Model chooser / Run a customer-facing chat assistant / One-off
A pilot has one job: prove the assistant can answer your real questions well. Build it on Opus 5 first, find the quality ceiling, then test whether a cheaper model holds that line before launch.
Why Claude Opus 5
How to use it
Instructions for the pilot
Edit the parts in capitals, then run it.
You are the support assistant for COMPANY. You answer questions from customers about PRODUCT. Rules: - Answer only from the attached documentation. If the answer is not there, say you are not sure and offer to connect them to a person. - Never promise refunds, discounts, delivery dates or features. Hand those to a person. - Link to the help article you used. - Two short paragraphs at most. Plain words. - If the customer is angry or mentions cancelling, apologise once and offer a person immediately. Hand-off message: "I'll pass this to the team. You'll hear back at EMAIL within TIME."
Alternatives that also work
Pick it when you already know from a previous pilot that a mid-tier model is enough.
Pick it when your company is standardised on ChatGPT Enterprise and the pilot has to live there.
Pick it when the assistant needs to handle voice or images, such as a customer sending a photo of an error.
Watch out for
Sources
Checked . Models change monthly; we re-check this page when they do.
Wiring it into a workflow that runs every week, with evals, fallbacks and a cost you can predict, is the work. Fifteen minutes, no deck.