Webinar | Deep dive | November 11

Agentic Development in BI – Choosing the Right Model

This is the second session in our webinar series on agentic development in BI. It focuses on the first building block: the model.

Sign up here
tabular-editor-portrait-ruben-and-eugene-1080x1080

Model choice is the most important decision you make when working with agents. Pick too weak a model and you get subtle errors. Pick the strongest one for everything and you get slow responses, higher costs, and over-engineered solutions.

This session is part of a webinar series based on our blog series on agentic development for BI. It follows the introductory session and expands on the article How to pick the right AI model for agentic development. Eugene Meidinger and Ruben Van de Voorde, Innovation Specialists, show how to match model, effort level, and host to the task in front of you.

In this session, you’ll learn:

  • How models differ in purpose, capabilities, behavior, speed, cost, and configuration
  • What effort level does, and why it affects both quality and cost
  • Which model and effort combinations suit typical BI tasks, from searching logs to planning an end-to-end project
  • When to use cloud-hosted models and when to run open-source models locally
  • How to combine models, for example by letting a stronger model review the work of another

More sessions will follow. Each one covers a building block of agentic development: model, context, prompt, tools, and environment.

Event Details

Date: Wednesday, November 11
Time: 15:00-16:00 (CET, UTC+1)
Host: Eugene Meidinger and Ruben Van de Voorde