Done-for-you SEO, verified against the live site
White-label, internal linking, technical audits, reporting, rank tracking - the execution work you do by hand on every client, automated and QA'd.
Enter the SEO track → 12 posts For developersMCP and the Claude Agent SDK, from production
Building MCP servers and agents that do real work: Python and TypeScript, debugging, Claude Code hooks and subagents, and the parts demos skip.
Enter the dev track →Start here
White-label SEO services: an operator's guide
How to vet a provider, what's safe to delegate, what to keep in-house, and where AI agents change the math. From running the execution side in production.
Read the guide →How to automate an internal link audit at scale
The verifiable way to do internal linking with agents: propose, then validate every link against the live site so nothing fabricated ever ships.
Read the method →Is AI SEO worth it yet? An operator's honest answer
The verifiable-versus-asserted line: where AI SEO is genuinely ready today, and where trusting it is still a liability.
Read the take →Start here
What is an MCP server? A clear explainer for developers
The Model Context Protocol without the jargon: what an MCP server is, the client-server model, tools vs resources vs prompts, and why it exists.
Read the explainer →How to build an MCP server in Python (production guide)
A working guide built around a real, open-source read-only Shopify server. Tools, annotations, the safety boundary tutorials skip, and five mistakes worth avoiding.
Read the guide →The Claude Agent SDK: build your own agent
The same engine that powers Claude Code, driven from your own program. What the SDK gives you in production, how tools and MCP servers plug in, and when to reach for it.
Read the guide →