DEV Community

AI Evals Series' Articles

Back to Sara Mo's Series
How Do You Build an Evaluation Harness for AI Agents?
Cover image for How Do You Build an Evaluation Harness for AI Agents?

Real traffic over imagination for test cases
sara_mo profile

How Do You Build an Evaluation Harness for AI Agents?

#ai #agents #testing #machinelearning
8
Comments 24
3 min read
What Are AI Evals, and Who Should Own Them?
Cover image for What Are AI Evals, and Who Should Own Them?
sara_mo profile

What Are AI Evals, and Who Should Own Them?

#ai #agents #testing #machinelearning
6
Comments 12
3 min read
Did the Model Upgrade Break Your AI Agent?
Cover image for Did the Model Upgrade Break Your AI Agent?

How silent behavioral shifts break passing tests
sara_mo profile

Did the Model Upgrade Break Your AI Agent?

#ai #machinelearning #llm #programming
16
Comments 18
3 min read
Your AI Eval Has a Blind Spot. You Built It.
Cover image for Your AI Eval Has a Blind Spot. You Built It.
sara_mo profile

Your AI Eval Has a Blind Spot. You Built It.

#ai #programming #llm #testing
5
Comments 4
3 min read
How Do You Build Your First Eval Set for an Agent?
Cover image for How Do You Build Your First Eval Set for an Agent?
sara_mo profile

How Do You Build Your First Eval Set for an Agent?

#ai #programming #machinelearning #testing
3
Comments 3
3 min read
Who Gets to Say the Agent Behaved Correctly?
Cover image for Who Gets to Say the Agent Behaved Correctly?
sara_mo profile

Who Gets to Say the Agent Behaved Correctly?

#ai #agents #testing #webdev
4
Comments
5 min read
QA Isn’t AI Evaluation
Cover image for QA Isn’t AI Evaluation
sara_mo profile

QA Isn’t AI Evaluation

#agents #ai #testing #llm
2
Comments
3 min read