Orchestrating LLMs and Agents

Agents are changing and new frameworks to build them are emerging and evolving at a faster rate than ever before. This month we take a look at a variety of these frameworks and what you can build with them.

"Using DSPy with Gemini and Gemma" - Martin Andrews

Each brand of LLM needs to be prompted differently. DSPy is a framework for orchestrating LLM actions that also allows automatic optimisation of LLM prompts. Martin will outline what's going on, and show some examples using both proprietary and open source models.

"LLM Agents - B2C use cases & evaluation" - Praveen Govindaraj

Praveen will talk about the use cases of LLM Agents in B2C businesses such as improving customer experience and optimizing network operations in Telecom

"What Agentic Frameworks should you use to get results fast?" - Sam Witteveen

In this talk Sam will go through a tour of a number of the frameworks for building autonomous agents such as CrewAI, LangGraph and AutoGen, showing their strengths, weaknesses and some tricks and tips you can use to get better results from your agents.

***

Talks will start at 7:00 pm and end at 8:50pm or so, at which point people normally come up to the front for a bit of a chat with each other, and the speakers.

As always, we're actively looking for more speakers - both '30 minutes long-form', and lightning talks. For the lightning talks, we welcome folks to come and talk about something cool they've done with keras_core, TensorFlow, PyTorch, JAX and/or Deep Learning for 5-10mins (so, if you have slides, then #max=10). We believe that the key ingredient for the success of a Lightning Talk is simply the cool/interesting factor. It doesn't matter whether you're an expert or an enthusiastic beginner: Given the responses we have had to previous talks, we're sure there are lots of people who would be interested to hear what you've been playing with. If you're interested in talking, please just introduce yourself to Martin or Sam at one of the events.