Ten small simulations of the same idea: a fast, cheap AI makes the small judgements, your code makes the decisions, and the expensive AI is only called when it is genuinely needed. No AI is actually called — these are animations of the patterns, with made-up but realistic numbers. Every page links to the Python it is built from.
Messages arriving from people who want something, and the question of who — or what — should deal with each one.
A thousand customer messages arrive. Most of them never need an expensive AI model — but something has to work out which ones do.
One mailbox, three people half-watching it, and a purchase enquiry buried under four recruiters. Sorted before anyone opens it.
A chatbot wrote a reply to a customer. Did it invent a number? Promise something? Actually answer? Check before it sends.
The front of the business: an enquiry that might be worth a quarter’s revenue, and an order that arrived as six unpunctuated words.
Someone submits a form. Rate them on four things and route them before the page finishes loading. Drag the sliders to change what matters.
For a lot of businesses the ordering system is a phone number. Jev judges what the message is; a regex reads the number. Neither does the other’s job.
The back-office grind — the work that is boring, constant, and expensive to get wrong. This is where a calibrated confidence number earns its keep.
Invoice or statement? Paid already? Does it match something we actually ordered? Your open orders go into the same call as the document.
Eight hundred bank lines, and the only number that matters is whether the model knows which ones it is unsure about. Watch the accuracy move with the floor.
Patterns that sit in front of, behind, or between frontier models — screening what they read, checking what they do, and deciding which one gets the job.
Search returned ten documents. One is irrelevant, one is trying to hijack the answer. Screen them before the expensive model reads a word.
An AI agent keeps asking to run commands. Check every one for four separate hazards, in less time than the command itself takes.
You pay for several AI models of different speeds and prices. Send each request to the cheapest one that can actually do the job.
1. Your code gathers exactly the information the question needs. 2. Jev answers every question about it at once, and says how sure it is. 3. Your code decides what happens — the thresholds are numbers you can read, test and revert. 4. An expensive model is called only for the part that genuinely needs one.
Each simulation matches the runnable Python in
cookbooks/, linked from the top of every page. The numbers shown are illustrative,
not measured.