Vertex-Ai

Agent Development Kit (ADK) is an open source agent development framework built by Google. In this talk we are going to see how to leverage Vertex AI to make production-ready agents that include features like memory, session management, artifact management, RAG and others. The session will walk you through the development of an “Executive Assistant” agent that will learn not only about your tasks, but your preferences. Even if you have never built an agent before, in this talk you will learn how to quickly ramp up using Gemini CLI, the developer knowledge MCP and codewiki, for a truly modern agent development experience.

Inspired by the "computer" in Star Trek, in this talk we are going to create a natural language diagnostic agent that can answer questions about your computer, from asking the number of cores and amount of memory installed to running a "Level 1 Diagnostic Procedure".

This talk demonstrates how to build an AI agent step-by-step using Python, Vertex AI, Gemini, and Osquery. It explores how Osquery, a tool for exposing OS information via SQL, can be leveraged by large language models to enable advanced diagnostics through natural language queries, eliminating the need to memorize complex command lines.