Madrid AI Developers Group

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

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.

Description:
Welcome to the weekly AI Deep Dive Webinar Series. Join us for deep dive tech talks on AI, hands-on experiences on code labs, workshops, and networking with speakers & fellow developers from all over the world.

Tech Talk: Evaluating AI Agent Reliability
Speaker: Anupam Datta (Snowflake) | Josh Reini (Snowflake)
Abstract: Agents often fail in ways you can’t see. They could return a final answer while taking a broken path: drifting from the goal, making irrational plan jumps, or misusing tools. Was the goal achieved efficiently? Did the plan make sense? Were the right tools used? Did the agent follow through?
These hidden mistakes silently rack up compute costs, spike latency, and cause brittle behavior that collapses in production. Traditional evals won’t flag any of it because they only check the output, not the decisions that produced it.
This session introduces the Agent GPA (Goal-Plan-Action) framework, available in the open-source TruLens library. Benchmark tests show the Agent GPA framework consistently outperformed standard LLM evaluators, giving teams scalable and trustworthy insight into agent behavior

• 95% error detection (vs. 55% baseline methods)
• 86% accuracy in pinpointing where an error occurred (vs. 49% baseline methods)
• Human reviewers using the GPA framework caught 100% of the internal agent errors in the TRAIL/GAIA dataset.

You’ll learn how to inspect an agent’s reasoning steps, detect issues like hallucinations, bad tool calls, and missed actions, and leave knowing how to make your agent truly production-ready.

Speakers/Topics:
Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

More upcoming sessions:

• Jan 15th: AI Deep Dive Webinar Series (Virtual)
• Jan 7th: AI Meetup (Virtual) - Agent Systems and LLM Compression Deep Dive

Local and Global AI Community on Discord
Join us on discord for local and global AI tech community:

• Events chat: chat and connect with speakers and global and local attendees;
• Learning AI: events, learning materials, study groups;
• Startups: innovation, projects collaborations, founders/co-founders;
• Jobs and Careers: job openings, post resumes, hiring managers

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

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.

Description:
Welcome to the weekly AI Deep Dive Webinar Series. Join us for deep dive tech talks on AI, hands-on experiences on code labs, workshops, and networking with speakers & fellow developers from all over the world.

Talk 1: Federated Learning Made Easy: NVIDIA FLARE's Simplified API Stack
Abstract: NVIDIA FLARE makes federated learning more accessible through three APIs that simplify the developer experience—from adapting existing training code, to building full FL jobs, to experimenting with new algorithms.
In this talk, we'll demonstrate how these three APIs work together to transform the federated learning development experience through live examples, showing how barriers to entry have been eliminated for practitioners, data scientists, and researchers alike.

Speaker: Holger Roth (NVIDIA)

Talk 2: Building and Deploying Federated Agents Across Multicloud and Edge AI
Abstract: As AI systems evolve from single models into coordinated collections of autonomous agents, centralized architectures increasingly fail to meet real-world requirements around data locality, regulatory compliance, latency, and heterogeneous infrastructure. This technical, demo-driven webinar presents a practical blueprint for building and operating federated AI agents across public cloud, private infrastructure, and edge environments using the Rhino Federated Computing Platform and NVIDIA GPU-accelerated technologies. Through a live end-to-end demonstration, attendees will see how policy-driven agent placement, secure coordination, local LLM-powered data harmonization, federated cohort construction, and data quality validation can be executed without centralized data movement.
The session focuses on concrete implementation patterns, operational considerations, and architectural tradeoffs, equipping ML engineers, platform teams, and AI architects with actionable guidance for deploying federated agent systems in production.
Speaker: Adrish Sannyasi (Rhino Federated Computing Platform)

Speakers/Topics:
Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

More upcoming sessions:

• Jan 15th: AI Deep Dive Series (Virtual) - Building AI Agents From Prototype to Production
• Jan 21st: AI Deep Dive Series (Virtual) - Evaluating AI Agent Reliability
• Jan 29th: AI Deep Dive Series (Virtual) - Agent Memory for Building Robust, Accurate Agents

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

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.

Description:
Welcome to the weekly AI Deep Dive Webinar Series. Join us for deep dive tech talks on AI, hands-on experiences on code labs, workshops, and networking with speakers & fellow developers from all over the world.

Tech Talk: RAG is Dead. Long Live Agent Memory
Speaker: Chris Latimer (Vectorize)
Abstract: RAG solved a problem: how to ground LLMs in in external knowledge. This was useful for basic chatbots. But in a world where we want autonomous agents to solve business problems, RAG fundamentally doesn't fit.

Agent memory systems are emerging as the new standard in AI architectures to solve problems like inconsistency, context rot, and hallucinations.
In this talk, we'll identify the root causes of these problems and explain how agent memory allows you to build robust, accurate agents that learn over time. We'll do a deep dive into Hindsight, an open source agent memory system that achieves state of the accuracy on benchmarks and in production. We'll see how Hindsight uses biomimetic data structures to produce agent memory that works more like human memory - and how you can use these capabilities to deliver agents you can trust in production.

Speakers/Topics:
Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

More upcoming sessions:

• Jan 21: AI Deep Dive Series (Virtual) - Evaluating AI Agent Reliability
• Jan 22: NVIDIA FLARE Webinar 1 - End-to-End Federated AI

Local and Global AI Community on Discord
Join us on discord for local and global AI tech community:

• Events chat: chat and connect with speakers and global and local attendees;
• Learning AI: events, learning materials, study groups;
• Startups: innovation, projects collaborations, founders/co-founders;
• Jobs and Careers: job openings, post resumes, hiring managers