Madrid AI Developers Group

AI Deep Dive (Virtual) - Building Self-Improving Agents

Wed, Jul 29 · 7:00 PM CEST

·

Online

Online

Important: Register on the event website to receive the joining link. (rsvp on meetup will NOT receive anything).

This is virtual event for our AI global community, please double-check your local time. Can't make it live? Register anyway to receive the webinar recording.

Join Snowflake to learn how to build self-improving agents

Tech Talk: Your Agent Should Fix Itself: Building Self-Improving Agents
Speaker: Elliot Botwick, Principal AI/ML Architect, Snowflake
Abstract: In this talk, we will share how coding agents help developers build high quality agents faster.
A key insight from building agents in production is that high quality agents operate with their goals, plans and actions aligned. We introduce the Agent Goal-Plan-Action (Agent GPA) framework to capture this insight, which achieved state of the art benchmarks on TRAIL/GAIA with 95% error coverage and 86% error localization.
The Agent GPA framework assesses the full agent's process:

• Was the goal achieved efficiently?
• Did the plan make sense?
• Were the right tools used?
• Did the agent follow through?

Without visibility into these steps, teams risk deploying agents that look reliable but create hidden costs in production. Inaccuracies can waste compute, inflate latency and lead to the wrong business decisions, all of which erode trust at scale.
We will show how to use coding agents to automate the process of measuring and improving your agent's GPA by using optimization skills that take advantage of the GPA evaluation framework. By the end, you’ll be able to use coding agents and the GPA framework to identify common agent failures, improve their agent and make it ready for production.

Venue:
Virtual, join from anywhere

More virtual sessions:

• July 22nd: AI Deep Dive with Google Ep1. RSVP
• July 29th: AI Deep Dive with Snowflake. RSVP
• Aug 5th: AI Deep Dive with Google Ep 2. RSVP
• Sep 2nd: AI Deep Dive with Google Ep 3. RSVP

Google AI Deep Dive (Ep 2)

Wed, Aug 5 · 7:00 PM CEST

·

Online

Online

Important: Register on the event website to receive the joining link. (rsvp on meetup will NOT receive anything).

This is virtual event for our AI global community, please double-check your local time. Can't make it live? Register anyway to receive the webinar recording.

The Google AI Deep Dive Series is a hands-on virtual initiative designed to empower developers to architect the next generation of Agentic AI. Moving beyond basic prompting, this series guides you through the complete engineering lifecycle using Google’s advanced stack.
You will master the transition from local Gemini CLI environments to building intelligent agents with the Agent Development Kit (ADK) and Model Context Protocol (MCP), culminating in the deployment of secure, collaborative Agent-to-Agent (A2A) ecosystems on Google Cloud Run. Join us to build AI systems that can truly reason, act, and scale.

Tech Talk: Wrangling unstructured data with LLM-driven vector embedding
Speaker: Annie Wang (Google)
Abstract: ADK 2.0, Google's Agent Development Kit, fixes this with three orchestration patterns: graph workflows, collaborative agents, and dynamic workflows. In this hands-on webinar, you'll watch all three run live inside a single app, then build them yourself, step by step, in a Colab lab. We'll cover when each pattern fits, how ADK 2.0 turns hidden control flow into visible, testable structure, and the one question that tells you which pattern to reach for. You'll leave with working code and a decision tree you can apply to your own agents the next day.

Venue:
Virtual, join from anywhere

More virtual sessions:

• Aug 11th: Google Agents in Production for Enterprises (Virtual) - Ep 1. RSVP
• Aug 20th: NVIDIA Flare Webinar Q3. RSVP
• Aug 25th: Google Agent in a Day Workshop (#2). RSVP
• Sep 2nd: AI Deep Dive with Google Ep 3. RSVP