New Workshop & Session Added to Monday Programming
Monday, March 17 will be a day filled with workshops, Tech Talks and Ignite Talks at the Carolina Theatre.
And now, it’s getting even better.
We’ve added a brand new afternoon workshop in Cinema 2 starting at 1:00 pm ET, as well as an hour-long session that will follow it.
Check out both sessions below, and move quickly to register if interested!
Note:
1. There is no cost to attend these sessions on Monday – they are free.
2. Separate registration is required in Eventbrite. Simply scroll down until you see the IBM Monday workshop option.
3. Only registration to the IBM 1:00 pm workshop is required. That registration gets you access to the Adrian Cole – Testing GenAI Applications session that follows. Both take place in Cinema 2 back-to-back.
4. Registration to the IBM workshop is limited to just 50 people due to space/room limitations. Please move quickly if interested.
5. For those that move quickly and successfully register, check in onsite on Monday will start at 12 noon ET. That provides up to an hour for checking in, locating Cinema 2, settling in, etc.

1:00 PM ET in Cinema 2
Cooking with Granite : Granite AI Models
The Granite family of foundation models span an increasing variety of modalities, including language, code, time series, and vision – with much more to come. This workshop will introduce the Granite model family and then you will work through several Granite recipes to get some hands-on experience using Granite models to address some AI use cases. Prerequisites for this workshop are either 1) a device with Python 3.11 and Jupyter Notebook installed, or 2) a device with a browser and GitHub and Google accounts.
Presenter: BJ Hargrave, Senior Technical Staff Member, IBM Research

3:30 PM in Cinema 2 (this session follows the IBM session)
Testing GenAI Applications
Software engineers are increasingly using Generative AI to build applications like chatbots, content generation tools and even agents. Testing can be tricky, especially if against a billable account. It gets even trickier when you want your application to perform reliably.
As OpenAI is the lingua franca, we’ll detail how its SDK gives developers reach beyond GPT, including Llama and DeepSeek, due to platform emulation and tools like Ollama. We’ll get into the trickiness of paid accounts and unpredictability of chat responses, and which techniques OpenTelemetry tests use to mitigate them. Finally, review some challenges higher up the stack in AI Assistants and Agents, such as tool hallucinations. We’ll briefly cover practice around quality, including evaluations.
You’ll leave with an overview of challenges GenAI developers encounter, and a few places to start bullet-proofing your codebase.
Presenter: Adrian Cole, Principal Software Engineer, Elastic