All Posts

In a way, writing this article feels like the old saying "cutting off one's nose to spite one's face." Complete documentation automation certainly feels like (another trite old saying) "another nail in the coffin." Hmmm, are there any other trite sayings that are appropriate? Oh, yeah, it may be "a blessing in disguise." But is full automation a replacement for an experienced documentarian? The article in question is from Sleekplan, and it describes using Claude Skills, Claud

One of the biggest blockers to keeping documentation (and AI responses) current is the myth of the rewrite. You don’t need to overhaul the whole help center. You just need to update the one thing that changed. Every release cycle, I see it: A new feature launches Release notes get drafted But the linked help doc… isn’t touched And the AI agent? Still trained on last month’s truth What if you treated each help article as its own data asset? Change a feature, update one doc, an

Like a lot of people who've been using generative AI seriously, I found it both genuinely useful and genuinely maddening. The frustrations are familiar if you've been there: running out of conversation space mid-project. Watching a long working session get progressively more confused as it tried to hold too many threads. Starting a new chat and realizing the AI had no memory of the three weeks of context I'd worked on. For something marketed as a collaborator, it had a remark

Amalgamation - originally came from Latin meaning to mix mercury with another metal. Later it became a word meaning combining different things into one. What does that have to do with product documentation? Because in most tech companies, help and documentation consists of a number of different systems that don’t mix. Eye-level view of a tech workspace with a laptop and notes Amalgamation - originally came from Latin meaning to mix mercury with another metal. Later it beca

A fast way to measure trust in your help system is brutally simple: take one common question and count how many versions of the answer exist across your surfaces. If you get five, you don’t have “coverage”; you have confusion. Customers hesitate. Your AI bot tries to average contradictions. Teams fix one copy and miss the others. The result is slower time-to-value and preventable tickets. This pattern usually appears for good reasons. Support writes an FAQ to stop an escalat