jev-playground Read the article View on GitHub

See it work

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.

Customer conversations

3 simulations

Messages arriving from people who want something, and the question of who — or what — should deal with each one.

Sales and orders

2 simulations

The front of the business: an enquiry that might be worth a quarter’s revenue, and an order that arrived as six unpunctuated words.

Money and paperwork

2 simulations

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.

Around the models you already run

3 simulations

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.

The shape they all share

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.