# How I Used My Own Blog to Research My Presentation About It

**URL:** https://andreskristensen.blog/post/how-i-used-my-own-blog-to-research-my-presentation-about-it

![funny guy presenting](https://cdn.sanity.io/images/i6gaeymf/production/fd07d75d5a0ef83023a762f6734749f72e38f0c7-1024x1024.png)


---

**Summary:** The author needed a fast way to collect 14 blog posts for a presentation without manually copy-pasting from the browser. Fortunately, the blog already exposed each post as clean markdown at /md/posts/[slug], originally built for AI tools. This endpoint strips away HTML, navigation, and cookie banners, returning only the core content, which the author then fed into Claude for rapid reading and summarisation.

Before working with individual posts, the author used /llms.txt, a structured, machine-readable index of the site similar to robots.txt but designed for AI discovery. Claude used this index to understand the site’s structure and locate relevant posts. For the presentation itself, the author used Slidev, a markdown-based slide tool, allowing Claude to generate and refine slides directly in markdown. The experience highlighted a “meta” benefit: infrastructure built for AI and other developers ended up being most useful to the author, demonstrating that investing in AI-friendly content formats can pay off immediately for the site owner.

## The Setup

When I was asked to present my blog to a group of colleagues, the first challenge was practical: how do I gather 14 posts worth of writing without copy-pasting from a browser? I'd built a lot into the blog over the past year and needed a fast way to pull it all together.

## Markdown at /md/posts

Every post on the blog is available as clean markdown at /md/posts/[slug]. I built this endpoint for AI tools — strip the HTML, navigation, and cookie banners, and return just the content. It turned out to be exactly what I needed for my own research. I fed several posts directly into Claude, which read and summarised them in seconds.

## llms.txt as a Site Index

Before diving into individual posts, I pointed Claude at /llms.txt — a structured index of the site, like a machine-readable table of contents. Claude used it to map what the site contained before pulling individual posts. It's a convention similar to robots.txt but designed for AI discovery rather than search engine crawling.

## Building the Slides with Slidev

For the slides I used Slidev (sli.dev) — a presentation tool built for developers where slides are written in markdown. That means Claude can write and edit them directly. The Claude Code skill for Slidev made it straightforward to generate the initial structure, iterate on layout, and keep the tone consistent. No drag-and-drop interfaces to fight with.

## The Meta Moment

There's something satisfying about a tool working for yourself first. The markdown API and llms.txt were built with the idea that AI systems and other developers would find the blog easier to consume. In practice, the first person to benefit was me — using my own infrastructure as a research pipeline for a presentation about that same infrastructure.



## Conclusion

If you're building a content site and wondering whether AI discoverability is worth the effort — build it anyway, even if you're not sure who else will use it. The most immediate value might come from yourself.