripe, AG-UI — drawn from BuildLog and Fixo.
Read → -
Rebooting this site
Why I rebuilt my corner of the internet — and what I am working on now.
Read → -
What an AI agent harness actually does
An agent harness is the loop around the model — tool access, error recovery, staying on task. Why that layer decides whether AI agents are useful.
Read → -
Building production AI agents with the Vercel AI SDK
Streaming, tool calling, structured output, and provider routing — the patterns I use to ship real AI products on the Vercel AI SDK, not just demos.
Read → -
AG-UI: giving your AI agent a real interface
AG-UI is a protocol for streaming agent state and actions into a product UI. How I use it in Fixo to turn a chat into real actions.
Read → -
MCP vs. agent connectors: how agents reach apps
MCP is the standard interface for handing tools to an agent. Agent connectors handle auth, hosting, and breadth. Here's how they fit.
Read → -
AI agent guardrails: policy, approvals, and pay
AI agent guardrails — plain-English policy, human approvals, and Agent Pay spending limits — are what make an agent safe to run past a demo.
Read → -
What I'm building at CoreSpeed
Most AI agents can think but cannot act. CoreSpeed gives them access to the apps you already use — so they do real work, not just chat.
Read → -
AI agent portability: run one agent across hosts
AI agent portability — keep your apps, memory, voice, and policy with the agent, not the host. Switch Claude Code, Codex, and Cursor without re-setup.
Read → -
The AI agent tools every platform should ship built in
App connectors aren't enough. The AI agent tools every agent needs built in: web search, scraping, image generation, code sandboxes, and email.
Read → -
A dual-format gateway for Claude Max
Point your existing OpenAI- or Anthropic-SDK code at a Claude Max subscription, no rewrites.
Read →