Amir Pournasserian
Serial entrepreneur, hands-on AI architect, open-source lover, always learning
I build AI and platform systems that have to keep working once they meet production, compliance and scale. Over twenty years of it, so far.
Right now I lead AI platform architecture for the guest-facing AI systems at Four Seasons Hotels and Resorts. Before that I founded and ran a banking software company, led the build of a real-time tracking system for Canada’s Department of National Defence, designed a travel booking platform, and started two IoT companies. I still like shipping software, not just architecting it, which is why FluentCMS, YeSvelte and mcp-my-site exist.
Explore
Writing Notes from my own research, for engineers building the same things: MCP servers, AI tooling for codebases, and the IoT and machine-learning work that came before.
- RAG, CAG, KAG and the search beneath them: which fits which problem in 2026 RAG, CAG, KAG and the search beneath them, from BM25 to graphs, compared on the published evidence, with a guide to which fits which problem.
- How MCP extensions work MCP extensions are optional additions, off by default: which exist in October 2026, how both sides negotiate them per request, and how a server falls back.
- What to require from an MCP server vendor: a buyer’s checklist The questions to put to an MCP server vendor before you sign, drawn from the 2026-07-28 specification, and what a good answer to each looks like.
- Open-source AI chat apps in 2026: 51 mapped, 12 compared, and which fits what Fifty-one open-source alternatives to the ChatGPT and Claude apps, mapped by GitHub stars and activity, twelve compared, and a pick for eight uses.
- Making a website AI friendly: what the bots actually fetched from mine What AI crawlers actually fetched from this site in 18 days: pages, robots.txt and the sitemap most of all, and llms.txt never by a verified crawler.
- An LLM-friendly website checklist: eight steps and a test for each Eight steps to make a website easy for AI crawlers and agents to read, in the order the bots fetched them, each with a command to check your own site.
- MCP servers for websites in 2026: 44 tools, sorted by who runs them Forty-four ways to let an AI agent search and ask a website over MCP, from Wix and Shopify to NLWeb and CMS plugins, sorted by who runs the server.
- AI tools that document a codebase in 2026: 17 compared, and what none of them does yet Seventeen tools that turn a repository into documentation, compared on what each reads and produces and who it serves, and the gaps none of them fills.
Ideas Startup and open-source ideas I keep coming back to, written up for anyone who wants to run with them.
- Sites that speak for themselves: an agent endpoint for every small website An idea for an open-source tool that lets a small website answer AI agents, its search box and a chat window from one index built when it is published.
- An OS for AI agents: not the one on your laptop An idea for running a fleet of personal AI agents: not an operating system per agent, but one small host that holds what each agent may call, spend and do.
- An AI-first CMS: AI operates, people govern An idea for a CMS built the other way round: the AI does the work by default, and people write the rules and review what matters before it goes live.
- MCP is in its Yahoo era An idea for the ranking era of MCP: one service an agent asks “who can do this?” and gets the best servers back, and why the time to build it is now.
