---
title: "Evaluation & Deployment"
description: "A fine-tuned router returns cleaner JSON. Check the category inside it is right, find requests that got worse, and test the exact artifact you will serve."
canonical_url: "https://fanout.sh/ai/lessons/fine-tuning-evaluation"
md_url: "https://fanout.sh/ai/lessons/fine-tuning-evaluation.md"
access: "pro-preview"
---

# Evaluation & Deployment

A fine-tuned router returns cleaner JSON. Check the category inside it is right, find requests that got worse, and test the exact artifact you will serve.

- Access: Fanout Pro (public preview)
- Module: How to Fine-Tune Models

## A glimpse of Evaluation & Deployment

Your fine-tuned support router returns cleaner JSON than the original model. That is useful, but it leaves two questions: is the category inside the JSON correct, and did any kind of request get worse?

We will inspect six saved responses. The required output is a JSON object with exactly one key, queue, whose value is billing, delivery or account.

## Continue learning

Pro unlocks guided learning, complete notes, practical walkthroughs, exercises, and every AI Research lesson.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md