Your experience making sure AI products are ready for customers

Study type
1-on-1 Interview
Study format
Online
Compensation
$325 choice of dozens of digital gift cards
Session length
60 minutes
Description

We're looking to speak with senior AI, machine learning and product leaders who are responsible for how their organization tests and evaluates its AI products or features, and who have evaluated, used or built AI evaluation tools in the past 24 months. In a 60-minute video conversation, we'd like to understand:

Defining AI quality: how you decide an AI feature is accurate, safe and ready to release, and who signs off.
Evaluation approaches: how you weigh in-house evaluation, automated or LLM-as-judge tools, and human evaluation.
Risk and accountability: the incidents, regulations or executive pressures shaping how you test AI today.
Choosing a provider: what triggers a search for outside help, and the proof you need before selecting a provider.

There are no right or wrong answers. We're interested in your real experience.