For a hands-on learning experience to develop Agentic AI applications, join our Agentic AI Bootcamp today. Early Bird Discount

Future of Data and AI

Agentic AI Conference

Virtual conference

9AM – 3PM PDT | April 6 – 10, 2026

Made possible by

Our speakers, partners, and community sponsors

Meet the speakers

Join us as leading world-class thought leaders, CEOs and AI researchers take the stage to share what’s next in agentic systems.

alex

Alex Salazar

Founder and CEO | Arcade.dev
Reena Agarwal Atlassian Agentic AI Conference

Reena Agarwal

VP, Engineering | Atlassian
Joshua Starmer | StatQuest | Future of Data and AI | Agentic AI

Bob Van Luijt

Founder and CEO | Weaviate
Philip Rathle

Philip Rathle

Chief Technology Officer | Neo4j
Tushar Jain Agentic AI Conference

Tushar Jain

EVP, Engineering | Docker
Kartik Talamadupula Oracle Agentic AI Conference

Kartik Talamadupula

Distinguished Architect | Oracle
Raja Iqbal Ejento AI Agentic AI Conference

Raja Iqbal

Founder | Ejento AI
Michael Irwin Docker Agentic AI conference

Michael Irwin

Principal Engineer | Docker
Andrea Kropp

Andrea Kropp

Applied AI Engineer | Landing AI
Ankit Khare LandingAI Agentic AI Conference

Ankit Khare

Go-To Market Lead | Landing AI
Mahdi

Mahdi Ghodsi

AI Solution Architect | AMD
Eda Zhou

Eda Zhou

Software Engineer | AMD
Chris McCormick

Chris McCormick

Ai Researcher | InnerWorkings.AI
Kwasi Ankomeh

Kwasi Ankomeh

Director, AI Solutions | SambaNova
Muazma Zahid | Future of Data and AI Speaker

Muazma Zahid

Group Product Leader | Google
Paige Bailey Agentic AI Conference

Paige Bailey

AI DevRel Lead | Google Deepmind
Varun Badrinath Krishna

Varun Krishna

Sr. Principal Engineer | SambaNova
Kayla Cinnamon Agentic AI Conference

Kayla Cinnamon

Sr. Developer Advocate | Microsoft
Scott-Askinosie-weaviate

Scott Askinosie

Developer Advocate | Contextual AI
shir

Shir Meir Lador

AI Leader | Google
Jeff Boudier Agentic AI Conference

Jeff Boudier

Product Growth | Hugging Face
Nav Bhasin Agentic AI Conference

Nav Bhasin

Head of Gen AI | AWS
Ramesh Vemu

Ramesh Vemu

Product Growth | EDM

Conference Agenda

Governing Autonomy

Policy, Control, and Accountability in Agentic AI Systems

As agentic AI systems gain the ability to reason, act, and collaborate across tools and environments, governance can no longer be an afterthought. This panel unifies architectural control mechanisms, human-in-the-loop oversight, regulatory accountability, interoperability standards, alignment frameworks, and adversarial resilience into a cohesive governance strategy. Experts will explore how enterprises can scale autonomy responsibly—through auditability, compliance readiness, protocol standardization, and robust safety design—before regulatory enforcement or operational failure forces reactive redesigns. 

From Hype to Durable Value

The Economics and Enterprise Reality of Agentic AI

Agentic AI sits at the intersection of hype, capital intensity, and organizational redesign. This panel unifies the economic debate around bubbles vs. durable transformation with the operational realities of stalled deployments, unclear ROI, and brittle architectures. Leaders will examine why projects collapse, what separates sustainable value from speculative momentum, and how to design productive human–agent collaboration models that enhance performance rather than degrade it. A strategic discussion for executives deciding where autonomy truly creates long-term enterprise advantages.

Securing Autonomous Agents

Threat Models, Zero-Trust Architectures, and the New Attack Surface

Agentic AI systems dramatically expand the security surface — persistent memory, tool execution, API integrations, and multi-agent coordination introduce entirely new attack vectors. This panel unifies emerging threat models, from prompt injection and memory poisoning to privilege escalation and adversarial manipulation, into a cohesive security strategy. Experts will debate whether today’s safeguards are sufficient and explore practical mitigation patterns including sandboxing, scoped identities, policy enforcement layers, red-teaming, and zero-trust architectures built specifically for autonomous systems. 

Technical Debt In Agentic AI Deployments

Autonomy, Stochastic Behavior, and Rapidly Evolving Frameworks

This panel will explore the emerging operational realities of deploying agentic AI at scale. Experts will discuss how technical debt accumulates across agent orchestration, evaluation frameworks, safety layers, and human oversight mechanisms. The conversation will highlight architectural patterns, governance strategies, and engineering practices that can help organizations manage this debt before it undermines reliability, security, and business value. The goal is to provide a practical perspective on building sustainable, production-grade agentic AI systems.

Agentic Document Extraction at Scale

Building a Self-Improving Pipeline with Multi-Agent Orchestration

This session walks developers through a production-grade document extraction architecture that doesn’t just process; it learns. Using LandingAI’s Agentic Document Extraction API and modern multi-agent frameworks, you’ll see how to build a pipeline that measures its own accuracy, identifies failures, and refines itself automatically across high volumes, multi-page layouts, and edge cases.

In this session, you’ll learn to:

  • Design an end-to-end extraction pipeline from raw documents to structured outputs with automated routing, evaluation, and feedback loops built in.
  • Build systems that measure accuracy against benchmark datasets, identify failure points, and drive targeted improvements using evidence instead of guesswork.
Future of Data and AI: Agentic AI Conference | Data Science Dojo

Andrea Kropp

Applied AI Engineer

Future of Data and AI: Agentic AI Conference | Data Science Dojo

GitHub Copilot everywhere​

Real Workflows Across CLI, VS Code, and the Cloud

This session takes a practical look at how GitHub Copilot fits into the modern development workflow across tools you already use. From the CLI to VS Code to cloud environments, you’ll see how Copilot supports real development tasks end to end, and where each interface adds value or creates friction. Through a live build, this session highlights how context shifts across tools and what that means for productivity.

In this session, you’ll learn to:

  • Use GitHub Copilot effectively across CLI, IDE, and cloud environments to build features end to end with a smooth, connected workflow.
  • Recognize where context breaks down between tools and apply practical patterns to switch surfaces without slowing down your development process.
Kayla Cinnamon Agentic AI Conference

Kayla Cinnamon

Senior AI Developer Tools Advocate

Microsoft | Future of Data and AI | Data Science Dojo

How Docker Is Building the Guardrails AI Coders Need

Securing AI Coding Agents with Docker Sandboxes and the MCP Toolkit

This session shows developers how to secure AI coding agents that bypass sandboxes, leak credentials, and delete filesystems. Using Docker Sandboxes and the MCP Toolkit, you’ll explore real attack scenarios and the guardrails Docker is building to give agents full power with safety.

In this session, you’ll learn to:

  • Identify and block common agent vulnerabilities, including sandbox bypasses, API token leaks, and prompt injections.
  • Use Docker Sandboxes and the MCP Toolkit to add guardrails and observability to agentic workflows.
Future of Data and AI: Agentic AI Conference | Data Science Dojo

Michael Irwin

Principal Software Engineer

docker agentic ai conference

AI Agent on AMD GPUs

Building Agentic Frameworks and Local LLM Deployment with AMD

This workshop shows developers how to build a personal AI agent from the ground up; without recurring API costs or third-party dependencies. Using open-weight models hosted on AMD GPUs and agentic frameworks like OpenClaw, you’ll learn to assemble a tool-using agent that’s customizable, private, and built for real workflows.

In this session, you’ll learn to:

  • Host and run open-weight LLMs on AMD GPUs to reduce API costs and maintain full control over your stack.
  • Build a tool-using AI agent using modern agentic frameworks, ready for production workflows.
Future of Data and AI: Agentic AI Conference | Data Science Dojo

Mahdi Ghodsi

AI Solution Architect

Future of Data and AI: Agentic AI Conference | Data Science Dojo

Eda Zhou

Software Development Engineer

Future of Data and AI: Agentic AI Conference | Data Science Dojo

Solving Agentic AI’s Infrastructure Crisis

Powering Agentic Inference with SambaNova

This hands-on lab shows how to move from single-agent setups to fully distributed systems. You will design and deploy a scalable multi-agent architecture using Google ADK, the A2A protocol, and Cloud Run, simulating real production workflows.

In this tutorial, attendees will:

  • Build and orchestrate specialized agents using Google ADK and A2A protocols
  • Deploy a scalable multi-agent system on Cloud Run with production-ready architecture
Future of Data and AI: Agentic AI Conference | Data Science Dojo

Kwasi Ankomeh

Director, AI Solutions

Future of Data and AI: Agentic AI Conference | Data Science Dojo

Building Distributed Multi-Agent Systems

Designing Scalable Architectures with Google ADK and Cloud Run

This hands-on lab shows how to move from single-agent setups to fully distributed systems. You will design and deploy a scalable multi-agent architecture using Google ADK, the A2A protocol, and Cloud Run, simulating real production workflows.

In this tutorial, attendees will:

In this session, you’ll learn to:

  • Build and orchestrate specialized agents using Google ADK and the Agent-to-Agent (A2A) protocol to enable structured, autonomous feedback loops
  • Deploy a fully functional, scalable multi-agent system on Google Cloud Run for production-ready distributed architectures
Future of Data and AI: Agentic AI Conference | Data Science Dojo

Shir Meir Lador

AI Leader

Future of Data and AI: Agentic AI Conference | Data Science Dojo

Antigravity and AI Studio with the Gemini APIs​

Building a Self-Improving Pipeline with Multi-Agent Orchestration

This session shows developers how to go from idea to production faster using Google AI Studio and the Gemini APIs. You’ll explore how Gemini’s multimodal capabilities and developer tooling remove the friction from building intelligent applications; so you can focus on what you’re creating, not the infrastructure underneath. 

In this session, you’ll learn to: 

  • Build and prototype AI-powered applications using Google AI Studio and the Gemini API suite.  
  • Leverage multimodal inputs, long context, and Gemini’s latest features to accelerate development workflows. 
Paige Bailey Agentic AI Conference

Paige Bailey

AI Developer Relations Lead

Google Deepmind Logo - Agentic AI Conference

The Last Mile of OCR/LLM-Based Document AI

Hands-On with Agentic Document Extraction

OCR performs well in benchmarks, but real-world document AI lives in the long tail: large tables, old scans, mixed-language documents, handwriting, and complex layouts. Even top models struggle here. This workshop demonstrates how LandingAI’s Agentic Document Extraction (ADE) goes beyond OCR and parsing to handle real-world enterprise workloads effectively.

In this workshop, attendees will:

  • Explore the core pillars of Agentic Document Extraction and understand how they address real-world document challenges
  • Build end-to-end document processing pipelines using ADE API and SDK for structured, reliable outputs
  • Use Skills to automate tasks and enable coding agents to generate solutions for complex document workflows
  • Apply ADE to enhance LLMs’ ability to process large tables, scanned documents, and mixed-language or handwritten content
Ankit Khare LandingAI Agentic AI Conference

Ankit Kharee

Developer Relations Specialist

Future of Data and AI: Agentic AI Conference | Data Science Dojo

Reinforcement Learning with Human Feedback and GRPO

How Do You Get Your LLM To Do Math?

This session tackles the challenge of making Large Language Models (LLMs) not just fluent in text, but capable of reasoning in math and code. Talking is imitation – learning by example – but logical tasks require learning by objective. That’s where RLHF comes in.

In this workshop, attendees will:

  • Understand why LLMs’ capabilities in reasoning, math, and coding emerged later than their language abilities
  • Learn what Reinforcement Learning with Human Feedback (RLHF) is and why it’s essential for fine-tuning models
  • Dive into Group Relative Policy Optimization (GRPO), a popular method for optimizing models on logical tasks
  • Explore practical applications of RLHF and GRPO to make LLMs more reliable in reasoning-intensive scenarios


This serves as a theoretical companion to Chris McCormick’s workshop. Attendance to Chris’s workshop is not required, but is recommended for anyone who is interested in a practical coding example of GRPO.

Luis Serrano Agentic AI Conference

Luis Serrano

Founder & Educator

Future of Data and AI: Agentic AI Conference | Data Science Dojo

From Isolation to Trust

Building Secure Sandboxes for Autonomous AI Agents

This session tackles the real problem with autonomous AI agents: speed is great, but unconstrained access is a liability. You want the performance. Not the security nightmares.

Enter Docker Sandboxes — a new primitive designed to let agents operate in a restricted environment with controlled filesystem access, network permissions, and secret injections. You will learn how to give your agents the freedom to work — without handing them the keys to your entire system.

During the session, attendees will:

  • Understand the typical ways AI agents go wrong when given unrestricted system access — and why basic isolation isn’t enough
  • Learn how Docker Sandboxes work as a controlled environment for autonomous agent execution
  • Walk through filesystem restrictions, network controls, and secure secret injection in practice
  • Build a workflow for running AI agents you can actually trust in production
Future of Data and AI: Agentic AI Conference | Data Science Dojo

Oleg Šelajev

Developer Relations

docker agentic ai conference

From Retrieval to Orchestration

Building Intent-Driven Agentic Context Engineering Systems

Most agentic RAG systems break in production because they treat every query the same. Real users ask multi-part questions, shift intent mid-conversation, and expect systems to keep up. This workshop shows you how to move beyond single-shot retrieval and build systems that actually handle real-world complexity.

In this workshop, attendees will:

  • Understand how vector databases store and retrieve context, and why hybrid search and metadata filtering outperform dense-only approaches in production
  • Learn to decompose complex, multi-intent queries into targeted sub-queries for more accurate and reliable retrieval across different parts of a knowledge base
  • Build an intent-based orchestration layer where specialized agents handle distinct tasks like product search, billing, or support with dedicated tools and strategies
  • Explore how to manage conversational state, route between intents, and handle mid-conversation goal shifts without breaking the user experience
  • Implement a lightweight evaluation workflow to measure retrieval quality and ensure your system improves as complexity increases
Scott-Askinosie-weaviate

Scott Askinosie

Developer Advocate

Future of Data and AI: Agentic AI Conference | Data Science Dojo

Advances in Agentic AI for Healthcare

Hands-on with Multi-LLM Clinical Applications

This session goes beyond conventional AI demos. While LLMs excel in controlled scenarios, real-world healthcare data is messy: electronic health records (EHRs) are fragmented, multi-modal, and require contextual reasoning across patient histories. This talk demonstrates how agentic AI systems, built on LangGraph agents orchestrating multiple LLMs within SambaNova’s SambaStack runtime, tackle these real-world challenges.

In this session, attendees will:

  • See how intelligent agents integrate specialized tooling to generate and execute Cypher queries on a Neo4j graph database for secure, high-fidelity EHR analysis
  • Explore multi-turn conversational workflows that support complex clinical queries and similarity searches across patient profiles using node embeddings
  • Understand how dynamic runtime model selection across co-deployed LLMs balances latency, throughput, and task-specific performance
  • Learn how on-premise SambaStack deployments can reduce total cost of ownership while maintaining data privacy, security, and production-grade reliability
Future of Data and AI: Agentic AI Conference | Data Science Dojo

Varun Krishna

Senior Principal Solutions Engineer - Generative AI

Future of Data and AI: Agentic AI Conference | Data Science Dojo

From GRPO Theory to Practice

Hands-On GRPO Training Pipeline To Fine-Tune A Qwen Model

A practical companion to Luis Serrano’s April 8 workshop on RLHF and GRPO, this session moves from theory and equations to running a stable training loop.  

In this hands-on workshop, we’ll walk through a GRPO training pipeline to fine-tune a Qwen model on arithmetic tasks. Instead of stepping through boilerplate code, we’ll focus on the design decisions that determine whether reinforcement learning trains successfully. 

During the session, attendees will: 

  • Walk through a GRPO training pipeline covering generation, reward calculation, and optimization 
  • Understand the key hyperparameters behind stable RL training, including prompt batch size, group size, learning rate, and dataset difficulty 
  • Learn how to interpret RL metrics such as the standard deviation of rewards 
  • Explore techniques for diagnosing instability and reward hacking using Weights & Biases 
  • See how GRPO systems scale using tools like vLLM and multi-GPU training 


Attendance at Luis Serrano’s April 8 session is recommended but not required; a brief RL refresher will be provided. 

Future of Data and AI: Agentic AI Conference | Data Science Dojo

Why you should join

The Agentic AI Conference features tutorials, panels, and hands-on workshops with thought leaders from the AI industry who will explore the latest technologies, trends, tools, and challenges shaping intelligent agents.

Access the event from anywhere, for free, this is your opportunity to learn, connect, and grow at the forefront of agentic AI. 

Expert-Led Sessions

From real-world use cases to technical deep dives, every session delivers insights you can act on.

Join from Anywhere, for Free

No travel, no cost - just world-class content. Our virtual format makes it easy to connect, learn, and grow from wherever you are.

$10,000+ in Exclusive Giveaways

We’re giving away over $10,000 worth of FREE bootcamp seats and other prizes. Attend the Agentic AI Conference live to win big!

Past conference by the numbers

A quick look at the impact and reach of this Agentic AI Conference edition

Attendees
1 +

A record turnout of AI enthusiasts, innovators, and leaders

Countries
1 +

A diverse community of AI experts and enthusiasts globally

giveaways
$ 1 +

Exciting prizes and exclusive offers for attendees 

Expert-led, hands-on workshops

serrano academy agentic ai conference

Reinforcement Learning with Human Feedback and GRPO

Learn how to fine-tune LLMs for reasoning, math, and coding with RLHF and GRPO methods, in order to create stable, reliable, logic-driven performance for practical, real-world AI applications.

Future of Data and AI: Agentic AI Conference | Data Science Dojo

From Isolation to Trust: Building Secure Sandboxes for Autonomous AI Agents

Learn to safely run autonomous AI agents using Docker Sandboxes, filesystem restrictions, network controls, and secure secret injection for production-ready enterprise deployment.

Learn to build multi-agent RAG systems using vector databases, hybrid search, and intent-based orchestration to handle complex queries, shifting user goals, and production-ready conversational workflows.

Learn to fine-tune a Qwen model on arithmetic tasks using a GRPO pipeline, exploring reward calculation, hyperparameters, stability techniques, and multi-GPU execution for reinforcement learning..

Get the complete workshop bundle

Enjoy full access to all workshops in a single bundle designed to help you upskill

Frequently asked questions, answered.

How do I register for the Agentic AI Conference?

Please use this link for registering for the Agentic AI Conference. 

Once you complete your registration, you’ll receive the Zoom link for the Agentic AI Conference via email. This link will allow you to join the live sessions on the conference days. 

No, you don’t need a paid Zoom account to attend the Agentic AI Conference. You can sign up for a free Zoom account and register for the conference using the same email address. On the event days, simply log into Zoom with that email to access and watch the sessions.

Yes! The main Agentic AI conference on September 15–16, including panels and tutorials, is completely virtual and free to attend. The optional workshops on September 17–19 are paid sessions. If you’d like to join these, you can purchase access separately after registering. 

Upon registering, you will get an invitation to join the exclusive LinkedIn group.

You can also join our discord community and connect with the Agentic AI conference speakers and other attendees. 

Each workshop includes:

  • Access to all Agentic AI conference sessions & giveaways
  • Live, instructor-led training
  • Personalized Q&A with the expert
  • Discounts on future bootcamps
  • Free bonus courses
  • Recording & slides to review later

Yes! Your questions will be put in a moderation queue and it will be answered by the panel.

Yes! All Agentic AI Conference sessions will be recorded, and you’ll be able to watch them at your convenience after the event. 

Registrations are closed!

Get notified about our next conference in October 2026

If the Agentic AI conference sparked your curiosity, you might enjoy a deeper dive through our Agentic AI Bootcamp