AI & Product Development

PDFs, slide decks, spreadsheets, scanned images, audio, even a YouTube URL — Microsoft's MarkItDown collapses all of them into the one format an LLM actually reads well. Here's what it does, how it's built, the security footnote most people skip, and where it slotted into my own stack.

The bot on this site got used more than I expected — and usage is just a stress test you didn't schedule. One visitor talked it into dropping the assistant role and performing a celebrity-style monologue. The next tried to make it read its own instructions out loud. This is the whole arc: how I caught the first one, why a careful model fell for it, the layered fix, the prompt-extraction hole I found next, and the moment I got tired of patching by hand and taught the thing to heal itself.

My site's chatbot makes two AI calls for every message — one to answer, one to grade the answer. For weeks I ran that pipeline half-blind. Langfuse is the open-source tool that let me finally see inside it.

105 commits across April and May. Every file written through conversation with an AI. Here is what two months of building with Claude Code actually looked like.

An AI tool that generates working UI components from plain English descriptions. Great for getting started fast — but never ship it as-is.

For a static portfolio I could have used something simpler. But the moment you add a chatbot that talks to an AI, you need a framework that handles both static pages and live server calls.

Pre-built building blocks that live inside your project instead of in someone else's package. Customize freely, no waiting on someone else to fix things.

Hosting, analytics, speed monitoring, custom domain, security certificates. All of it just runs. Here's what I trust it for and what I don't.

Subtle scroll animations and smooth transitions that make your site feel polished and intentional, not flashy.

I stopped using a traditional code editor and started building everything through a conversation with an AI agent. Here's what changed.

One AI answers your questions fast. A different AI grades every answer for quality. Here's why that split exists and how it works.