Join us for DataConnect Conference on Oct 2-3 in Columbus, OH!
00
DAY
00
HR
00
MIN
00
SEC
See what to expect at DCC West on May 20, 2025 in San Francisco, CA. More details will be posted soon.
Register now
Friendship Foyer
Check-in, grab a coffee and network before sessions begin!
8:00 am
-
2:00 pm
Bar & Lounge
8:00 am
-
9:00 am
Julia Morgan Ballroom
9:00 am
-
9:05 am
Julia Morgan Ballroom
The reliability challenges facing conversational AI deployments today mirror those that the autonomous vehicle industry confronted years ago. This talk explores how evaluation methodologies developed for self-driving cars can be transferred to create autonomous, self-improving evaluation systems for conversational AI. Drawing from Brooke’s experience building evaluation infrastructure at Waymo and now developing Coval, an enterprise-grade reliability platform for conversational agents, Brooke demonstrates how systematic testing infrastructure is not just a technical requirement but a competitive advantage in the rapidly evolving AI landscape.
9:05 am
-
9:35 am
9:35 am
-
9:45 am
Julia Morgan Ballroom
As artificial intelligence evolves toward increasingly autonomous, agentic systems, traditional approaches to data and AI governance are being challenged. This panel brings together leading voices from industry and academia to explore how governance frameworks must adapt to support collaboration between humans and intelligent agents. Topics will include the emerging risks and opportunities posed by agentic AI, new paradigms for accountability and oversight, and the role of policy, ethics, and technical infrastructure in ensuring safe and effective co-working between people and machines. Attendees will gain insight into how to design governance models that are dynamic, resilient, and aligned with human values—paving the way for responsible innovation in the era of agentic AI.
9:45 am
-
10:30 am
Bar & Lounge
While every second of the conference is an opportunity to network, these sessions are specifically tailored to optimize your experience of connecting with fellow attendees, meeting new contacts and contributing to conversations that are meaningful to you! Join us at the cocktail tables in the Bar & Lounge for engaging conversations with our networking facilitators!
9:45 am
-
10:30 am
Grab a snack, refill a beverage and take a minute to yourself in-between breakout session. Our Snack Break is sponsored by Grammarly!
10:30 am
-
10:40 am
Julia Morgan Ballroom
This session provides an accessible introduction to the emerging field of DevOps for agentic AI systems. We'll explore foundational concepts and practical approaches for creating infrastructure that supports AI systems capable of reasoning and adaptation. Topics include: how traditional DevOps principles can be adapted for AI workloads, essential CI/CD pipeline considerations, fundamental monitoring approaches for AI systems, and key strategies for balancing system reliability with AI autonomy. Attendees will gain practical, immediately applicable knowledge through real-world case studies drawn from enterprise AI deployments. You'll learn specific implementation patterns that have succeeded in production environments, common pitfalls to avoid when scaling agentic AI systems, and concrete examples of monitoring setups that effectively track AI agent behavior. The session will include actionable templates and frameworks that you can adapt to your organization's specific needs, regardless of where you are in your agentic AI journey.
10:40 am
-
11:25 am
Merchants Exchange Club
Agentic AI promises systems that don’t just respond—they reason, act, and adapt dynamically to complex tasks. But what’s actually required to build one? In this talk, I’ll break down the essential building blocks behind modern agentic AI systems. You’ll learn how language models integrate with external tools through function calling, how grounding with data sources reduces hallucinations, and how memory and planning enable adaptive multi-step behavior. I'll walk through a real-world example—an agent that handles user queries, generates charts, and navigates multi-turn conversations—to show how these components come together in practice. Whether you're building your first agent or scaling one for production, this session will give you a clear, practical framework to move from theory to implementation.
10:40 am
-
11:25 am
11:25 am
-
12:45 pm
Julia Morgan Ballroom
While we still don’t yet know all the best practices for building applications with generative AI, we do know many practices that don’t work. This talk first discusses how building with foundation models differs from traditional ML, and where it stands with product and full-stack engineering. It then discusses different anti-patterns throughout the developmental cycle.
12:45 pm
-
1:15 pm
1:15 pm
-
1:25 pm
Merchants Exchange Club
The AI industry faces a paradox: we're building sequential thinking agents but running them on parallel processing hardware. This fundamental mismatch creates a latency bottleneck that's holding back truly agentic AI systems - those that can reason, adapt, and drive outcomes autonomously. In this session, Jordan Hagan, AI Solutions Architect with Groq, demonstrates how LPUs break through this barrier with architecture specifically designed for sequential processing. See live demos showing how Groq's technology slashes token generation time, transforming theoretical agent capabilities into practical reality. Audience members will discover why Groq's approach produces not just faster but more reliable agent behavior - crucial for mission-critical applications where consistency matters as much as speed. Through real-world examples and performance benchmarks, learn how to identify workloads that benefit most from LPU acceleration and how to integrate this technology into your existing agentic AI pipelines. Leave with actionable insights on when, where, and how to deploy sequential processing technology for agentic systems where every millisecond of latency directly impacts user experience and agent effectiveness.
1:25 pm
-
2:10 pm
Julia Morgan Ballroom
The increasing deployment of generative AI models in production environments introduces new security challenges, particularly in the realm of adversarial attacks. While visually or textually subtle, these attacks can manipulate generative models, leading to harmful consequences such as medical misdiagnoses from tampered images or the spread of misinformation through compromised chatbots. This talk examines the vulnerabilities of generative models in production settings and explores potential defenses against adversarial attacks. Drawing on insights from attacks against Vision-Language Pre-training (VLP) models, which are a key component in text-to-image and text-to-video models, this talk highlights the importance of understanding cross-modal interactions and leveraging diverse data for crafting robust defenses.
1:25 pm
-
2:10 pm
While every second of the conference is an opportunity to network, these sessions are specifically tailored to optimize your experience of connecting with fellow attendees, meeting new contacts and contributing to conversations that are meaningful to you! Join us at the cocktail tables in the Bar & Lounge for engaging conversations with our networking facilitators!
1:45 pm
-
2:10 pm
Julia Morgan Ballroom
Grab a snack, refill a beverage and take a minute to yourself in-between breakout session. Our Snack Break is sponsored by Grammarly!
2:10 pm
-
2:20 pm
Julia Morgan Ballroom
As enterprises navigate an increasingly complex AI landscape, selecting the right approach based on the use case—whether traditional machine learning, generative AI, or agentic systems—has become a strategic imperative. In this fireside chat, Srujana Kaddevarmuth, an AI leader within Walmart, joins Rehgan Bleile, CEO of AlignAI, for a candid conversation on how to make these architectural decisions in high-scale environments where simplicity, performance, and efficiency matter. The discussion will explore key challenges in building agentic AI, particularly around infrastructure, compute, and data management. You'll hear insights on how large organizations validate model outputs as they move from pilot to production, and why cross-functional input is critical for building systems that are both effective and grounded in real-world context.
2:20 pm
-
3:05 pm
Merchants Exchange Club
What if your digital assistant could not only track your health data but also offer personalized wellness recommendations that evolve with you? This talk explores the process of building and evaluating a personal AI wellness agent—a cutting-edge companion that uses data from wearables like Apple Health and Oura to guide users toward healthier lives.We’ll take you through the journey of designing and developing this AI agent, focusing on data integration, personalized feedback, and AI-driven insights. From setting up data pipelines to designing meaningful, actionable recommendations, we’ll show you how the agent adapts to individual users’ health needs, learning from their data over time.But creating the agent is only half the story—evaluating its impact is where the true value lies. How do we measure success? Through real-world examples, we’ll cover key metrics such as recommendation accuracy, user engagement, and goal achievement rates. We’ll delve into how to use behavioral data, user feedback, and expert validation to assess whether the agent is truly making a difference in users’ wellness journeys.This talk will provide practical insights for anyone looking to design, build, or evaluate a wellness-focused AI, offering a comprehensive approach to both the creation and assessment of AI-driven personal health solutions.
2:20 pm
-
3:05 pm
3:05 pm
-
3:15 pm
Julia Morgan Ballroom
Agentic AI is the next frontier—AI that doesn’t just follow commands but reasons, adapts in real time, and drives outcomes with minimal hand-holding. Unlike traditional models that wait for input, agentic AI takes initiative, learns from its environment, and collaborates dynamically to automate complex workflows. For companies, this means faster decision-making, smarter automation, and AI that scales with the business. Context and data will be key as organizations build and deploy agentic systems. Evaluating these systems at scale will be critical to managing risks.
3:15 pm
-
4:00 pm
Julia Morgan Ballroom
4:00 pm
-
4:05 pm
Bar & Lounge
Join us for a Social Hour to conclude the day. Discuss your favorite talks with fellow analytics, data and AI enthusiasts while enjoying great food, drinks and music. Sponsored by Databricks!
4:05 pm
-
5:30 pm
