Whether you're using a chatbot or something more sophisticated, the same fundamentals determine whether AI succeeds or fails. This session walks through three key principles in plain language: evals, tracing and context. We'll use live demos and real-world NFP examples throughout, so no technical background is needed. You'll leave knowing how to set AI up so it works in your team's hands, and what to check when it doesn't.
このウェビナーでは次のようなトピックを扱います:
Understand what evals, tracing and context mean in practice, and why they determine whether AI succeeds or fails.
Identify the most common reasons AI systems underperform in real-world team settings.
Apply a simple framework to assess and improve the reliability of AI tools already in use at your organisation.
Vivek is Executive Director and Co-founder at Good Data Institute. He is passionate about building data products that create positive change. GDI helps charities build data capabilities, supporting over 70 organisations on more than 80 projects globally. In his spare time, Vivek loves to jam on data science, ML and ethics. He's recently spoken at YOW!, PyCon, LAST, and Tech 4 Social Justice, and Vivek also holds a PhD in Optimisation via Quantum Computing.