Production-ready AI Agents Hackathon @ AI By the Bay
Join us for a 2-day hackathon dedicated to building production-ready AI Agents that can accomplish something amazing in a business-to-business or business-to-consumer use case.
All Hackathon Attendees must be pre-registered here on Luma & DevPost.
Review Hackathon Instruction here!
THE CHALLENGE
You will need to make sure your agent is maintainable, scalable, and observable and also secure by design, i.e., safe from agent-related attack vectors (prompt injection, data exfiltration, privilege escalation, broken access controls, etc).
You will need to illustrate how your agent accomplishes these production-ready tasks while still providing access to business data and processes. Bonus points if you use tools to validate the production readiness of your agent.
WHO SHOULD ATTEND
Developers looking to build their next production-ready AI agent project, alongside the best software engineers and legends within the Bay Area and beyond.
Max team size is 5. No team? No problem. We’ll help match you with others at the event. At least 30% of the team should come in person.
All attendees must be registered and approved on Luma.
We’d be happy to help you make the case to your manager about the value of participating in our hackathon. Just email us at [email protected], and we’ll send you key points you can share.
AGENDA
Subject to change.
Tue, Nov 18
9:00 am – 10:00 am | Onboarding, registration, coffee
10:00 am – 10:30 am | Kickoff, rules, safety/CoC
12:30 pm - 1:30 pm | Lunch
Mentor office hours 11:00 am - 4:00 pm
Who and Where:
Hugh McKee - Akka booth
Claire Longo- Comet booth
Chandler Mayo - Redpanda booth
Fred Patton - Auth0 (Okta) booth
Jeremy Adams - Hackathon Mentor Zone
Francis Bouvier- Hackathon Mentor Zone
3:30 pm - 4:00 pm | Coffee break
6:00 pm | Happy Hour
7:00 pm | Doors close
Wed, Nov 19
8:00 am | Doors open, coffee
Mentor office hours (+ more details soon)
11:00 am | Submissions due (repo + 3-min demo video)
11:00 am - 1:30 pm | Online Judging
12:30 pm - 1:30 pm | Lunch
1:30 pm - 3:00 pm | In-Person Judging (a team representative has to be at the venue)
3:00 pm – 4:10 pm | Finalist lightning demos - will be recorded and posted on our YouTube channel
4:10 pm - 4:40 pm | Coffee Break
4:40 pm – 5:10 pm | Closing panel with judges
5:10 pm – 5:20 pm | Awards + group photo
5:20 pm – 5:40 pm | Closing remarks
CREDITS
- AWS accounts will be provided enabling you to pick from numerous hosted Amazon Bedrock models and compute environments.
MENTORS & JUDGES
While participants are free to use any frameworks and tools they prefer, we will have an experienced group of mentors and judges on site to provide guidance.
Vaibhav Gupta leads Boundary (YC w23), he hates ugly code. And as we know, most agent systems out there wouldn't pass a code review. So Viabhav is building BAML for clean, reliable AI infra. [AI that works podcast]
Isaac Miller is a long-time core contributor for DSPy, working on typing, fine-tuning, RL infra, and multi-modal support.
Hugh McKee is a skilled developer advocate with decades of experience building enterprise applications. Hugh is an expert in distributed systems and Akka, and can help connect all the dots!
Claire Longo is a mathematician and AI leader currently serving as Lead AI Researcher at Comet. She’s led teams at Twilio, Opendoor, and Arize AI, mentors engineers, and actively champions diversity in AI.
Jeremy Adams is a Senior Developer Advocate at Neo4j who blends deep technical understanding with strategic insight. He’s passionate about people, entrepreneurship, integration, and automation, and has worked across technical and business roles at Dagger, GitHub, Twistlock, and Puppet.
Fred Patton is a Senior Developer Advocate at Auth0 for Okta. He helps teams design AI systems that are scalable, accountable, and identity-aware. Prior to Auth0, he led developer-facing work on streaming data platforms at Nstream (formerly Swim.ai), working in security and healthtech.
Prashanth Rao is an AI engineer at LanceDB. He's spent a lot of time working on use cases related to RAG, knowledge graphs, vector search, and incorporating them as tools for agents using modern frameworks like DSPy and BAML. He writes about these techniques on his blog, thedataquarry.com.
Gaurav Jain is a Senior Staff Engineer at Pure Storage, where he leads the customer-facing GenAI Copilot initiative. A Carnegie Mellon alumnus, he combines broad engineering perspective with deep expertise in large-scale systems, applied AI, and building production-ready, enterprise-grade agents.
Mahati Kumar is a Senior Staff Engineer at Meta, where she leads teams building next-generation mobile and metaverse products. She’s passionate about 0→1 innovation, scalable systems, and mentoring builders at the intersection of tech and creativity.
Rushabh Mehta has led impactful AI Infra initiatives across 12 years at Big Tech. Most recently he has contributed to LLM Post training platform, Agents & Evals unlocking 100+ use cases across the company.
Vasusen Patil is the technical CEO @ Donobu, bringing 15y of tech experience. He has a rich background in scaling engineering teams and products, notably at WePay and Coursera, where he organized large-scale AI hackathons. His current work at Donobu focuses on AI-driven quality assurance, making him a perfect fit for judging this hackathon focused on production-ready AI agents.
Peter Corless is a Principal Product Marketing Manager at Redpanda. He has worked across a broad spectrum of the data industry over the past decade: real-time data streaming, as well as distributed databases, OLTP and OLAP, SQL and NoSQL. He recently wrote an O'Reilly book on Open Source Observability.
Tosh Rayadhurgam is a Senior Engineering Leader (EM) for Foundational AI and Ranking at Meta. With 12+ years of experience at Meta, Lyft, and Amazon Lab126, he specializes in AI-powered recommendation systems, productionizing LLMs, and scaling generative AI from proof-of-concept to production. He is also an active angel investor in AI startups including Langlify, Overview, Overtune, and Adalflow/Sylph AI.
Michael Maximilien is a Distinguished Engineer and leader for the teams contributing to OSS AI at IBM Research, holding masters and Ph.D. in CS. His main expertise is in software engineering and distributed systems.
Chandler Mayo is a Developer Relations Lead at Redpanda, leveraging a strong technical background to build thriving developer communities, drive product adoption, and empower engineers to innovate with confidence.
Francis Bouvier is CEO and co-founder of Lightpanda, a machine-first web browser inspired by his experience building BlueBoard (acquired by ChannelAdvisor in 2020).
Mentors are also familiar with MCP which you may want to use for data/process integration.
Please keep in mind, the mentoring and technical support are available but limited. Your team should have all the skills to troubleshoot any technical issues otherwise.
RUBRIC
Projects will be evaluated on production readiness, innovation, technical complexity, practicality, user experience, and overall quality. A detailed judging rubric can be found here.
AWARDS
Top 5 winners will have an opportunity to demo their projects on the main stage of the AI By the Bay conference.
🔥 Prize: $2000 1st, $1000 2nd, $1000 3rd. Top teams give lightning talks on the main stage.
USEFUL RESOURCES TO GET STARTED
Spring AI Project, Docs, Short Intro, Samples on GitHub
Josh's talks on Spring AI Session with James Session at SFJava
Rod Johnson's take Docs, Embabel Agent on GitHub, Blog
Amazon Bedrock Docs
Langchain4j Docs, Repo of Examples
DSPy Video
RAG in DSPy, Optimizing a program for math reasoning, Building an Agent with DSPy
Omar Khattab, DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
Akka, What is Agentic AI?, Agentic tutorials and AI app samples
SUPPORT US EVEN MORE!
Interested in partnering? Email [email protected]