Founder and CTO of Afros in AI, and a researcher and speaker on AI ethics, governance and responsibility.
Session
Workshop
Date
Monday, November 30
Level
Intermediate
// AI Engineering Skill /
Grounding models with data
// 01 / Bio
Nyah Macklin is Senior Developer Advocate for AI at Neo4j and a researcher and speaker on AI, ML, ethics, governance and responsibility. They are also the founder and CTO of Afros in AI, a technical community dedicated to showcasing the many sides of AI.
Outside of work, Nyah cares about empowering, teaching and tutoring engineers, live-streaming technical deep dives, and building open-source tools that make software more accessible, explainable and community-driven.
// 02 / The session
Find the wrong evidence before your users do
Abstract
Your agent just gave a customer the wrong refund decision and attached a real company policy to prove it. Now the customer has a screenshot. The passage matched the question. It came from a policy version that didn’t apply to that customer on that date.
In this hands-on workshop you’ll pull apart how that happened and repair it with the simplest approach that works. Then you’ll take on a harder case, where the answer depends on connections across customer, product and policy data. A small set of checks shows when the system has found applicable evidence, and when it should stop.
What you’ll learn
Why a retrieved passage can match the question and still be the wrong evidence
Fixing a retrieval failure with the simplest approach that works
Using connections across customer, product and policy data to find the right answer
Checks that tell an agent when to stop instead of answering
// 03 / Courses
Keep learning
Go deeper on what this session covers.
AI DEV · BY DEEPLEARNING.AI
Join us at AI Dev
Meet the engineers shipping AI to production, and leave ready to do it yourself.