From Agentic AI to Multi-AI Networks

Agentic AI, unlike traditional AI systems, focuses on creating AI agents that can operate autonomously, making decisions and taking actions to achieve goals. The future of agentic AI lies in the development of “multi-ai networks.” This concept moves beyond the limitations of individual AI agents, each specializing in a single task, towards a system where multiple AI agents collaborate and work together like a team.

Imagine a network of specialized AI agents, each with unique capabilities. For example, an AI agent skilled in legal research could provide information to a separate agent specializing in contract drafting, leading to the efficient completion of a legal task. While the sources primarily focus on the development of this concept by Personal AI, this “multi-ai network” represents a potential future for the entire field of agentic AI. This approach aims to mimic human collaboration and teamwork, offering a compelling vision of how AI can evolve to tackle increasingly complex challenges.

Mastering RAG and Fine-Tuning in LLMs

Join Jennifer Cwagenberg at the 11th CTO Colloquium for an in-depth exploration of retrieval-augmented generation (RAG) and fine-tuning large language models (LLMs). Jennifer will share insights on lessons learned in the different strategies for populating vector databases, selecting embedding models, context length optimization, and evaluating model inferencing pipelines.

We will dive into the security concerns of fine-tuning LLMs, using public models, as well as implementing guardrails.