
Build and evaluate a retrieval workflow
Description
About Build and Evaluate a Retrieval Workflow: Evidence Before Confidence
"Build and Evaluate a Retrieval Workflow: Evidence Before Confidence" is a live, interactive session hosted by AumOS, focused on building and evaluating a simple document retrieval workflow. This event is designed for an engineering audience and includes both hands-on participation and an observer option. Participants will enhance their skills by inspecting a retrieval workflow to determine if its responses are backed by provided documents.
The session provides a comprehensive 90-minute online experience featuring a worked example, exercises, discussion, and an opportunity for questions. It encourages engagement from a global audience, supporting community learning and collaboration in AI development. The event is open to all, with the online room link shared post-RSVP. Attendees are encouraged to bring questions, share experiences, and connect with fellow AI enthusiasts worldwide.
What Is It About?
Key Topics
• Building a retrieval workflow
• Evaluating evidence support in retrieval workflows
• Using public, synthetic, licensed, or authorized examples
What Can You Expect?
Participants can choose to engage in a hands-on experience or follow along as observers, gaining insights into retrieval workflows. The session includes a worked example and practical exercises where attendees will inspect and test workflow responses against document evidence. An evaluation worksheet is provided as a takeaway for further exploration. This interactive session allows for Q&A and sharing of relevant experiences, promoting a collaborative learning atmosphere.
Things to Consider Before Attending
This event is conducted live online, accessible to participants from anywhere in the world. It is free of charge, offering a flexible way to engage in AI community learning without the need for physical attendance. Basic knowledge of Python and Git is recommended for those opting for the hands-on path, although not mandatory for observers.
Let your network know you`re going
Share this event to start conversations, invite colleagues, and connect before it begins.











