Optional introductory course for AI Engineers, free for all Summit attendees. Build 5 small projects c...

Noah Hein

AI Engineering 101

[Must preregister, limited to 100 signups] [SOLD OUT - will release recordings on YouTube, please subscribe] Learn from first principles how to fine-tune open-source Llama-2 models.

Mark Huang

Finetuning Lunch & Learn

[Must preregister, limited to 50 signups] Free for preregistered Summit attendees. Learn the state of the art on prompt engineering from experience leading engineering on Anthropic Claude.

Karina Nguyen

Writing Principles for Task-Tuned Prompt Engineering

[Must preregister, limited to 50 signups] Introductory course for AI Engineers, free for preregistered Summit attendees. Advanced knowledge of AI Engineering, led by instructor Charles Frye of the massively popular Full Stack LLM Bootcamp.

Charles Frye

AI Engineering 201

Head up the lobby escalators to the second floor to pick up your badge and swag bag! Badges are required to attend the welcome reception.

Registration opens

Join us at Hotel Nikko in the lobby, Kan Pai Lounge, and Feinstein's Club for an epic welcome reception! Meet with speakers, sponsors, and fellow attendees over a bite and a cocktail or mocktail -- plus a live Jazz Quintet -- courtesy of Microsoft!

The Microsoft Welcome Reception

AutoGPT is the fastest growing open source project in history. Learn to build the next generation of AutoGPTs with AutoGPT Forge and join the largest open source community of AI Agent builders in the world!

Reinier van der Leer

Craig Siwift

Workshop: Introduction to Agent Development

This workshop will guide you through this development process. You'll start with the basic RAG stack, create an initial evaluation suite, and then experiment with different advanced techniques to improve RAG performance.

Simon Suo

Workshop: Building, Evaluating, and Optimizing your RAG App for Production

AI.JSX is the best way for JavaScript developers to bring the power of LLMs to applications. This workshop will teach you how to build production-grade Sidekicks that use RAG, Tools, and Generative UI...

Ben Lower

Justin Uberti

Workshop: Building a RAG powered, multi-modal Sidekick using AI.JSX

Learn how to best use OpenAI function calling within LangChain to do structured data extraction and build agents, with LangSmith access!

Harrison Chase

Logan Kilpatrick

R. Lance Martin

Workshop: Function calling and tool usage with LangChain and OpenAI

In this workshop you'll learn how to build a secure and production-ready pgvector powered webapp using Supabase Vector.

Greg Richardson

Workshop: Pgvector to Prod in 2 hours

AutoGPT is the fastest growing open source project in history. Now, for the next step: Learn how to improve your agents and beat benchmarks with Evals-Driven Development!

Silen Naihin

Merwane Hamadi

Workshop: Advanced Evals-Driven Development

Benjamin Dunphy, co-founder of the AI Engineer Summit and managing partner at Software 3.0, LLC, welcomes attendees to the Summit, and makes a few key announcements for the event's software app, Network. 

Benjamin Dunphy

Announcing the AI Engineer Network

Born too late to explore the earth. Born too early to explore the stars. Just in time to bring AI to everyone.

swyx

The 1000x AI Engineer

What is the future of Software Engineering in the age of AI? Amjad Masad, Founder & CEO of Replit, and Michele Catasta, head of AI at Replit, provide their take on this in this opening keynote presentation from the AI Engineer Summit 2023.

Amjad Masad

Michele Catasta

Building AI For All

Join Toran, the visionary behind the wildly popular open-source project AutoGPT, as he navigates the next phase of AutoGPT's journey.

Toran Bruce Richards

The Future of Work

We're heading towards a multimodal world.

Simón Fishman

See, Hear, Speak, Draw

How will ubiquitous AI agents impact our daily lives, and what do they mean for the future of computing?

Flo Crivello

The Age of the Agent

It wouldn't be a good conference without one...

Barr Yaron

Sasha Sheng

One Smol Thing

Housekeeping

Join us in the Expo on the 3rd floor to meet with the companies driving innovation for AI Engineering.

Food & Expo

How can companies best build useful and differentiated applications on top of language models?

Building Context-Aware Reasoning Applications with LangChain and LangSmith

Please return only json, do not add any other comments ONLY RETURN JSON OR I'LL TAKE A LIFE.

Jason Liu

Pydantic is all you need

What are some building blocks for integrating LLMs into production systems and customer-facing products? In this talk, we'll discuss evals, RAG, guardrails, and collecting feedback.

Eugene Yan

Building Blocks for LLM Systems & Products

This talk will be a grand tour through a series of experimental projects from my last two years of research for visualizing, manipulating, and interpreting embeddings.

Linus Lee

The Hidden Life of Embeddings

Turning your company into an AI company — from two of the best this year!

Brittany Walker

Chris White

Bryan Bischof

The AI Pivot: Fireside chat with Chris White of Prefect & Bryan Bischof of Hex

Your turn to talk! The crowd favorite feature of our conferences is an unconference-style freeform session where you can connect with...

Topic Tables, Expo, F&B

Join us in the 3rd floor expo hall for breakfast and chat with other attendees, sponsors, and speakers!

Breakfast and Expo

Let's get settled in to Day 2 and get ready for a day of jam-packed content & connections!

Welcome & Introduction

How AI is transforming how the world builds software together

Mario Rodriguez

Keynote: The AI Evolution

Why we need Agents writing Tests faster than Humans writing Code

Dedy Kredo

Move Fast Break Nothing

AI.JSX is like React for LLMs -- it lets you build powerful, conversational AI apps using the power of TypeScript and JSX.

Matt Welsh

Building Reactive AI Apps

How might we use AI to build products focused not just on working faster, but on transforming how we work?

Amelia Wattenberger

Climbing the Ladder of Abstraction

On building AI Products From First Principles

Samantha Whitmore

Jason Yuan

The Intelligent Interface

Discuss the morning's talks with your fellow attendees, speakers, and sponsors in the expo hall!

Morning Break & Expo

How *YOU* can - and should - build great multimodal AI apps that go viral and scale to millions in a weekend.

Hassan El Mghari

The Weekend AI Engineer

On the many trials and successes of building with multimodal apps with vision foundation models!

Joseph Nelson

120k players in a week: Lessons from the first viral CLIP app

Every month, thousands of new AI applications are launched on Supabase, powered by pgvector.

Paul Copplestone

Supabase Vector: The Postgres Vector database

Head to the 25th floor or the 2nd floor Anzu Restaurant to enjoy your provided lunch! Both locations are providing the same options.

Lunch

TypeChat is an experimental library to bridge the unstructured output of language models to the structured world of our code.

Daniel Rosenwasser

Pragmatic AI With TypeChat

Learn the different fine-tuning methods depending on the dataset, operational best practices for fine-tuning, how to evaluate them for specific business use-cases, and more.

Abi Aryan

Domain adaptation and fine-tuning for domain-specific LLMs

In the last few months, we've seen an explosion of the use of retrieval in the context of AI. Document question answering, autonomous agents, and more use embeddings-based retrieval systems in a variety of ways.

Anton Troynikov

Retrieval Augmented Generation in the Wild

In this talk, we talk about core techniques for evaluating and improving your retrieval systems for better performing RAG.

Jerry Liu

Building Production-Ready RAG Applications

 Break

Discover llm, a revolutionary Rust library that enables developers to harness the potential of large language models (LLMs) locally...

Mithun Hunsur

Harnessing the Power of LLMs Locally

Making Large Language Models Production-Ready with Guardrails

Shreya Rajpal

Trust, but Verify

Recapping the past year in AI, and what open questions are *worth pursuing* in the next year! Covering local models, transparency, tool usage, prompt injection. Please will SOMEBODY solve these??

Simon Willison

Open Questions for AI Engineering

Thank you

Join us in the expo hall for an exciting conclusion to the conference, courtesy of Alessio Fanelli & Decibel VC!

Decibel VC Afterparty

In this cutting-edge workshop, participants will embark on a transformative journey into the world of Vector Search, exploring two compelling applications: Retrieval-Augmented Generation (RAG)...

Patrick McFadin

Workshop: Unlocking the Power of Vector Search: RAG for AI Chatbots and Image Search with CLIP

Come join us as we walk through how you can use GitHub to manage your DevOps processes with AI to accelerate your development. ( And yes, there will be plenty to talk about with GitHub Copilot!)

Christopher Harrison

Workshop: Streamline coding with GitHub with Christopher Harrison

Matija Sosic

GPT Web App Generator

Developing a sophisticated AI application often involves integrating diverse models and tools. Using ModelFusion, this complexity can be streamlined. In this talk, Lars Grammel will take attendees through the journey of creating a kids' story generator...

Lars Grammel

Storyteller

Making a game requires creating lots of content - tons of cheap and disposable ideas while prototyping, and a vast (or infinite?) depth of content to explore while playing...

Jeff Schomay

Using AI to Build an Infinite Game

"Swyx’s watershed essay “The Rise of the AI Engineer” revealed the need for evolving your talents to seize the opportunities of the future; but how can you rapidly learn a novel discipline mired in lack of structure, fluff, & clickbait? ...

Reid Mayo

Shift Left: How to Become an AI Engineer from a Fullstack Background

Ado Kukic

The Code AI Maturity Model and What It Means For You

Fine-tuning LLMs requires a lot of resources, both memory and GPU, which are notoriously costly. In this talk, I will describe five ways to minimize resource usage, and to find the cheapest resources out there to fine-tune LLMs with a tight budget.

Emmanuel Turlay

How to evaluate a model for your use case

I will explain what fine-tuning is, why it's the next practical step to take from prompt engineering, its benefits for production deployments, and how modern AI Engineers can now do it with zero code.

Mark Hennings

No-code Fine-tuning

Niklas Quarfot Nielsen

Scaling Reliability of LLM Applications

Jesse Han

Morph: The Rise of the AI Software Engineer

Everything is going well until a prompt that works most of the time, goes off the rails. Does this sound familiar? The inherent fragility and non-deterministic nature of prompts can be challenging, often leading to inconsistent outputs...

Schedule