The brand book didn't exist. The website had been writing one for years.
Three design systems reverse-engineered from live sites in one week. The trick isn't reading the theme settings — it's measuring what actually gets painted.
Topic
AI
A collection of 46 issues
Everything returned 200. Four leads still went nowhere.
Three things broke on my own projects this week and not one of them produced an error. Silent failures are the expensive kind — here is what I changed so the systems shout.
I planned a two-week content sprint. Ten minutes of querying killed it.
I was sure the site needed more pages. Ten minutes of querying the live system showed the pages were already there — and the real constraint was one level further back.
The AI slop nobody logs: the 20-page doc that makes its problem your problem.
There's a hidden tax on teams right now: polished AI output that shifts the thinking onto whoever opens it. The real skill was never volume. It's what you cut.
My assistant created the same task three days running. The fix has a name: idempotency.
A tiny automation bug taught the same lesson payment systems learned years ago: the question isn't whether it runs, it's what happens when it runs again.
Four versions of the same email sat in my drafts. This morning, the tool just edited one.
Claude's Gmail connector now updates drafts in place instead of duplicating them. A small fix — and exactly the kind that turns AI tooling from a demo into something you trust daily.
A context window is working memory, not a hard drive. Feel that, and you manage AI differently.
The AI doesn't remember everything you've told it. It has working memory, and it's finite — here's the cheap trick I use to hear it filling up, and the fix when it does.
The real test of a system is whether the work moves when you've left the desk.
A week away, not too many meetings, and the clients' work kept moving — because the mechanical parts run on their own. On building systems that outlast your presence, and the judgement that can't be automated.
I asked AI for my best quotes. It handed me things people told me in confidence.
I built a system to surface the best quotes from everything I'd saved. The best lines were things said to me in confidence — and the model couldn't tell. Why the boundary is judgement, not a smarter model.
The AI said my files were empty. Every byte was still there.
My phone-side AI reported a project's notes as empty and refused to save a spreadsheet. A desktop audit found zero data loss. The failure was confidence, not storage.