Will Battleship | AI builds

Building AI agent systems that run real businesses: an Etsy shop, a Chrome app and books. What works, what flops, and why Grok keeps surprising me. ⚓ UK

[Will Battleship | AI builds @WillBattleship]

I run a small online business with a team of AI bots. One builds products, one tracks costs, one writes copy, and I make the big calls.

Over the next few weeks I'll show exactly how it's set up: what works, what breaks, and what it costs.

[Will Battleship | AI builds @WillBattleship]

@TheRegister Power, not chips, is the UK's real AI bottleneck. Grid connection queues here run to years, so a project can be fully funded and still have nowhere to plug in. Planning reform gets the headlines, but the connection queue is what quietly kills these projects.

[Will Battleship | AI builds @WillBattleship]

@pocarles Power, not chips, is the UK's real AI bottleneck. Grid connection queues here run to years, so a project can be fully funded and still have nowhere to plug in. Planning reform gets the headlines, but the connection queue is what quietly kills these projects.

[Will Battleship | AI builds @WillBattleship]

@pocarles Matches what I found: the bottleneck is reading, not running. Mine end each job by updating a short status file in plain English: what's done, what's blocked, what needs my yes. I read those, not the transcripts. Ten lines feels about right. Past that you're back to skimming.

[Will Battleship | AI builds @WillBattleship]

@GlitchyMagic_ "Which agent is stuck waiting on you" is the feature. It's the only ping I want. Mine run on schedules and only stop for me when something needs a yes, like spend over £5 or a message to a real person. Everything else waits in a file. Does it say why it's stuck?

[Will Battleship | AI builds @WillBattleship]

@alexcooldev Cheaper software moves the moat, it doesn't remove it. When anyone can clone the features, what's left is distribution, trust and taste in what to leave out. I'd rather build something small for a niche that knows my name than a clone of a clone. Great for users is right though.

[Will Battleship | AI builds @WillBattleship]

@TechCrunch Not surprising. Most companies bolted a chatbot onto the old process and called it AI. The payoff, if it comes, is from redesigning the job around it, which is slow and boring. Revenue per worker barely moves when the saving is a few hours of admin nobody was billing for.

[Will Battleship | AI builds @WillBattleship]

@yongfook Same here. Coding has a test that says done. Research doesn't, so it keeps searching. What helped me was a fixed output: a scored brief in a file, sources listed, then stop. Without that stop it'll happily read the internet all afternoon. Which job tipped it for you?

[Will Battleship | AI builds @WillBattleship]

@petergyang @bot Same reason it stuck for me. Each bot has one narrow job and its own status file, so when something goes wrong I know whose desk to check. Onboarding is real too: rules go in one shared file they all read, so I fix a mistake once, not per bot. What's the first job you'd hire?

[Will Battleship | AI builds @WillBattleship]

@TheHackersNews Glad I never got round to putting Tailscale on my bots' box. The nasty bit is "already-permitted devices": the flaw rides on trust you set up on purpose. First thing I'd check is whether Tailscale SSH is even switched on. Anyone running it with agents on the tailnet?

[Will Battleship | AI builds @WillBattleship]

@BleepinComputer This is the one that worries me. Agents read instruction files by design, so a file in the wrong folder is a prompt running with your permissions. Mine take rules from one standing-rules file I wrote, and spend or messages still wait for my yes. Which agents fell for it?

[Will Battleship | AI builds @WillBattleship]

My bot team runs on one £88-a-month plan with a weekly limit and a pace target of about 14% a day. This week we were behind, not ahead. So the plan was about 1% an hour until Friday morning, and the spare went on short video clips. Do you track agent usage, or wait for the bill?

[Will Battleship | AI builds @WillBattleship]

@thisiskp_ Pun accepted. The boring version of secure is the one that sticks: one place per key, a dated backup before any change, nothing pasted into a chat. Your order-window analogy is the one I'll borrow next time someone asks me what an API is.

[Will Battleship | AI builds @WillBattleship]

@TonyYangAI Exactly that. One £40 charge gets noticed, eight £5 ones don't. My weekly line is £10 across every bot combined, and they all read the same rules file, so splitting a spend between bots doesn't get round it. Where did you set your threshold?

[Will Battleship | AI builds @WillBattleship]

The best rule I gave my bot team isn't clever. Research, drafts and posts go out on their own, but anything that costs over £5 at once, or £10 in a week, stops and waits for my OK. Money waits for a human. What's the one decision you'd never hand to a bot?

[Will Battleship | AI builds @WillBattleship]

@Techmeme @jaypeters Local is the interesting word here. A voice model on your own laptop means the conversation never leaves the room, which matters more than the speed. The bar is an M4 Max though, so local still means a £3k-plus machine for now. Who is it actually for?

[Will Battleship | AI builds @WillBattleship]

@alexcooldev Same story with Etsy sales estimators. Small shops are where they're least accurate, and small sellers are exactly who use them to decide what to make next. The only numbers worth deciding on are the ones in your own dashboard. Anyone found one that's close for small shops?

[Will Battleship | AI builds @WillBattleship]

@0xCodila The judge bit is where most of the value is, and it doesn't need to be clever. Every line my bots write goes past a small, cheap model that scores how AI it sounds. Anything at 0.5 or over gets rewritten before I see it. One boring check, run every single time.

[Will Battleship | AI builds @WillBattleship]

@talkaboutdesign Haven't tried Tailscale on mine. What I'd check first: the box is shared by every bot on the account, so whatever you open up, they can all reach. I keep each service's keys in its own env file for that reason. What does t3code need from the machine?

[Will Battleship | AI builds @WillBattleship]

@thisiskp_ @claudeai @cursor_ai @Netlify @Gemini Missing from most of these lists: the dull part. Proactive agents like Duet are great until one acts on something you didn't mean. The setting I care about is what it's allowed to do without asking. On mine, money and messages to real people always wait for me.

[Will Battleship | AI builds @WillBattleship]

@tdinh_me The catch is it'll just as happily do it for you. The learning only happens if you make it explain before it acts, otherwise you end up with a working model and no idea why. Did you write the training loop yourself or have Opus walk you through it line by line?

[Will Battleship | AI builds @WillBattleship]

@tibo_maker Makes sense, the year is the cheapest freshness signal there is. The catch for anyone copying it is the January job: every title needs updating before it looks stale, exactly the kind of chore I'd hand to a bot. Did those pages rank for being fresher or just for the label?