AI agents operate in a continuous loop where the LLM generates tool calls as JSON, which are then executed and their results are fed back as the next prompt.
Model Context Protocol (MCP) provides a standard for agents to connect with external tools, benefiting both agent and tool developers by creating a unified ecosystem.
A demonstration shows the Goose AI agent using multiple MCP-enabled tools like Databricks and a file editor to query data and build a web dashboard.
Multi-agent systems use recursion, where a parent agent delegates tasks to sub-agents, primarily to manage and reduce the context window for improved performance and cost.
Google's Agent-to-Agent (A2A) protocol enables communication across different agents and organizations, with potential use cases in specialized tasks and front-end communication.
AI development is being shaped by protocols like the established MCP for tools and the emerging A2A for multi-agent systems, which will define future agent collaboration.
msg
Ismaning, Germany
25:32Viktoria Semaan
29:03Jörg Neumann
23:17Angie Jones
24:22Philipp Schmid
39:11Thomas Dohmke
23:33Oliver Will
30:38Alex Soto
25:14Ivan Burazin
Jobs that call for the skills explored in this talk.
United Software Group, Inc.
Alpharetta, United States of America
CommandLink
Collaboration Betters The World GmbH
Lockheed Martin
