I joined Patrick Bosek on the Behind the Docs podcast to talk about what AI actually means for technical writing. We covered the evolving role of tech writers as architects of tooling and content systems, why AI works better as a collaborator than a replacement, the tension between moving fast and implementing thoughtfully, the case for local and self-hosted models, and why great docs in the future will need to work for machines as much as for humans.
Seventh episode of the AI & Docs podcast series is up! In this one, Tom, Larah Vasquez, and I talk about local LLMs and the shift away from API dependence, why AI output is bad by default, skills as a token-efficient alternative to stuffing everything into MCP servers, the memory problem in LLMs, and whether tech writers are quietly architecting themselves into a higher role — or out of one.
Sixth episode of the AI & Docs podcast series is up! In this one, Tom, Manny Silva, and I talk about documentation testing (the deterministic kind), skills files and why they matter, the ethical tension of externalizing your expertise, and the evolving role of tech writers as content curators. Or, if you prefer the romantic version, guardians of knowledge.
Fifth episode of the AI & Docs podcast series is up! In this one, Tom and I discuss our predictions for tech comm in 2026, the evolution of writers into automation engineers, the risk of the Reverse Centaur dynamic, and the growing value of authentic human connection.
Fourth episode of the AI & Docs podcast series is up! In this one, Tom and I chat with CT Smith about AI workflows, building tools that don’t depend on AI, the fear of skill atrophy, living intentionally offline, and why the line between developer and writer is starting to blur.
Third episode of the AI & Docs podcast series is up! In this episode, Tom and I talk about documentation theatre, benchmarks for AI, productivity metrics in the AI age, and much more.
I really enjoyed speaking at Write the Docs Berlin this year. My talk was a bit special, a message in a bottle for writers who are struggling — for anyone who’s struggling in their careers, really. Here are the recording and the slides, as well as some links to the content that inspired the talk. I hope you’ll find it useful.
Second episode of the AI & Docs podcast series is up! In this episode, Tom and I talk about MCP servers with Anandi Knuppel. As Anandi says, “wherever there are words with regards to a technical product, that’s the technical writer’s domain”. Don’t miss it!
Today I discussed how tech writers can use AI at work with Tom Johnson and Scott Abel. It all started from my post What’s wrong with AI-generated docs, though we didn’t just focus on the negatives; in fact, we ended up acknowledging that, while AI has limitations, it’s also the most powerful productivity tool at our disposal. Here are some of the things I said during the webinar, transcribed and edited for clarity.
I spoke at the betterCode() ArchDoc 2025 conference a couple of weeks ago about the Seven Action Documentation model. It was a very nice experience and I thank the organizers for inviting me and letting me post the video. Here is the full recording of the presentation (it’s about 40 minutes long):
I recently was a guest on The Stack Overflow’s Podcast today, talking about docs (of course), the Vale prose linter, job titles, automation, LLMs, and much more. You can listen to the entire episode here or in the SO blog, or read the transcript. Getting docs closer to developers was one of my personal goals this year, and I think these kind of appearances might help. We need to be where developers are.
Some months ago I wrote a post about open source docs contributions. My dear colleague Scott Abel (The Content Wrangler) found that to be a good topic for a webinar, so today I hosted Contributing to Open Source Documentation Projects, where I expanded my thoughts on the topic and provided some practical guidance. You can also download the slides here. Enjoy!
Last week I had the pleasure of conversing with Niklas Begley from Doctave. It was a follow-up to The Pros and Cons of Markdown, focused on why Markdown and other lightweight markup languages could benefit from some structure, in the DITA sense, but without going the XML way. Hint: There could be a bit of JSON schemas involved.
I had a cool chat with Tom Johnson (idratherbewriting.com) about AI and its impact on technical writing and documentation. Along the way, we also had the chance of discussing open source docs and the challenge of being a first-time contributor.
The programmatic equivalent of UX Writing is API Design. The words that you use to describe your API enable conversations between software and people - it’s just a bit more structured and mechanical. That’s why technical writers are uniquely suited to assist technical teams in doing API design, especially when an API First design approach is being followed.
A hands-on review of the most recent open source API documentation toolchains, such as ReDoc, Widdershins, and Elements, the newest solutions from Stoplight, among others. Get the slides here.