Loading…
AI DevSummit 2025 + DeveloperWeek Leadership 2025
Subject: Frameworks / Tools & Applied AI (AI DevSummit) clear filter
Wednesday, May 28
 

10:00am PDT

OPEN Session: 10 Commandments for Vibe Coding
Wednesday May 28, 2025 10:00am - 10:25am PDT
YK Sugi, CS Dojo, Founder

Since the launch of GPT-4, I've spent an intense and insane amount of time coding with AI. In this talk, I’ll distill everything I’ve learned from this into 10 practical rules. I’ll end with a look ahead—what the future holds as we move into the agentic future of coding and software engineering.

1. Thou shalt not rely on it too much if you are a junior.
2. Thou shalt write lots of tests.
3. Thou shalt not exceed 400 lines of code for each file.
4. Thou shalt organize your codebase well.
5. Thou shalt move slow so that you can go fast.
6. Thou shalt make architectural decisions carefully.
7. Thou shalt provide or let AI collect necessary context.
8. Thou shalt keep the provided context to a minimum.
9. Thou shalt break down a large problem into smaller ones.
10. Thou shalt go agentic.
 
Speakers
avatar for YK Sugi

YK Sugi

Founder, CS Dojo
Founder of CS Dojo, a leading programming education platform with over 1.9 million subscribers on YouTube, dedicated to empowering individuals with the skills needed for a successful career in tech. Beyond YouTube, he actively shares insights and tips on coding, AI, and tech career... Read More →
Wednesday May 28, 2025 10:00am - 10:25am PDT
AI DevSummit Expo Stage

11:30am PDT

PRO Session: The Future of AI-Driven Discovery: Can We Build Recommendation System That Inspire, Not Just Retain?
Wednesday May 28, 2025 11:30am - 11:55am PDT
Jiahui (Sophia) Bai, Meta, Data Scientist Lead

This talk explores the evolving role of AI-powered recommendation systems in shaping content discovery, moving beyond engagement-driven optimization to fostering meaningful exploration. Today’s recommendation algorithms are finely tuned to maximize user retention, often reinforcing content bubbles and favoring already-popular creators. While effective for keeping users engaged, this approach can limit exposure to new ideas, diverse voices, and serendipitous discovery—key elements that make digital platforms more enriching and dynamic.

We begin by defining the core challenges of AI-driven content recommendations: noisy engagement signals, over-reliance on short-term behavioral data, and algorithmic bias toward dominant content and creators. We explore how improving signal quality—by distinguishing between passive consumption and genuine interest—can lead to more personalized yet diverse recommendations. Next, we tackle the issue of democratizing reach, discussing algorithmic strategies that ensure small and emerging creators have a fair chance to break through without compromising user satisfaction.

The session will also cover rethinking success metrics for recommendation systems, moving beyond click-through rates and watch time to metrics that measure content diversity, long-term engagement, and user well-being. Finally, we will discuss the future of AI-driven discovery, including the role of Generative AI, hybrid human-AI curation, and serendipity-focused models in creating recommendation systems that inspire, inform, and surprise users—rather than just retaining them.
Speakers
avatar for Jiahui (Sophia) Bai

Jiahui (Sophia) Bai

Data Scientist Lead, Meta
Sophia Bai is a Senior Data Scientist at Meta, specializing in AI-driven recommendation systems and product analytics. She has led key initiatives in improving signal quality, optimizing content discovery, and redesigning recommendation models to create more balanced and engaging... Read More →
Wednesday May 28, 2025 11:30am - 11:55am PDT
AI DevSummit Main Stage

1:00pm PDT

KEYNOTE (AI): Hasura -- Path Towards 100% Accurate & Repeatable Data Agents for AI
Wednesday May 28, 2025 1:00pm - 1:25pm PDT
Praveen Durairaju, Hasura, Field CTO

Achieving 100% accuracy in Retrieval-Augmented Generation (RAG) is critical for AI agents handling complex workflows. But most RAG architectures fail due to goal drift, incomplete reasoning, and multi-step errors.
In this session, we will cover:
Why traditional RAG and tool-calling approaches break down in real-world AI workflows.
Agentic query planning: A structured approach to eliminate errors and improve reliability.
Benchmarking results: The path to achieve 100% accuracy where existing approaches fall short, backed by benchmarks.
Engineering strategies for verifiable, repeatable AI workflows.
We’ll walk through real-world examples and show how structured planning and separate execution fixes common RAG failures.


Live Demo: See how PromptQL ensures accurate, repeatable AI actions in production environments.
Speakers
avatar for Praveen Durairaju

Praveen Durairaju

Field CTO, Hasura
Praveen is a Field CTO at Hasura with over 10 years of full-stack web dev experience. Praveen was a core contributor to open source projects like hasura/graphql-engine and works on solving data access for the AI world. Besides the day job, Praveen runs community meetups like GraphQL... Read More →
Wednesday May 28, 2025 1:00pm - 1:25pm PDT
AI DevSummit Main Stage

2:00pm PDT

OPEN Session: The Age of Industrial AI Agents: Opportunities & Challenges
Wednesday May 28, 2025 2:00pm - 2:25pm PDT
Apurv Sibal, Wiley, Author

An AI Agent is an intelligent ‘computer’ system capable of agency, i.e. independent decision making and autonomous action based on contextualized situational awareness using sensing, perception, (causal) world modeling and a nuanced understanding of one's own agency and its impact on the world. Communicative AI agents are set to revolutionize human-machine collaborative systems and workflows whereby humans and agents can engage in natural multimodal communication in the same way as humans do. The agents can operate in a continuum of delegated autonomy modes, offloading data-intensive tasks needing high throughput, invoke backend tools to carry out a series of sophisticated actions, while not compromising human oversight or judgment. While such agents are poised to transform industries as diverse as healthcare and manufacturing, significant challenges remain in creating industrial strength agents that can operate robustly in open-world settings, exhibit both common sense reasoning and formal, domain-specific knowhow, are instructable and conform to human expectations, and communicate with high precision and accuracy backed by domain-specific grounded explanations. Our technical session will draw on Apurv's own experiences, and he will will present and discuss the opportunities and the challenges to creating industrial-strength agents that can provide real-value to the industry and the society at large, in a risk-free and safe fashion. 
Speakers
avatar for Apurv Sibal

Apurv Sibal

Author, Wiley
With a background in machine learning and data science, Apurv has published two books with Wiley and Springer Nature and has 7 years of experience working with AWS, Shorthills, and WorldQuant. He is an open-source contributor to Elastic, Azure, and AWS Data and have co-authored Pybanking... Read More →
Wednesday May 28, 2025 2:00pm - 2:25pm PDT
AI DevSummit Expo Stage

2:00pm PDT

PRO Session: How to Think About Multi-Agent Systems
Wednesday May 28, 2025 2:00pm - 2:25pm PDT
Kevin Van Gundy, Hypermode, Founder & CEO

We've made AI more complicated than it needs to be.

With buzzwords and obtuse new concepts, we've made it too difficult for the average developer to reason about agentic systems. While we're writing new kinds of programs, they're still programs nonetheless, and the core concepts of a well-architected application still hold. Fundamentally, we're attempting to write better business process automation just at a scale we've never seen before.

In this talk, Kevin will give attendees a simple, non-technical, non-buzzword-filled framework for looking at existing problems within their business and reimagining them as multi-agent systems.

We'll start by breaking down existing workflows into jobs to be done and the data needed to do those jobs. Then, map those into agents and tools. We'll then go over strategies for incrementally implementing these systems that control for output quality.
Speakers
avatar for Kevin Van Gundy

Kevin Van Gundy

Founder & CEO, Hypermode
I’m a technologist and the CEO of Hypermode. I’m originally from a farming community in central California. I’ve spent my career building for developers, data scientists, and engineers. Along the way, I’ve been lucky enough to help grow three unicorn startups over the last... Read More →
Wednesday May 28, 2025 2:00pm - 2:25pm PDT
AI DevSummit Main Stage

3:30pm PDT

OPEN Session: Enterprise GenAI: How to Make it Simple, Safe and Secure
Wednesday May 28, 2025 3:30pm - 3:55pm PDT
Debo Dutta, Nutanix, Chief AI Officer

Generative AI is reshaping industries, from healthcare to finance and beyond, offering transformative opportunities for innovation. However, deploying it effectively in enterprise settings requires navigating complex challenges around scalability and security. Debo Dutta, VP of Engineering & AI at Nutanix and founding member of MLCommons—an AI consortium advancing technology for global impact– shares his insights on integrating GenAI seamlessly while ensuring robust infrastructure and safeguarding model integrity. Debo delves into the tech stack essentials, including foundational models, fine-tuning frameworks, deployment tools, and governance systems needed to tailor to diverse business needs across industries. 
Speakers
avatar for Debo Dutta

Debo Dutta

Chief AI Officer, Nutanix
As Chief AI Officer at Nutanix (NASDAQ: NTNX; $16.97B market cap), Debo leads AI driven operations and governance, AI and ML Infra and data engineering used by the likes of Wells Fargo, Toyota and Air Liquide. Outside of his work at Nutanix, Debo is a founding member and serves as... Read More →
Wednesday May 28, 2025 3:30pm - 3:55pm PDT
AI DevSummit Expo Stage

5:30pm PDT

AI/ML Panel: The Next Frontier in AI Development: Why Agent Experience (AX) Matters
Wednesday May 28, 2025 5:30pm - 6:20pm PDT
Dana Lawson, Netlify, CTO
Julianna Lamb, Stytch, Co-founder and CTO
Aiden Ba, Million.js, Founder
Sean Roberts, Netlify, Distinguished Engineer


Agent experience (AX) is the holistic experience AI agents will have as the user of a product or platform. AI agents are reshaping software development, but today’s developer tools and platforms weren't built for them. For AI agents to truly be effective, we need to craft our products with AX in mind. How do we design platforms, APIs, and workflows that help AI agents operate effectively? While DX optimized tools for humans, AX challenges us to rethink systems for AI-first development.
This panel brings together experts in AI infrastructure, developer tooling, and LLMs to discuss:
-Introduction to Agent Experience (AX)
-The current limitations of AI agents when building, deploying, and iterating software.
-How platforms might need to evolve to support AI-native workflows.
-The tensions between human-driven and AI-driven development—and what collaboration could look like.
-The early signs of AX in today’s AI-powered development landscape.
Speakers
avatar for Aiden Ba

Aiden Ba

Founder, Million.js
avatar for Julianna Lamb

Julianna Lamb

Co-founder and CTO, Stytch
avatar for Dana Lawson

Dana Lawson

CTO, Netlify
avatar for Sean Roberts

Sean Roberts

Distinguished engineer, Netlify
Wednesday May 28, 2025 5:30pm - 6:20pm PDT
AI DevSummit Expo Stage
 
Thursday, May 29
 

9:30am PDT

OPEN Session: From Technical Possibility to User Value: Product Management Strategies for Successful AI Implementation
Thursday May 29, 2025 9:30am - 9:55am PDT
Abhai Pratap Singh, Amazon, Senior Product Manager-Technical

"From Technical Possibility to User Value: Product Management Strategies for Successful AI Implementation" explores the delicate balance between advancing AI capabilities and maintaining genuine user value. Drawing from experience leading Alexa's voice assistant development, this session reveals practical strategies for putting user needs at the center of AI product development. Learn how to avoid the trap of 'tech for tech's sake' while driving meaningful innovation. Through real-world examples from voice AI and multi-modal interactions, discover frameworks for evaluating AI features, measuring user impact, and making strategic decisions that enhance rather than complicate the user experience. Perfect for product leaders navigating the AI revolution.
Speakers
avatar for Abhai Pratap Singh

Abhai Pratap Singh

Senior Product Manager-Technical, Amazon
Abhai Pratap Singh is a Senior Product Manager-Technical at Amazon Alexa, where he leads strategic initiatives in voice AI technology. With 9 years of experience building AI-driven products used by millions, he specializes in creating human-centric AI experiences that balance innovation... Read More →
Thursday May 29, 2025 9:30am - 9:55am PDT
AI DevSummit Expo Stage

9:30am PDT

PRO Session: Building Production Ready, Intelligent Agentic Systems with Dapr Agents
Thursday May 29, 2025 9:30am - 9:55am PDT
Mark Fussell, Diagrid, CEO
Yaron Schneider, Diagrid, Co-Founder / CTO


As developers push the boundaries of AI-driven automation, the challenge of orchestrating and managing autonomous agents at scale becomes increasingly complex. Dapr Agents is an open-source framework that dramatically lowers the creation of production ready agentic systems, powered by the CNCF Dapr's (dapr.io) distributed application runtime, used by thousands of enterprises today in mission critical services. By combining LLM-driven reasoning with Dapr’s virtual actor model, pub/sub messaging, and stateful workflows, Dapr Agents enables developers to build intelligent, scalable, and fault-tolerant multi-agent systems.

This talk will provide a deep dive into Dapr Agents, demonstrating how it facilitates structured LLM interactions, tool selection, memory retention, and event-driven communication. We'll explore practical use cases, from task automation to collaborative agentic workflows, and discuss best practices for designing real world, robust agent-based architectures. We will also compare different agentic frameworks in use today and show how many of them only address a few of the requirements needed to go into production environments. Attendees will gain hands-on insights into implementing Dapr Agents for real-world applications, optimizing performance, and seamlessly integrating with existing cloud-native infrastructures.

If you're interested in building intelligent, scalable, and resilient agentic systems, this session will equip you with the knowledge to easily build these.
Speakers
avatar for Mark Fussell

Mark Fussell

CEO, Diagrid
CEO of Diagrid, a developer focused startup. Leader with proven track record of building innovative computing platforms, running large scale, cloud services, building OSS communities and starting new businesses.
avatar for Yaron Schneider

Yaron Schneider

Co-Founder / CTO, Diagrid
Yaron co-created the CNCF projects Dapr and KEDA while at Microsoft and led the engineering architecture for serverless container platforms that run at scale using open source technologies. Yaron is an avid lover of open source tech and distributed systems, and is a co-founder and... Read More →
Thursday May 29, 2025 9:30am - 9:55am PDT
AI DevSummit Main Stage

10:00am PDT

PRO Session: What’s Different About LLM Applications
Thursday May 29, 2025 10:00am - 10:25am PDT
Nuno Campos, LangChain, Founding Engineer

This talk identifies the three key things that make LLM applications different from previous software: latency, versatility and flakiness. LLMs are orders of magnitude slower than we were used to. The outputs of LLM apps are also more variable, and prone to mistakes. And LLM apps can be taken by users into domains we the creators didn’t necessarily program into them or expect. I’ll show how we can use these 3 qualities to our advantage, by learning to work with them, and so use them to build things that were simply impossible before. 
Speakers
avatar for Nuno Campos

Nuno Campos

Founding Engineer, LangChain
I'm a founding software engineer at LangChain, creator of LangGraph, the leading LLM agent framework, and co-author of the O’Reilly book Learning LangChain. Previously I was a maintainer of other popular open source packages, such as Enzyme, and have worked for tech startups for... Read More →
Thursday May 29, 2025 10:00am - 10:25am PDT
AI DevSummit Main Stage

10:30am PDT

KEYNOTE (AI): Google -- Agentic Future for the Enterprise
Thursday May 29, 2025 10:30am - 10:55am PDT
Logan Ramalingam, Google Cloud, Head of AI Solutions

This session will talk about practical agent usecases for the enterprise.
 
Speakers
avatar for Logan Ramalingam

Logan Ramalingam

Head of AI Solutions, Google Cloud
Logan is currently leading the AI Solutions in Google Cloud’s Global Services Delivery. He works with customers across the North America to build complex AI solutions in the cloud. He has over 13+ years of experience in AI/ML, Data & Analytics, and SAP.
Thursday May 29, 2025 10:30am - 10:55am PDT
AI DevSummit Main Stage

11:00am PDT

OPEN Session: AI Coding Agents: Three Keys to Successfully Scaling in the Enterprise
Thursday May 29, 2025 11:00am - 11:25am PDT
Rob Whiteley, Coder, CEO

With great power comes great responsibility—and yes, coding agents can backfire if they’re not thoughtfully deployed. Instead of boosting productivity, they can frustrate developers, slow down progress, and even diminish your competitive edge.

Join Coder CEO, Rob Whiteley, as he unpacks three essential strategies organizations should embrace when scaling agentic coding agents enterprise-wide. Drawing from firsthand lessons and internal experiments—where agents effectively resolved nearly half the tasks we threw at them—we’ll share real-world scenarios showcasing engineering work AI agents excelled at. We’ll also highlight where they fell short, detailing what went wrong and what we’d do
differently next time.

You’ll walk away understanding:

* How realistic expectations ensure AI boosts rather than hinders productivity.
* Why effective human-agent collaboration is critical for developer satisfaction and innovation.
* How clear governance frameworks can prevent technical debt and keep productivity flowing.

Learn from our experiences and ensure your organization’s deployment of AI coding agents empowers your developers, ignites innovation, and solidifies your market leadership.
Speakers
avatar for Rob Whiteley

Rob Whiteley

CEO, Coder
Rob Whiteley serves as CEO of Coder. Previously he was GM of NGINX. He has led marketing, product, and analyst teams for companies like Hedvig, Riverbed, and Forrester. Rob uses his experience working with enterprise IT and DevOps customers to deliver thought leadership and drive... Read More →
Thursday May 29, 2025 11:00am - 11:25am PDT
AI DevSummit Expo Stage

1:00pm PDT

PRO Session: Numaflow: Powering Scalable Inference on Real-Time Data Streams at Intuit
Thursday May 29, 2025 1:00pm - 1:25pm PDT
Sri Harsha Yayi, intuit, Staff Product Manager
Vigith Maurice, Intuit, Principal Engineer


At Intuit, the ML teams encountered challenges when managing and executing inference on high-throughput streaming data. Integrating with diverse messaging systems like Kafka, Pulsar, and SQS required considerable effort, while enabling intermediate data transformations and inference added complexity. Additionally, dynamically scaling inference workflows to handle fluctuating event volumes posed unique challenges.

To address these issues, we developed Numaflow, an open-source, Kubernetes-native platform designed for scalable event processing. Numaflow simplifies connections to various event sources, empowers teams to process and infer on streaming data with ease, and integrates effortlessly with existing infrastructure. This session is ideal for ML engineers, data scientists, and anyone interested in asynchronous inference on streaming data. We’ll dive into how Numaflow eliminates bottlenecks and optimizes inference on streaming data.
 
Speakers
avatar for Vigith Maurice

Vigith Maurice

Principal Engineer, Intuit
Vigith is a co-creator of Numaproj and Principal Software Engineer for the Intuit Core Platform team in Mountain View, California. One of Vigith's current day-to-day focus areas is the various challenges in building scalable data and AIOps solutions for both batch and high-throughput... Read More →
avatar for Sri Harsha Yayi

Sri Harsha Yayi

Staff Product Manager, Intuit
Sri Harsha Yayi is a Product Manager at Intuit, where he primarily focuses on the company's Modern SaaS Kubernetes platform, specifically within the real time event processing domain. He is the PM for Numaflow, an open-source, Kubernetes native platform designed for the real time... Read More →
Thursday May 29, 2025 1:00pm - 1:25pm PDT
AI DevSummit Main Stage

1:00pm PDT

OPEN Session: Operationalizing Production-Ready AI Agents for Data Analytics Workflows
Thursday May 29, 2025 1:00pm - 1:25pm PDT
David Kucher, Numbers Station, Principal Engineer

The rise of AI agents is driving a growing push to automate repetitive tasks. Recent breakthroughs like Devin and Cursor highlight AI’s impact on software development—now, it’s transforming data analytics. Using a multi-agent system, Numbers Station (numbersstation.ai) has emerged to automate the end-to-end analytics workflow—from pulling insights, generating dashboards, and taking action using your native tools.

This talk explores Numbers Station’s composable AI agents, including a step-by-step guide to building a SQL Agent using retrieval-augmented generation and error correction. We’ll then discuss how our agents—handling search, diagnostics, charting, and reporting—are orchestrated together to automate analytics requests.

We’ll cover challenges like message routing and long-context management in multi-agent systems. Finally, we’ll showcase real-world applications, demonstrating how these AI agents enhance decision-making and eliminate inefficiencies in enterprise data workflows.
 
Speakers
avatar for David Kucher,

David Kucher,

Principal Engineer, Numbers Station
David Kucher is a Principal Engineer at Numbers Station, where he brings machine learning and AI to automate and improve data tasks. He previously worked on computer vision and ML systems at SambaNova Systems. David holds Bachelor's and Master's degrees in Electrical and Computer... Read More →
Thursday May 29, 2025 1:00pm - 1:25pm PDT
AI DevSummit Expo Stage

1:30pm PDT

OPEN Session: AI Faster, Better, Cheaper
Thursday May 29, 2025 1:30pm - 1:55pm PDT
Gunveer Gujral, Meta, Senior Staff Software Engineer

Discover practical strategies to accelerate AI development, boost performance, and optimize costs without compromising innovation. Drawing from real-world experiences, this talk will dive into making AI truly scalable. 
Speakers
avatar for Gunveer Gujral

Gunveer Gujral

Senior Staff Software Enginee, Meta
Gunveer is a Senior Staff Software Engineer at Meta, where they lead initiatives in cutting-edge AI for smart wearables. Over the past decade, their work has driven industry-defining AI features in products like Ray-Ban Meta and Oculus Quest.A graduate of Carnegie Mellon University... Read More →
Thursday May 29, 2025 1:30pm - 1:55pm PDT
DeveloperWeek Leadership Expo Stage

1:30pm PDT

PRO Session: AI Agents in Software Engineering: Can Autonomous AI Teams Build and Maintain Code
Thursday May 29, 2025 1:30pm - 1:55pm PDT
Tanush Sharanarthi, IBM, Staff Software Engineer

AI-powered coding assistants like GitHub Copilot have changed how developers write code, but what if AI could go beyond assisting and work together as a team? This talk explores the potential of multi-agent AI systems, where different AI agents take on specialized roles—one writing code, another reviewing it, a third optimizing performance, and another refactoring—to collaboratively build and maintain software with minimal human input. We’ll dive into real-world applications, emerging research, and the challenges of AI-driven development, from debugging AI-generated code to ensuring reliability. Attendees will gain insight into the future of AI-powered software engineering, whether AI can function as independent development teams, and what this means for the role of human engineers. 
Speakers
avatar for Tanush Sharanarthi

Tanush Sharanarthi

Staff Software Engineer, IBM
Tanush Sharanarthi is a Staff Software Engineer at IBM Silicon Valley Labs with a strong background in software development and artificial intelligence. His work focuses on AI-driven development, large language models, and building intelligent automation systems. He has served as... Read More →
Thursday May 29, 2025 1:30pm - 1:55pm PDT
AI DevSummit Main Stage
 
Wednesday, June 4
 

10:00am PDT

[Virtual] OPEN Session: 10 Commandments for Vibe Coding
Wednesday June 4, 2025 10:00am - 10:25am PDT
YK Sugi, CS Dojo, Founder

Since the launch of GPT-4, I've spent an intense and insane amount of time coding with AI. In this talk, I’ll distill everything I’ve learned from this into 10 practical rules. I’ll end with a look ahead—what the future holds as we move into the agentic future of coding and software engineering.

1. Thou shalt not rely on it too much if you are a junior.
2. Thou shalt write lots of tests.
3. Thou shalt not exceed 400 lines of code for each file.
4. Thou shalt organize your codebase well.
5. Thou shalt move slow so that you can go fast.
6. Thou shalt make architectural decisions carefully.
7. Thou shalt provide or let AI collect necessary context.
8. Thou shalt keep the provided context to a minimum.
9. Thou shalt break down a large problem into smaller ones.
10. Thou shalt go agentic.
 
Speakers
avatar for YK Sugi

YK Sugi

Founder, CS Dojo
Founder of CS Dojo, a leading programming education platform with over 1.9 million subscribers on YouTube, dedicated to empowering individuals with the skills needed for a successful career in tech. Beyond YouTube, he actively shares insights and tips on coding, AI, and tech career... Read More →
Wednesday June 4, 2025 10:00am - 10:25am PDT
VIRTUAL AI DevSummit Expo Stage

11:30am PDT

[Virtual] PRO Session: The Future of AI-Driven Discovery: Can We Build Recommendation System That Inspire, Not Just Retain?
Wednesday June 4, 2025 11:30am - 11:55am PDT
Jiahui (Sophia) Bai, Meta, Data Scientist Lead

This talk explores the evolving role of AI-powered recommendation systems in shaping content discovery, moving beyond engagement-driven optimization to fostering meaningful exploration. Today’s recommendation algorithms are finely tuned to maximize user retention, often reinforcing content bubbles and favoring already-popular creators. While effective for keeping users engaged, this approach can limit exposure to new ideas, diverse voices, and serendipitous discovery—key elements that make digital platforms more enriching and dynamic.

We begin by defining the core challenges of AI-driven content recommendations: noisy engagement signals, over-reliance on short-term behavioral data, and algorithmic bias toward dominant content and creators. We explore how improving signal quality—by distinguishing between passive consumption and genuine interest—can lead to more personalized yet diverse recommendations. Next, we tackle the issue of democratizing reach, discussing algorithmic strategies that ensure small and emerging creators have a fair chance to break through without compromising user satisfaction.

The session will also cover rethinking success metrics for recommendation systems, moving beyond click-through rates and watch time to metrics that measure content diversity, long-term engagement, and user well-being. Finally, we will discuss the future of AI-driven discovery, including the role of Generative AI, hybrid human-AI curation, and serendipity-focused models in creating recommendation systems that inspire, inform, and surprise users—rather than just retaining them.
Speakers
avatar for Jiahui (Sophia) Bai

Jiahui (Sophia) Bai

Data Scientist Lead, Meta
Sophia Bai is a Senior Data Scientist at Meta, specializing in AI-driven recommendation systems and product analytics. She has led key initiatives in improving signal quality, optimizing content discovery, and redesigning recommendation models to create more balanced and engaging... Read More →
Wednesday June 4, 2025 11:30am - 11:55am PDT
VIRTUAL AI DevSummit Main Stage

12:00pm PDT

[Virtual] PRO Session: The Next Frontier in AI Development: Why Agent Experience (AX) Matters
Wednesday June 4, 2025 12:00pm - 12:50pm PDT
Dana Lawson, Netlify, CTO
Julianna Lamb, Stytch, Co-founder and CTO
Aiden Ba, Million.js, Founder
Sean Roberts, Netlify, Distinguished Engineer


Agent experience (AX) is the holistic experience AI agents will have as the user of a product or platform. AI agents are reshaping software development, but today’s developer tools and platforms weren't built for them. For AI agents to truly be effective, we need to craft our products with AX in mind. How do we design platforms, APIs, and workflows that help AI agents operate effectively? While DX optimized tools for humans, AX challenges us to rethink systems for AI-first development.
This panel brings together experts in AI infrastructure, developer tooling, and LLMs to discuss:
-Introduction to Agent Experience (AX)
-The current limitations of AI agents when building, deploying, and iterating software.
-How platforms might need to evolve to support AI-native workflows.
-The tensions between human-driven and AI-driven development—and what collaboration could look like.
-The early signs of AX in today’s AI-powered development landscape.
Speakers
avatar for Aiden Ba

Aiden Ba

Founder, Million.js
avatar for Julianna Lamb

Julianna Lamb

Co-founder and CTO, Stytch
avatar for Dana Lawson

Dana Lawson

CTO, Netlify
avatar for Sean Roberts

Sean Roberts

Distinguished engineer, Netlify
Wednesday June 4, 2025 12:00pm - 12:50pm PDT
VIRTUAL AI DevSummit Main Stage

1:00pm PDT

[Virtual] KEYNOTE (AI): Hasura -- Path Towards 100% Accurate & Repeatable Data Agents for AI
Wednesday June 4, 2025 1:00pm - 1:25pm PDT
Praveen Durairaju, Hasura, Field CTO

Achieving 100% accuracy in Retrieval-Augmented Generation (RAG) is critical for AI agents handling complex workflows. But most RAG architectures fail due to goal drift, incomplete reasoning, and multi-step errors.
In this session, we will cover:
Why traditional RAG and tool-calling approaches break down in real-world AI workflows.
Agentic query planning: A structured approach to eliminate errors and improve reliability.
Benchmarking results: The path to achieve 100% accuracy where existing approaches fall short, backed by benchmarks.
Engineering strategies for verifiable, repeatable AI workflows.
We’ll walk through real-world examples and show how structured planning and separate execution fixes common RAG failures.


Live Demo: See how PromptQL ensures accurate, repeatable AI actions in production environments.
Speakers
avatar for Praveen Durairaju

Praveen Durairaju

Field CTO, Hasura
Praveen is a Field CTO at Hasura with over 10 years of full-stack web dev experience. Praveen was a core contributor to open source projects like hasura/graphql-engine and works on solving data access for the AI world. Besides the day job, Praveen runs community meetups like GraphQL... Read More →
Wednesday June 4, 2025 1:00pm - 1:25pm PDT
VIRTUAL AI DevSummit Main Stage

2:00pm PDT

[Virtual] OPEN Session: The Age of Industrial AI Agents: Opportunities & Challenges
Wednesday June 4, 2025 2:00pm - 2:25pm PDT
Apurv Sibal, Wiley, Author

An AI Agent is an intelligent ‘computer’ system capable of agency, i.e. independent decision making and autonomous action based on contextualized situational awareness using sensing, perception, (causal) world modeling and a nuanced understanding of one's own agency and its impact on the world. Communicative AI agents are set to revolutionize human-machine collaborative systems and workflows whereby humans and agents can engage in natural multimodal communication in the same way as humans do. The agents can operate in a continuum of delegated autonomy modes, offloading data-intensive tasks needing high throughput, invoke backend tools to carry out a series of sophisticated actions, while not compromising human oversight or judgment. While such agents are poised to transform industries as diverse as healthcare and manufacturing, significant challenges remain in creating industrial strength agents that can operate robustly in open-world settings, exhibit both common sense reasoning and formal, domain-specific knowhow, are instructable and conform to human expectations, and communicate with high precision and accuracy backed by domain-specific grounded explanations. Our technical session will draw on Apurv's own experiences, and he will will present and discuss the opportunities and the challenges to creating industrial-strength agents that can provide real-value to the industry and the society at large, in a risk-free and safe fashion. 
Speakers
avatar for Apurv Sibal

Apurv Sibal

Author, Wiley
With a background in machine learning and data science, Apurv has published two books with Wiley and Springer Nature and has 7 years of experience working with AWS, Shorthills, and WorldQuant. He is an open-source contributor to Elastic, Azure, and AWS Data and have co-authored Pybanking... Read More →
Wednesday June 4, 2025 2:00pm - 2:25pm PDT
VIRTUAL AI DevSummit Expo Stage

2:00pm PDT

[Virtual] PRO Session: How to Think About Multi-Agent Systems
Wednesday June 4, 2025 2:00pm - 2:25pm PDT
Kevin Van Gundy, Hypermode, Founder & CEO

We've made AI more complicated than it needs to be.

With buzzwords and obtuse new concepts, we've made it too difficult for the average developer to reason about agentic systems. While we're writing new kinds of programs, they're still programs nonetheless, and the core concepts of a well-architected application still hold. Fundamentally, we're attempting to write better business process automation just at a scale we've never seen before.

In this talk, Kevin will give attendees a simple, non-technical, non-buzzword-filled framework for looking at existing problems within their business and reimagining them as multi-agent systems.

We'll start by breaking down existing workflows into jobs to be done and the data needed to do those jobs. Then, map those into agents and tools. We'll then go over strategies for incrementally implementing these systems that control for output quality.
Speakers
avatar for Kevin Van Gundy

Kevin Van Gundy

Founder & CEO, Hypermode
I’m a technologist and the CEO of Hypermode. I’m originally from a farming community in central California. I’ve spent my career building for developers, data scientists, and engineers. Along the way, I’ve been lucky enough to help grow three unicorn startups over the last... Read More →
Wednesday June 4, 2025 2:00pm - 2:25pm PDT
VIRTUAL AI DevSummit Main Stage
 
Thursday, June 5
 

9:30am PDT

[Virtual] OPEN Session: From Technical Possibility to User Value: Product Management Strategies for Successful AI Implementation
Thursday June 5, 2025 9:30am - 9:55am PDT
Abhai Pratap Singh, Amazon, Senior Product Manager-Technical

"From Technical Possibility to User Value: Product Management Strategies for Successful AI Implementation" explores the delicate balance between advancing AI capabilities and maintaining genuine user value. Drawing from experience leading Alexa's voice assistant development, this session reveals practical strategies for putting user needs at the center of AI product development. Learn how to avoid the trap of 'tech for tech's sake' while driving meaningful innovation. Through real-world examples from voice AI and multi-modal interactions, discover frameworks for evaluating AI features, measuring user impact, and making strategic decisions that enhance rather than complicate the user experience. Perfect for product leaders navigating the AI revolution.
Speakers
avatar for Abhai Pratap Singh

Abhai Pratap Singh

Senior Product Manager-Technical, Amazon
Abhai Pratap Singh is a Senior Product Manager-Technical at Amazon Alexa, where he leads strategic initiatives in voice AI technology. With 9 years of experience building AI-driven products used by millions, he specializes in creating human-centric AI experiences that balance innovation... Read More →
Thursday June 5, 2025 9:30am - 9:55am PDT
VIRTUAL AI DevSummit Expo Stage

9:30am PDT

[Virtual] PRO Session: Building Production Ready, Intelligent Agentic Systems with Dapr Agents
Thursday June 5, 2025 9:30am - 9:55am PDT
Mark Fussell, Diagrid, CEO
Yaron Schneider, Diagrid, Co-Founder / CTO


As developers push the boundaries of AI-driven automation, the challenge of orchestrating and managing autonomous agents at scale becomes increasingly complex. Dapr Agents is an open-source framework that dramatically lowers the creation of production ready agentic systems, powered by the CNCF Dapr's (dapr.io) distributed application runtime, used by thousands of enterprises today in mission critical services. By combining LLM-driven reasoning with Dapr’s virtual actor model, pub/sub messaging, and stateful workflows, Dapr Agents enables developers to build intelligent, scalable, and fault-tolerant multi-agent systems.

This talk will provide a deep dive into Dapr Agents, demonstrating how it facilitates structured LLM interactions, tool selection, memory retention, and event-driven communication. We'll explore practical use cases, from task automation to collaborative agentic workflows, and discuss best practices for designing real world, robust agent-based architectures. We will also compare different agentic frameworks in use today and show how many of them only address a few of the requirements needed to go into production environments. Attendees will gain hands-on insights into implementing Dapr Agents for real-world applications, optimizing performance, and seamlessly integrating with existing cloud-native infrastructures.

If you're interested in building intelligent, scalable, and resilient agentic systems, this session will equip you with the knowledge to easily build these.
Speakers
avatar for Mark Fussell

Mark Fussell

CEO, Diagrid
CEO of Diagrid, a developer focused startup. Leader with proven track record of building innovative computing platforms, running large scale, cloud services, building OSS communities and starting new businesses.
avatar for Yaron Schneider

Yaron Schneider

Co-Founder / CTO, Diagrid
Yaron co-created the CNCF projects Dapr and KEDA while at Microsoft and led the engineering architecture for serverless container platforms that run at scale using open source technologies. Yaron is an avid lover of open source tech and distributed systems, and is a co-founder and... Read More →
Thursday June 5, 2025 9:30am - 9:55am PDT
VIRTUAL AI DevSummit Main Stage

10:00am PDT

[Virtual] PRO Session: What’s Different About LLM Applications
Thursday June 5, 2025 10:00am - 10:25am PDT
Nuno Campos, LangChain, Founding Engineer

This talk identifies the three key things that make LLM applications different from previous software: latency, versatility and flakiness. LLMs are orders of magnitude slower than we were used to. The outputs of LLM apps are also more variable, and prone to mistakes. And LLM apps can be taken by users into domains we the creators didn’t necessarily program into them or expect. I’ll show how we can use these 3 qualities to our advantage, by learning to work with them, and so use them to build things that were simply impossible before. 
Speakers
avatar for Nuno Campos

Nuno Campos

Founding Engineer, LangChain
I'm a founding software engineer at LangChain, creator of LangGraph, the leading LLM agent framework, and co-author of the O’Reilly book Learning LangChain. Previously I was a maintainer of other popular open source packages, such as Enzyme, and have worked for tech startups for... Read More →
Thursday June 5, 2025 10:00am - 10:25am PDT
VIRTUAL AI DevSummit Main Stage

10:30am PDT

[Virtual] KEYNOTE (AI): Google -- Agentic Future for the Enterprise
Thursday June 5, 2025 10:30am - 10:55am PDT
Logan Ramalingam, Google Cloud, Head of AI Solutions

This session will talk about practical agent usecases for the enterprise.
 
Speakers
avatar for Logan Ramalingam

Logan Ramalingam

Head of AI Solutions, Google Cloud
Logan is currently leading the AI Solutions in Google Cloud’s Global Services Delivery. He works with customers across the North America to build complex AI solutions in the cloud. He has over 13+ years of experience in AI/ML, Data & Analytics, and SAP.
Thursday June 5, 2025 10:30am - 10:55am PDT
AI DevSummit Main Stage

11:00am PDT

[Virtual] OPEN Session: AI Coding Agents: Three Keys to Successfully Scaling in the Enterprise
Thursday June 5, 2025 11:00am - 11:25am PDT
Dave Ahr, Coder, Staff Sales Engineer

With great power comes great responsibility—and yes, coding agents can backfire if they’re not thoughtfully deployed. Instead of boosting productivity, they can frustrate developers, slow down progress, and even diminish your competitive edge.

You’ll walk away understanding:

* How realistic expectations ensure AI boosts rather than hinders productivity.
* Why effective human-agent collaboration is critical for developer satisfaction and innovation.
* How clear governance frameworks can prevent technical debt and keep productivity flowing.

Learn from our experiences and ensure your organization’s deployment of AI coding agents empowers your developers, ignites innovation, and solidifies your market leadership.
Speakers
avatar for Dave Ahr

Dave Ahr

Staff Sales Engineer, Coder
Thursday June 5, 2025 11:00am - 11:25am PDT
VIRTUAL AI DevSummit Expo Stage

12:30pm PDT

[Virtual Exclusive] OPEN Session: Beyond Model Optimization: Rethinking AI Pipeline Efficiency
Thursday June 5, 2025 12:30pm - 12:55pm PDT
Shashidhar Shenoy, Google, Tech Lead
Achyut Sarma Boggaram, Torc Robotics, Sr. Machine Learning Engineer


AI teams focus heavily on model optimization—distillation, pruning, and quantization—yet still face high costs, scaling challenges, and deployment inefficiencies. The missing piece? Pipeline optimization.

This session introduces a pipeline-first approach to AI scalability, showcasing how Dagster, Ray, and Kubernetes-native tools can optimize ML pipelines.

Shift from model-centric to pipeline-aware AI infrastructure to build faster, cost-effective, and scalable ML systems.
Speakers
avatar for Achyut Sarma Boggaram

Achyut Sarma Boggaram

Sr. Machine Learning Engineer, Torc Robotics
As a Sr. Machine Learning Engineer at Torc Robotics, I am building critical ML infrastructure for the L4 self-driving class-8 trucks, paving the way for safer transportation of freight.I have a decade of experience in delivering impactful robotics solutions across various industries... Read More →
avatar for Shashidhar Shenoy

Shashidhar Shenoy

Tech Lead, Google
Shashidhar Shenoy is a software engineer and technical leader specializing in distributed systems, AI/ML infrastructure, and scalable authentication platforms. With over a decade of experience, he has led high-impact projects, including optimizing cloud infrastructure for AI/ML workloads... Read More →
Thursday June 5, 2025 12:30pm - 12:55pm PDT
VIRTUAL AI DevSummit Expo Stage

1:00pm PDT

CANCELLED -- [Virtual] PRO Session: Numaflow: Powering Scalable Inference on Real-Time Data Streams at Intuit
Thursday June 5, 2025 1:00pm - 1:25pm PDT
Sri Harsha Yayi, intuit, Staff Product Manager
Vigith Maurice, Intuit, Principal Engineer


At Intuit, the ML teams encountered challenges when managing and executing inference on high-throughput streaming data. Integrating with diverse messaging systems like Kafka, Pulsar, and SQS required considerable effort, while enabling intermediate data transformations and inference added complexity. Additionally, dynamically scaling inference workflows to handle fluctuating event volumes posed unique challenges.

To address these issues, we developed Numaflow, an open-source, Kubernetes-native platform designed for scalable event processing. Numaflow simplifies connections to various event sources, empowers teams to process and infer on streaming data with ease, and integrates effortlessly with existing infrastructure. This session is ideal for ML engineers, data scientists, and anyone interested in asynchronous inference on streaming data. We’ll dive into how Numaflow eliminates bottlenecks and optimizes inference on streaming data.
 
Speakers
avatar for Vigith Maurice

Vigith Maurice

Principal Engineer, Intuit
Vigith is a co-creator of Numaproj and Principal Software Engineer for the Intuit Core Platform team in Mountain View, California. One of Vigith's current day-to-day focus areas is the various challenges in building scalable data and AIOps solutions for both batch and high-throughput... Read More →
avatar for Sri Harsha Yayi

Sri Harsha Yayi

Staff Product Manager, Intuit
Sri Harsha Yayi is a Product Manager at Intuit, where he primarily focuses on the company's Modern SaaS Kubernetes platform, specifically within the real time event processing domain. He is the PM for Numaflow, an open-source, Kubernetes native platform designed for the real time... Read More →
Thursday June 5, 2025 1:00pm - 1:25pm PDT
VIRTUAL AI DevSummit Main Stage

1:00pm PDT

[Virtual] OPEN Session: Operationalizing Production-Ready AI Agents for Data Analytics Workflows
Thursday June 5, 2025 1:00pm - 1:25pm PDT
David Kucher, Numbers Station, Principal Engineer

The rise of AI agents is driving a growing push to automate repetitive tasks. Recent breakthroughs like Devin and Cursor highlight AI’s impact on software development—now, it’s transforming data analytics. Using a multi-agent system, Numbers Station (numbersstation.ai) has emerged to automate the end-to-end analytics workflow—from pulling insights, generating dashboards, and taking action using your native tools.

This talk explores Numbers Station’s composable AI agents, including a step-by-step guide to building a SQL Agent using retrieval-augmented generation and error correction. We’ll then discuss how our agents—handling search, diagnostics, charting, and reporting—are orchestrated together to automate analytics requests.

We’ll cover challenges like message routing and long-context management in multi-agent systems. Finally, we’ll showcase real-world applications, demonstrating how these AI agents enhance decision-making and eliminate inefficiencies in enterprise data workflows.
 
Speakers
avatar for David Kucher,

David Kucher,

Principal Engineer, Numbers Station
David Kucher is a Principal Engineer at Numbers Station, where he brings machine learning and AI to automate and improve data tasks. He previously worked on computer vision and ML systems at SambaNova Systems. David holds Bachelor's and Master's degrees in Electrical and Computer... Read More →
Thursday June 5, 2025 1:00pm - 1:25pm PDT
VIRTUAL AI DevSummit Expo Stage

1:30pm PDT

[Virtual] OPEN Session: AI Faster, Better, Cheaper
Thursday June 5, 2025 1:30pm - 1:55pm PDT
Gunveer Gujral, Meta, Senior Staff Software Engineer

Discover practical strategies to accelerate AI development, boost performance, and optimize costs without compromising innovation. Drawing from real-world experiences, this talk will dive into making AI truly scalable. 
Speakers
avatar for Gunveer Gujral

Gunveer Gujral

Senior Staff Software Enginee, Meta
Gunveer is a Senior Staff Software Engineer at Meta, where they lead initiatives in cutting-edge AI for smart wearables. Over the past decade, their work has driven industry-defining AI features in products like Ray-Ban Meta and Oculus Quest.A graduate of Carnegie Mellon University... Read More →
Thursday June 5, 2025 1:30pm - 1:55pm PDT
VIRTUAL DeveloperWeek Leadership Expo Stage

1:30pm PDT

[Virtual] PRO Session: AI Agents in Software Engineering: Can Autonomous AI Teams Build and Maintain Code
Thursday June 5, 2025 1:30pm - 1:55pm PDT
Tanush Sharanarthi, IBM, Staff Software Engineer

AI-powered coding assistants like GitHub Copilot have changed how developers write code, but what if AI could go beyond assisting and work together as a team? This talk explores the potential of multi-agent AI systems, where different AI agents take on specialized roles—one writing code, another reviewing it, a third optimizing performance, and another refactoring—to collaboratively build and maintain software with minimal human input. We’ll dive into real-world applications, emerging research, and the challenges of AI-driven development, from debugging AI-generated code to ensuring reliability. Attendees will gain insight into the future of AI-powered software engineering, whether AI can function as independent development teams, and what this means for the role of human engineers. 
Speakers
avatar for Tanush Sharanarthi

Tanush Sharanarthi

Staff Software Engineer, IBM
Tanush Sharanarthi is a Staff Software Engineer at IBM Silicon Valley Labs with a strong background in software development and artificial intelligence. His work focuses on AI-driven development, large language models, and building intelligent automation systems. He has served as... Read More →
Thursday June 5, 2025 1:30pm - 1:55pm PDT
VIRTUAL AI DevSummit Main Stage
 

Share Modal

Share this link via

Or copy link

Filter sessions
Apply filters to sessions.