Evals 101

Writing evals is a core skill for making AI products that actually work. Evals are our "definition of what good looks like". They are both harder than they seem to get right, and at the same time not rocket science at all - anyone can learn to write evals.

Start watching for free

Free episodes available immediately. Full access with a 15-day free trial.

1. Let's write some evals

1.1
Evals intro: set up your accounts

This is what we came for: some hands-on eval writing.

Premium
3:37
1.2
An introduction to evals

What are evals, why do we need them, and why isn't this just QA?

Premium
11:11
1.3
Let's write an eval together

This is the fun part, hands-on writing evals together.

Premium
13:53
1.4
Eval Tips and Common Mistakes

Evals can be tricky, and it's easy to make some very expensive (in terms of quality, end result and cost) mistakes.

Premium
7:12
1.5
Creating Data Sets

There are no evals without data sets. How do we create solid data sets? How many data points are enough? What about synthetic data?

Premium
8:12
1.5
How we define what Good looks like

One reason evals are tricky, is that it can be hard to define what Good looks like when working (as we are) in a team.

Premium

What participants say

"This training has provided valuable insights into AI product development methodologies and practical implementation strategies."

— Course Participant

"Highly relevant for our enterprise software organization as we scale AI feature evaluation processes."

— Course Participant

"The evaluation framework training has been instrumental in establishing our AI quality processes."

— Course Participant

Ready to get started?

15-day free trial. Cancel any time.

Start your free trial