# Building eval sets that survive model swaps — AI Engineer workshop

Source: [AI Engineer](https://www.youtube.com/watch?v=ai-eng-evals-2026)  
Feed7 permalink: https://feed7.dev/p/evals-workshop-aie  
Published: 2026-06-21T00:00:00.000Z  
Trust: Transcript Verified (transcript_verified)

## Why Included

Eval sets usually die when you change models. This workshop shows how to write ones that transfer.

## Source Summary

Behavior-anchored evals: assert on user-visible outcomes, not model phrasing. Includes a template repo and a live migration from GPT to Claude.

## Practical Implication

Rewrite phrasing-based assertions as outcome assertions now — before your next model swap forces it.

## Agent-Ready Context

Write evals against user-visible outcomes, not model phrasing. Outcome-anchored evals survive model swaps. Template: given/when/then on behavior, never on wording.

## Context Map

- Layer: benchmark
- Domains: coding
- Topics: agent-evals, model-selection

## Uncertainty

- None recorded.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.