Inside Shopify's AI strategy with CTO Mikhail Parakhin
Source
youtube.com
Author
Claude
Date
Why it matters
Shows how a large engineering org handles tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → budgets and model choice, including giving every engineer unlimited tokens. Useful for teams deciding how to allocate inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → spend.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
