Which model gets which job, and what that costs.
Every task an agent takes on can run on a frontier model. Most shouldn’t. The ladder I run sends each task to the cheapest lane that fits, and a checklist keeps me from reaching for the expensive model out of habit.
Fable is the most expensive model I can run, and the worst thing I can do with it is let it type. kaibot runs Fable as an orchestrator that plans, delegates to Opus and Sonnet, reviews, and exits, and that discipline is built into the harness so it survives every session, not just the ones where somebody remembers.
“What are some nice things people are doing with Fable anyway? I have access but I can’t think of anything Fable-worthy, Opus just works fine for me.” Friend, I am using the shit out of Fable, Opus, and Sonnet right now. The split, and a pile of ideas to steal.
Three Max subscriptions. How to see them, swap them, add a client’s token, and pin a project so a client’s burn lands on the right account, automatically.
Keeping a busy agent from breaking things.
I run five, sometimes ten, Claude Code sessions against the same kaibot repo at once. Left alone, that setup silently loses data. One worktree per session, a merge-back discipline and guard hooks make collisions physically impossible instead of just against the rules.
Every “ALWAYS” and “NEVER” in your CLAUDE.md is a rule you’re hoping the model remembers. I turn those hopes into hooks my model can’t forget, and you can prompt your own Claude to do the same for you.
My agent runs shell commands all day: it greps logs, calls APIs, writes code. Everything it reads gets echoed into a transcript, and everything it types gets logged. That’s a bad place to keep a real credential. So I set kaibot up so the agent resolves what it needs at runtime and never once holds the value in a place it could print.
Somebody ships a clever skills repo, a sharp blog post, a tool with one great idea inside it. I want the idea, not the dependency. I pull the 2-3 patterns worth taking, and run the safety gates first, because a cloned repo can attack your agent without ever executing a line of code.
How the system finds out it was wrong.
A model reviewing its own work has blind spots that match its own training. I run every change that would be expensive to get wrong past a panel of rival vendors instead, because the disagreement between labs is a signal one reviewer can never produce on itself.
The tool I lean on hardest, and the one thing I recommend to everyone: fan a change out to rival models before you trust it. Two pieces, because the code and the doctrine go stale at completely different speeds.
Out of the box, AI writes the worst tests you can imagine. I feed my coding agents these rules before they write a line, distilled from ten conference talks and months of getting burned. Point your agent at this page.
A prompt you paste into Claude Code, or any agent with a shell and a browser, from the root of your app’s repo. It photographs every page on real data, writes down the design rules your app is already following, and hands you back one page you can actually read.
LLM prose has a recognizable sound: importance without specifics, drama without content, cleverness performed for an audience. I use a taxonomy to strip that sound out of writing (mine and my Claude’s) without stripping the writer, and you can give your Claude the same discipline.
What it keeps, and what it learns from.
Most memory setups for Claude are one file that grows forever, until nothing in it stands out and nobody trusts it. The doctrine kaibot runs instead: one fact per file, a capped index, and a scorer that decides what’s worth remembering today.
A great conference talk evaporates the moment you close the tab. The pipeline I run turns a YouTube lecture into two durable things: upgrades to a skill my Claude actually uses, and a searchable corpus entry, with the transcript filed under the exact slide that was on screen when each sentence was said.
Work that carries on after I walk away.
A friend told me he can’t get a self-driving loop going that produces work he’s happy with, so he’s still driving every step by hand. The loop he’s missing isn’t smarter than his. It’s dumber. Mine makes zero decisions while it runs, and that’s the whole trick.
You bring the job in one paragraph. It brings back branches with the receipts attached. Nothing touches main until you type the one command that does.
Keep a Claude Code session going from the iPhone while you walk the dog. The app is Moshi, the desk command is walk, and the office Mac does the actual work. I stopped using Moshi in October 2026; this is the setup as it ran.
Side projects, and one I haven’t written yet.
I’m rebuilding the overworld map from the 1997 game Shandalar. The entire art problem fits in one sentence: take a grid of square tiles and make it read as a single hand-painted map. The pile of tricks that get you there, from a friend who spent a long time in the weeds so you don’t have to. I’ve since moved the overworld to pixel-art tilesets; this is what the painterly route taught me.
“Hey here is a screenshot of wasted ink in the terminal output, can you send this to <agent> and have them fix it?” Software in the future is magical. Most of the future is shit, but this part, pointing at agentic software development, is freaking amazing.
$400 1 hour
Book a callA paid one-on-one call with answers to your questions about using AI for projects, building your AI stack, or growing your business with AI. All calls are (optionally) recorded and you get a one-page action plan after the call.