
Join us for a power-packed night of learning, sharing, and networking at AI Dev Day - San Francisco. We are excited to bring the AI developer community together to learn and discuss the latest trends, practical experiences, and best practices in the field of AI, LLMs, generative AI, and machine learning.
In addition to the tech talks, there will be plenty of opportunities to network with AI developers, live demos by AI startups, panel discussion, and career opportunities.
Agenda:
- 4:30pm~5:30pm: Checkin, food/drink and networking
- 5:30pm~8:00pm: Tech talks, and panel
- 8:00pm: open discussion, mixer
Tech Talk 1: From Generic To Genius: Personalize Generative AI
Speaker: Ryan Michael, VP of Engineering @Kaskada
Abstract: Generative AI has already demonstrated immense value, but systems like ChatGPT don’t know anything about who we are as individuals. At Kaskada, we have developed a compute engine to help LLM’s understand who they’re talking to and what they’re talking about. Kaskada does this by augmenting prompts with real-time contextual information and making it easy to recreate the context of past prompts, significantly accelerating the prompt engineering process. In this talk, we introduce the abstraction that makes this possible: the concept of timelines. Timelines can be interpreted as a history of changes or as snapshots at specific time points.
Tech Talk 2: Astra DB and JSON API: The Next Chapter for JS AI Developers
Speaker: Val Kulichenko @DataStax
Abstract: Generative AI development is moving fast. Every day, new applications are popping up, demanding rapid development and iteration. In this environment, there is no room for a steep learning curve. A Generative AI platform needs to offer a quick and easy development start, without the fuss of operations, data modeling, and so forth. This is why we introduce the JSON API for Astra DB. It is an HTTP-based API that showcases Astra DB as a document database, complete with vector search capabilities. With this API, diving into AI application development is immediate—just set up a database and get coding. What is more, the API is aligned with MongooseJS, a popular library many regard as the go-to for handling document databases.
Join this talk to learn about the capabilities of the newly introduced JSON API for Astra DB, and discover how you can harness its power to swiftly embark on creating cutting-edge Generative AI applications.
Tech Talk 3: Evaluating LLM Agents
Speaker: Shayak Sen @TruEra
Abstract: In a LLM-powered autonomous agent system, LLM functions as the agent’s brain by using planning and inference to decide what tools to use and how. As requests to your agent drift, evaluation is needed to identify gaps in tool coverage and keep the agent performing. This talk will cover the basics of building an LLM agent and how to evaluate it with open-source TruLens
Stay tuned as we are updating speakers and schedules.
If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics
Venue:
GitHub, 88 Colin P Kelly Junior Street, San Francisco, CA
How to find us: the entrance is located at 275 Brannan st.
Lucky draw
We will raffle winners for prizes during the event. To enter the lucky draw, "comment" the post on LinkedIn: LinkedIn Post
Sponsors:
Community on Slack
- Event chat: chat and connect with speakers and attendees
- Sharing blogs, events, job openings, projects collaborations
Join Slack (search and join the #sanfrancisco channel)
Community Partners:
Contact us if you are interested in partnership.