Is Your llms.txt Already Stale?
In which I build a freshness check for llms.txt and discover that my tools were the problem.
In which I build a freshness check for llms.txt and discover that my tools were the problem.
In which I explain why a vibes-based approach to AI and docs ain't cutting it.
In which I lurk in server logs and try to make sense of what I see.
In which I show you how I made multiple Hugo sites agent-friendly.
In which I deep dive on a Stripe Skill, and what it means for the industry.
In which I discuss how model training and agents need different docs access patterns.
In which I answer someone who asked me how to get started with AI.
In which I ask an agent to help me explore Web Fetch with docs pages - and get a surprise.
In which I ask an agent to view hundreds of docs pages - and feel sad.
In which I build a validator and analyze popular Agent Skills.
In which I deep dive into the problem domain to discuss the problems we had to solve.
In which I design systems to scale code example testing across the org.
In which we report what we learned through the code example audit.
In which we explore different ways to break down audit data.
In which we decide what information to store, and how.
In which we have an LLM help us assign categories to code examples.
In which we explore the best way to get content and work with audit data.
In which we dive deeper into what we actually want to know.
In which we decide what to count, and how.
In which we try to make sense of our code examples, and track them.
In which I explore lessons learned in the second month of a project to consolidate 9 docs sets.
In which I explore lessons learned in the first month of a project to consolidate 9 docs sets.
In which I explore WHAT to test in docs code examples.
In which I explore HOW to test docs code examples.
In which I make a whole lotta Charts.
In which I decide how I want to structure my documentation metadata.
In which I free my data from Google Sheets.
In which I discuss the benefits of having a documentation team writing the code examples.
In which I discuss the strategies for knowing when docs need updates.
In which I explore why you really need to test docs code examples.
In which I automate readability scoring for documentation.
In which I wax poetic about the value of previewing a docs-as-code site.