PubMed is a free search interface for biomedical literature, including citations and abstracts from many life science scientific journals. It is maintained by the National Library of Medicine at the NIH. Yet, most users only interact with it through simple keyword searches. In this hands-on tutorial, we will introduce PubMed as a data source for intelligent biomedical research assistants — and build a Health Research AI Agent using modern agentic AI frameworks such as LangChain, LangGraph, and Model Context Protocol (MCP) with minimum hardware requirements and no key tokens. To ensure compatibility, the agent will run in a Docker container which will host all necessary elements.

Participants will learn how to connect language models to structured biomedical knowledge, design context-aware queries, and containerize the entire system using Docker for maximum portability. By the end, attendees will have a working prototype that can read and reason over PubMed abstracts, summarize findings according to a semantic similarity engine, and assist with literature exploration — all running locally on modest hardware.

Expected Audience: Enthusiasts, researchers, and data scientists interested in AI agents, biomedical text mining, or practical LLM integration. Prior Knowledge: Python and Docker familiarity; no biomedical background required. Minimum Hardware Requirements: 8GB RAM (+16GB recommended), 30GB disk space, Docker pre-installed. MacOS, Windows, Linux. Key Takeaway: How to build a lightweight, reproducible research agent that combines open biomedical data with modern agentic AI frameworks.

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

This is virtual event for our global community, please double check your local time. Can't make it live? Register anyway! We'll send you a recording of the webinar after the event.

Description: The 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.

All Sessions: Dec 4th, Dec 11th, Dec 13th, Dec 18th and Dec 20th.

Session 1 (Dec 4th) - Get started with Gemini 3.0 using AI Studio Speaker: Arun KG (Staff Customer Engineer, GenAI, Google) Abstract: This session is your fast track to deploying next-generation AI applications using Gemini 3.0 and Google AI Studio.

You will learn the new 'vibe coding' workflow to rapidly prototype full-stack web apps from natural language and instantly deploy them to a production-ready Cloud Run endpoint. Master the seamless integration that takes you from a simple prompt to a secure, scalable, and fully managed serverless service in minutes, fundamentally changing your development cycle. Gemini 3, AI Studio Cloud Run

All attendees will get $5 cloud credits

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

This is virtual event for our global community, please double check your local time. Can't make it live? Register anyway! We'll send you a recording of the webinar after the event.

Description: The 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.

All Sessions: Dec 4th, Dec 11th, Dec 13th, Dec 18th and Dec 20th.

Session 1 (Dec 4th) - Get started with Gemini 3.0 using AI Studio Speaker: Arun KG (Staff Customer Engineer, GenAI, Google) Abstract: This session is your fast track to deploying next-generation AI applications using Gemini 3.0 and Google AI Studio.

You will learn the new 'vibe coding' workflow to rapidly prototype full-stack web apps from natural language and instantly deploy them to a production-ready Cloud Run endpoint. Master the seamless integration that takes you from a simple prompt to a secure, scalable, and fully managed serverless service in minutes, fundamentally changing your development cycle. Gemini 3, AI Studio Cloud Run

All attendees will get $5 cloud credits

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

This is virtual event for our global community, please double check your local time. Can't make it live? Register anyway! We'll send you a recording of the webinar after the event.

Description: The 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.

All Sessions: Dec 4th, Dec 11th, Dec 13th, Dec 18th and Dec 20th.

Session 1 (Dec 4th) - Get started with Gemini 3.0 using AI Studio Speaker: Arun KG (Staff Customer Engineer, GenAI, Google) Abstract: This session is your fast track to deploying next-generation AI applications using Gemini 3.0 and Google AI Studio.

You will learn the new 'vibe coding' workflow to rapidly prototype full-stack web apps from natural language and instantly deploy them to a production-ready Cloud Run endpoint. Master the seamless integration that takes you from a simple prompt to a secure, scalable, and fully managed serverless service in minutes, fundamentally changing your development cycle. Gemini 3, AI Studio Cloud Run

All attendees will get $5 cloud credits

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

This is virtual event for our global community, please double check your local time. Can't make it live? Register anyway! We'll send you a recording of the webinar after the event.

Description: The 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.

All Sessions: Dec 4th, Dec 11th, Dec 13th, Dec 18th and Dec 20th.

Session 1 (Dec 4th) - Get started with Gemini 3.0 using AI Studio Speaker: Arun KG (Staff Customer Engineer, GenAI, Google) Abstract: This session is your fast track to deploying next-generation AI applications using Gemini 3.0 and Google AI Studio.

You will learn the new 'vibe coding' workflow to rapidly prototype full-stack web apps from natural language and instantly deploy them to a production-ready Cloud Run endpoint. Master the seamless integration that takes you from a simple prompt to a secure, scalable, and fully managed serverless service in minutes, fundamentally changing your development cycle. Gemini 3, AI Studio Cloud Run

All attendees will get $5 cloud credits

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

This is virtual event for our global community, please double check your local time. Can't make it live? Register anyway! We'll send you a recording of the webinar after the event.

Description: The 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.

All Sessions: Dec 4th, Dec 11th, Dec 13th, Dec 18th and Dec 20th.

Session 1 (Dec 4th) - Get started with Gemini 3.0 using AI Studio Speaker: Arun KG (Staff Customer Engineer, GenAI, Google) Abstract: This session is your fast track to deploying next-generation AI applications using Gemini 3.0 and Google AI Studio.

You will learn the new 'vibe coding' workflow to rapidly prototype full-stack web apps from natural language and instantly deploy them to a production-ready Cloud Run endpoint. Master the seamless integration that takes you from a simple prompt to a secure, scalable, and fully managed serverless service in minutes, fundamentally changing your development cycle. Gemini 3, AI Studio Cloud Run

All attendees will get $5 cloud credits

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

This is virtual event for our global community, please double check your local time. Can't make it live? Register anyway! We'll send you a recording of the webinar after the event.

Description: The 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.

All Sessions: Dec 4th, Dec 11th, Dec 13th, Dec 18th and Dec 20th.

Session 1 (Dec 4th) - Get started with Gemini 3.0 using AI Studio Speaker: Arun KG (Staff Customer Engineer, GenAI, Google) Abstract: This session is your fast track to deploying next-generation AI applications using Gemini 3.0 and Google AI Studio.

You will learn the new 'vibe coding' workflow to rapidly prototype full-stack web apps from natural language and instantly deploy them to a production-ready Cloud Run endpoint. Master the seamless integration that takes you from a simple prompt to a secure, scalable, and fully managed serverless service in minutes, fundamentally changing your development cycle. Gemini 3, AI Studio Cloud Run

All attendees will get $5 cloud credits

Unlock AI agent potential with this advanced session on scaling tools using Amazon Bedrock AgentCore Gateway. Learn to build and manage secure, production-ready agent tool environments. We'll cover multi-tenant architecture, deployment strategies, and integration patterns for agentic tools. Explore zero-code MCP tool creation with intelligent tool discovery. Gain insights on security controls, monitoring, and performance optimization for enterprise-scale agent tool ecosystems.

Learn more: More AWS events: https://go.aws/3kss9CP

Subscribe: More AWS videos: http://bit.ly/2O3zS75 More AWS events videos: http://bit.ly/316g9t4

ABOUT AWS: Amazon Web Services (AWS) hosts events, both online and in-person, bringing the cloud computing community together to connect, collaborate, and learn from AWS experts. AWS is the world's most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers—including the fastest-growing startups, largest enterprises, and leading government agencies—are using AWS to lower costs, become more agile, and innovate faster.

AWSreInvent #AWSreInvent2025 #AWS

Discover how to leverage AI Foundry and MongoDB to enable the next generation of intelligent, data-driven, context-aware agents. This session demonstrates how AI Foundry’s agentic workflow integrates with MongoDB’s MCP Server to deliver secure, contextual, and scalable access to enterprise data. Through a demo of an industry use case, see how a complex business process is utterly simplified by intelligent agents — showcasing a practical path from integration to innovation.

Living on Washington State’s peninsula offers endless beauty, nature, and commuting challenges. In this talk, I’ll share how I built an agentic AI system that creates and compares optimal routes to the mainland, factoring in ferry schedules, costs, driving distances, and live traffic. Originally a testbed for the Model Context Protocol (MCP) framework, this project now manages my travel schedule, generates expense estimates, and sends timely notifications for events. I’ll give a comprehensive overview of MCP, show how to quickly turn ideas into working agentic AI, and discuss practical integration with real-world APIs. Attendees will leave with actionable insights and a roadmap for building their own agentic AI solutions.

Agentic AI Protocols: Coordinating the Future of Autonomous Systems

As autonomous agents become more capable, coordinating their interactions with tools and with each other has become a critical challenge. In this session, we’ll introduce the emerging landscape of Agentic AI protocols — with a focus on MCP (Model Context Protocol), A2A (Agent-to-Agent Protocol), and ACP (Agent Communication Protocol). These AI protocols are laying the foundation for interoperability, scalability, and real-world adoption of agentic AI. We’ll begin with an overview of the multi-agent coordination challenge — why multiple agents require shared standards for communication, negotiation, and orchestration. Then we’ll explore how MCP, developed by Anthropic, provides a “USB-C for AI” that enables seamless integration with thousands of external tools. Building on this, we’ll look at A2A for direct agent-to-agent coordination and ACP for creating a common messaging language between heterogeneous agents. You’ll also see a live demo of Zapier’s MCP integration, showing how an AI agent can trigger multi-step workflows across 7,000+ apps — extended with a multi-agent scenario to illustrate how protocols complement each other in practice. Finally, we’ll compare MCP, A2A, and ACP, and discuss strategies for designing scalable, standards-based agent systems.

What We Will Cover:

• Understand the multi-agent coordination challenge and why protocols are needed
• Learn how MCP, A2A, and ACP address different aspects of agent interoperability
• See a live demo of Zapier’s MCP integration with an extended multi-agent workflow
• Explore design strategies for orchestrating multiple agents, including retries, delegation, and error handling
• Compare MCP vs. A2A vs. ACP — when to use each and how they work together
• Discover practical applications and future directions for Agentic AI protocols

Hands on Exercise:

Through live demos and audience Q&A, participants will gain hands-on insights into MCP-powered automation and explore how emerging protocols like A2A and ACP extend agent capabilities for real-world, multi-agent systems.

Agentic AI Protocols: Coordinating the Future of Autonomous Systems

As autonomous agents become more capable, coordinating their interactions with tools and with each other has become a critical challenge. In this session, we’ll introduce the emerging landscape of Agentic AI protocols — with a focus on MCP (Model Context Protocol), A2A (Agent-to-Agent Protocol), and ACP (Agent Communication Protocol). These AI protocols are laying the foundation for interoperability, scalability, and real-world adoption of agentic AI. We’ll begin with an overview of the multi-agent coordination challenge — why multiple agents require shared standards for communication, negotiation, and orchestration. Then we’ll explore how MCP, developed by Anthropic, provides a “USB-C for AI” that enables seamless integration with thousands of external tools. Building on this, we’ll look at A2A for direct agent-to-agent coordination and ACP for creating a common messaging language between heterogeneous agents. You’ll also see a live demo of Zapier’s MCP integration, showing how an AI agent can trigger multi-step workflows across 7,000+ apps — extended with a multi-agent scenario to illustrate how protocols complement each other in practice. Finally, we’ll compare MCP, A2A, and ACP, and discuss strategies for designing scalable, standards-based agent systems.

What We Will Cover:

• Understand the multi-agent coordination challenge and why protocols are needed
• Learn how MCP, A2A, and ACP address different aspects of agent interoperability
• See a live demo of Zapier’s MCP integration with an extended multi-agent workflow
• Explore design strategies for orchestrating multiple agents, including retries, delegation, and error handling
• Compare MCP vs. A2A vs. ACP — when to use each and how they work together
• Discover practical applications and future directions for Agentic AI protocols

Hands on Exercise:

Through live demos and audience Q&A, participants will gain hands-on insights into MCP-powered automation and explore how emerging protocols like A2A and ACP extend agent capabilities for real-world, multi-agent systems.

Agentic AI Protocols: Coordinating the Future of Autonomous Systems

As autonomous agents become more capable, coordinating their interactions with tools and with each other has become a critical challenge. In this session, we’ll introduce the emerging landscape of Agentic AI protocols — with a focus on MCP (Model Context Protocol), A2A (Agent-to-Agent Protocol), and ACP (Agent Communication Protocol). These AI protocols are laying the foundation for interoperability, scalability, and real-world adoption of agentic AI. We’ll begin with an overview of the multi-agent coordination challenge — why multiple agents require shared standards for communication, negotiation, and orchestration. Then we’ll explore how MCP, developed by Anthropic, provides a “USB-C for AI” that enables seamless integration with thousands of external tools. Building on this, we’ll look at A2A for direct agent-to-agent coordination and ACP for creating a common messaging language between heterogeneous agents. You’ll also see a live demo of Zapier’s MCP integration, showing how an AI agent can trigger multi-step workflows across 7,000+ apps — extended with a multi-agent scenario to illustrate how protocols complement each other in practice. Finally, we’ll compare MCP, A2A, and ACP, and discuss strategies for designing scalable, standards-based agent systems.

What We Will Cover:

• Understand the multi-agent coordination challenge and why protocols are needed
• Learn how MCP, A2A, and ACP address different aspects of agent interoperability
• See a live demo of Zapier’s MCP integration with an extended multi-agent workflow
• Explore design strategies for orchestrating multiple agents, including retries, delegation, and error handling
• Compare MCP vs. A2A vs. ACP — when to use each and how they work together
• Discover practical applications and future directions for Agentic AI protocols

Hands on Exercise:

Through live demos and audience Q&A, participants will gain hands-on insights into MCP-powered automation and explore how emerging protocols like A2A and ACP extend agent capabilities for real-world, multi-agent systems.

Overview of the AI Gateway pattern as a central control plane for enterprise AI ecosystems, including API abstraction, failover, semantic caching, centralized guardrails, and cost controls. Discuss practical architectural patterns for high-availability gateways that handle thousands of concurrent requests with sub-millisecond in-memory decision-making, separation of control and data planes, asynchronous logging, horizontal scaling, and future MCP integration for tool ecosystems and natural language automation across enterprise software.

As AI agents become more autonomous and capable, integration becomes a key challenge. In this session, we’ll introduce Agentic AI and how MCP (Model Context Protocol) — an open standard developed by Anthropic — is transforming the way agents connect with external tools. Think of MCP as the “USB-C for AI” that enables seamless, no-code integration between agents and thousands of applications.

We’ll walk through how Zapier’s support for MCP integration allows AI agents to trigger over 35,000 actions across 7,000+ apps — without needing any manual API integration. From sending emails to updating spreadsheets and triggering webhooks, agents can now perform complete workflows end-to-end through MCP-integrated automation.

You’ll see a live demo of how an AI agent connects to a Zapier-generated MCP server URL and executes automated tasks — no code required. We’ll also explore practical agent design strategies for real-world implementation, from orchestrating actions and assigning roles to handling retries and errors at scale.

What We Will Cover:

• Understand what Agentic AI is and how MCP integration enables scalable, real-time integrations with external tools
• Learn how Zapier’s MCP feature works and how it empowers agents to perform thousands of actions across major platforms
• See a live demo of an AI agent triggering a multi-step workflow via a Zapier MCP integration endpoint — with no manual API calls
• Explore design strategies for agent orchestration: retries, error handling, and modular role assignments
• Discover how to build and deploy intelligent, automated workflows using MCP integration — and apply these patterns to your own projects
• Interactive Element: Through live demos and audience Q&A, participants will gain hands-on insights into agent-based automation powered by MCP integration, and leave with a scalable framework they can begin applying immediately.

As AI agents become more autonomous and capable, integration becomes a key challenge. In this session, we’ll introduce Agentic AI and how MCP (Model Context Protocol) — an open standard developed by Anthropic — is transforming the way agents connect with external tools. Think of MCP as the “USB-C for AI” that enables seamless, no-code integration between agents and thousands of applications.

We’ll walk through how Zapier’s support for MCP integration allows AI agents to trigger over 35,000 actions across 7,000+ apps — without needing any manual API integration. From sending emails to updating spreadsheets and triggering webhooks, agents can now perform complete workflows end-to-end through MCP-integrated automation.

You’ll see a live demo of how an AI agent connects to a Zapier-generated MCP server URL and executes automated tasks — no code required. We’ll also explore practical agent design strategies for real-world implementation, from orchestrating actions and assigning roles to handling retries and errors at scale.

What We Will Cover:

• Understand what Agentic AI is and how MCP integration enables scalable, real-time integrations with external tools
• Learn how Zapier’s MCP feature works and how it empowers agents to perform thousands of actions across major platforms
• See a live demo of an AI agent triggering a multi-step workflow via a Zapier MCP integration endpoint — with no manual API calls
• Explore design strategies for agent orchestration: retries, error handling, and modular role assignments
• Discover how to build and deploy intelligent, automated workflows using MCP integration — and apply these patterns to your own projects
• Interactive Element: Through live demos and audience Q&A, participants will gain hands-on insights into agent-based automation powered by MCP integration, and leave with a scalable framework they can begin applying immediately.

As AI agents become more autonomous and capable, integration becomes a key challenge. In this session, we’ll introduce Agentic AI and how MCP (Model Context Protocol) — an open standard developed by Anthropic — is transforming the way agents connect with external tools. Think of MCP as the “USB-C for AI” that enables seamless, no-code integration between agents and thousands of applications.

We’ll walk through how Zapier’s support for MCP integration allows AI agents to trigger over 35,000 actions across 7,000+ apps — without needing any manual API integration. From sending emails to updating spreadsheets and triggering webhooks, agents can now perform complete workflows end-to-end through MCP-integrated automation.

You’ll see a live demo of how an AI agent connects to a Zapier-generated MCP server URL and executes automated tasks — no code required. We’ll also explore practical agent design strategies for real-world implementation, from orchestrating actions and assigning roles to handling retries and errors at scale.

What We Will Cover:

• Understand what Agentic AI is and how MCP integration enables scalable, real-time integrations with external tools
• Learn how Zapier’s MCP feature works and how it empowers agents to perform thousands of actions across major platforms
• See a live demo of an AI agent triggering a multi-step workflow via a Zapier MCP integration endpoint — with no manual API calls
• Explore design strategies for agent orchestration: retries, error handling, and modular role assignments
• Discover how to build and deploy intelligent, automated workflows using MCP integration — and apply these patterns to your own projects
• Interactive Element: Through live demos and audience Q&A, participants will gain hands-on insights into agent-based automation powered by MCP integration, and leave with a scalable framework they can begin applying immediately.

LLMs are powerful but limited—they operate as isolated systems and struggle with complex, multi-step tasks or integration with enterprise data sources.

The Model Context Protocol (MCP) addresses these gaps by providing a standard way to orchestrate multiple AI agents, models, and tools. MCP enables agents to collaborate, share context, and access structured data, which is essential for advanced analytics.

DataSpaces offers a secure, governed environment for sharing and analyzing data across organizations.

Integrating MCP with DataSpaces allows AI agents to access enterprise data securely, automate analytics workflows, and deliver more actionable insights. This combination extends the capabilities of LLMs, making advanced data analytics more flexible, interoperable, and enterprise-ready.

Speaker: Matthias Buchhorn-Roth Matthias is a data and AI solutions architect with experience in Cloud Computing, Dataspaces. He is worked closely with Microsoft technologies, including Azure-based data solutions. Currently his focus is on building scalable, user-centric and Agentic AI systems along user journeys and new technologies like Model Context Protocol.

Join via Teams: https://teams.microsoft.com/l/meetup-join/19%3ameeting_MjU2NjQyNzQtYjAyNC00ZjRlLWJkMWQtZDA1NjAzYWJlZTRk%40thread.v2/0?context=%7b%22Tid%22%3a%2240dee412-4d0f-42cf-8aad-aa22f61f4948%22%2c%22Oid%22%3a%222d576807-9b4e-4f34-9bfd-2fc5fd7c1c6a%22%7d

¡Únete a nosotros para el quinto Meetup oficial de PyData Málaga en Google!

The PyData community in Malaga continues with engaging talks, insightful lightning sessions, and lively networking. A massive thank you to our generous hosts, Google Sec Malaga for supplying the venue and Saavedra Grupo for the pizzas!

Sign up to be a future speaker here: https://bit.ly/pydata-malaga-speaker

AGENDA:

• 🚪 6:00 pm - Apertura de puertas / Doors open
• 🕡 6:30 pm - Comienzo de las charlas (¡puntuales!) / Talks commence (sharp!)

📚 Charlas principales / Main 25-min talks:

1. Developing an Agentic Framework Utilizing the Model Context Protocol (MCP) - Moïse Goma
2. Modern Defenses Against Misinformation Through RAG Poisoning Attacks - Alex Santangelo

📚 Charlas relámpago de 5 minutos / 5-minute lightning talks:

1. TBD

TALKS / CHARLAS

• Developing an Agentic Framework Utilizing the Model Context Protocol (MCP) - Moïse Goma

In this talk, Moïse Goma will delve into the development of an agentic framework leveraging the Model Context Protocol (MCP). Agentic AI refers to autonomous systems capable of making decisions and performing tasks without human intervention, enhancing efficiency and adaptability across various domains. The Model Context Protocol is an open standard that enables seamless integration between large language model (LLM) applications and external data sources and tools. By employing MCP, developers can build secure, two-way connections between their data sources and AI-powered tools, streamlining the integration process and enhancing the capabilities of AI agents. This session will explore the architecture of MCP, its practical applications, and how it facilitates the creation of robust agentic frameworks.

• Modern Defenses Against Misinformation Through RAG Poisoning Attacks - Alex Santangelo

In this talk, Alex Santangelo will explore contemporary strategies to counteract misinformation by focusing on Retrieval-Augmented Generation (RAG) poisoning attacks. RAG systems enhance large language models by integrating external knowledge sources, improving the factual accuracy of AI-generated content. However, they are vulnerable to adversarial poisoning attacks, where attackers inject malicious or misleading data into the knowledge databases that RAG systems rely on. This manipulation can cause the AI to generate incorrect, biased, or harmful outputs. Santangelo will delve into the mechanisms of RAG poisoning, discussing how attackers can influence retrieval systems by poisoning the data corpus used for retrieval. He will also present modern defense mechanisms designed to detect and mitigate such attacks, ensuring the integrity and reliability of AI-generated information. The session aims to equip attendees with a comprehensive understanding of the threats posed by RAG poisoning and the strategies to defend against misinformation in AI systems.

📢 Anuncios de la comunidad / Community announcements 🤝 Networking relajado con cervezas y refrescos / Relaxed networking over beers and soft drinks

¿Interesado en compartir tus conocimientos o experiencia en este o un futuro evento? Pregunta a Frank, Anna o Hugo, nuestros co-organizadores voluntarios. / Interested in sharing your knowledge or experience at this or a future event? Ask Frank, Anna or Hugo, our volunteer co-organisers, or sign up here: https://bit.ly/pydata-malaga-speaker ¡Esperamos verte allí para una fantástica tarde de Python, Ciencia de Datos y camaradería! / We look forward to seeing you there for a fantastic evening of Python, Data Science, and camaraderie!

🕖 LOGISTICS Talks kick off at 18:30 sharp; then networking in TBD bar from 20:40. If you can't make it, please un-RSVP in good time to free up your place for your fellow community members. Follow us on meetup.com for updates on this and future events, as well as news from the global PyData community.

📜 CODE OF CONDUCT The PyData Code of Conduct governs this meetup (https://pydata.org/code-of-conduct/). To discuss any issues or concerns relating to the code of conduct or behaviour of anyone at the PyData meetup, please contact the PyData Malaga organisers, or you can submit a report of any potential Code of Conduct violation directly to NumFOCUS (https://numfocus.typeform.com/to/ynjGdT).