Relevance Labs - 02
Topic: Talk 2 Blurb
How to iterate on AI agents quickly with Modal Labs
This is a hybrid event - you can either attend using the g-meet link or join us in person at Relevance HQ.
Address: 132 Kippax Street, Surry Hills, NSW
Google link: https://meet.google.com/dxh-wzer-wkp
AI Enthusiasts, welcome to the second Relevance Labs Meetup!
At our first event, we took a deep dive into our Inventor Agent. A meta-agent designed to build other agents and tools on our platform.
But, have you ever wondered what kind of software infrastructure is needed to power our Invent Agent?
Modal Labs is a platform for running serverless applications service specializing in making this seamless and has empowered our AI engineering team to deploy with speed. Whether you are beginner, a seasoned pro, or somewhere in between, if you’re interested in an AI agent tech stack that works, this is the talk for you!
Some of the key software infrastructure challenges that developers face when building AI agents -
How do you iterate quickly? The AI game changes daily, how can you respond to these changes and continue to stay up to date with State Of The Art methods?
How do you evaluate? Evaluation is everything. Without understanding how your agents are performing, recognizing problems and implementing improvements is impossible.
How do we make the Inventor Agent fast? Slow response times frustrate users—what does it take to keep agents snappy and efficient?
How do you set up your agents safely? Agents should only access permitted data, and AI-generated code must be executed securely.
How do you scale? As your AI agents gain traction, they must seamlessly handle increasing demand. How do you ensure smooth scaling without compromising performance or security?
For this event, our AI Engineer, Charlie, will be sharing how Modal Labs has accelerated our Invent progress.
Join us at the second Relevance Labs Meetup to explore these challenges—and the infrastructure solutions that make it all possible!
Looking forward to meeting you.
Agenda
5:30pm: Arrive, get to know your peers.
6pm: Relevance Labs & Speaker introduction
6:10pm: How to iterate on AI agents quickly with Modal Labs
6:40pm: Q/A Panel
7:30pm: Wrap-up