Notes from building an AI design collaborator · part 12
Our documentation updates itself, because updating it is the AI's job
· 3 min read
Every team doc I've ever seen dies the same death. Someone writes it in a burst of good intentions, it's accurate for about three weeks, and then reality moves and the doc doesn't. Six months later nobody trusts it, so nobody reads it, so nobody updates it, and now it's just a confidently wrong artifact taking up space.
The reason is boring and universal. Keeping docs current is nobody's actual job. It's the thing you do after the real work, which means it's the thing you never do.
So I made it the AI's job
While building the AI design workflow, I ended up keeping a running wiki of how the whole thing was designed. Not the user docs, the thinking. Why we chose this over that. What we tried that didn't work. The decisions, with their reasons attached.
And instead of writing it myself and watching it rot, I made keeping it current a step in the work. After any significant effort, a decision made, a thing built, a problem solved, the AI updates the wiki as part of finishing. New page if the topic is new, edit the existing page if it isn't, a dated line in a running log, flag anything that now contradicts something older.
The trick that makes it not rot is that the update isn't a separate task you remember to do. It's the last move of the task you were already doing. Maintenance stops being a chore after the work and becomes the tail end of the work.
What it's actually good for
The obvious payoff is that the docs stay true. The one I didn't expect is what it does to memory across sessions. When I come back weeks later and ask "wait, why did we do it this way," the answer is written down, with the alternatives we rejected and why. I'm not reconstructing my own reasoning from scratch, which is the tax I complained about in an earlier post, just aimed at myself.
There are rules to keep it from bloating, because an AI that loves writing will happily turn your wiki into a swamp. Update before you create. One page per topic. Status is present tense, history goes in the log. Without those it grows into something as useless as the stale doc, just longer.
Docs don't die because writing them is hard. They die because updating them is homework nobody's assigned. Assign it. Make "update the record" the final step of the thing that changed the record, and hand that step to the one participant that never gets bored of doing it. The doc stays alive because staying alive is now built into how the work ends.
Part of a series on building an AI collaborator for our design team at Xflow. Each post stands on its own.
- ai
- documentation
The rest of Notes from building an AI design collaborator
- 1. I stopped describing my product to AI. I just gave it the HTML.
- 2. I gave the AI my design process, not my design decisions
- 3. I turned my design process into a dozen small skills, not one giant prompt
- 4. I built a free tool that gives your AI your real product
- 5. I taught the AI to push designs into Figma. Then it quietly stopped.
- 6. We rebuilt our Figma design system out of the code, not the other way round
- 7. We ran our design process on itself, and it broke in useful ways
- 8. How do you teach an AI your taste?
- 9. It worked great on the smart model. Then I ran it on a cheaper one.
- 10. The AI told me our brand colour with total confidence, and it was wrong
- 11. A screen list lies. I found a whole feature I didn't know we shipped.
- 13. I sat down to turn my workflow into a swarm of agents. Most of it refused.
- 14. Every modal in our app shared one URL. Our analytics couldn't tell them apart.
- 15. My AI's rules only worked because one tool bothered to read them
- 16. Six designers, one GitHub account, and a script that saves us from ourselves
- 17. "Out of scope" usually means "we'll repaint this in six months"