CloudFixies mascot logo CloudFixies.
← All articles
AI Agents

Evaluating an agent before shipping

A 100-example eval set beats a demo, every time. Here’s how we build one.

Published by CloudFixies · 09 December 2025

The eval set

Fifty real user requests. Twenty edge cases (missing data, permission denied, ambiguous phrasing). Twenty adversarial prompts. Ten cases where the correct answer is "I can’t help with that."

The score

Not a single number. A dashboard: correctness, tool-call accuracy, refusal rate on adversarial, latency p95. Regress on every one before shipping.

◆ Takeaway

A hundred labelled examples, four scores. Ship when all four hold.

← When not to use an agent The real cost of an agent in production →