Welcome to the monthly in-person AI meetup in Seattle. Join us for deep dive tech talks on AI, GenAI, LLMs and machine learning, food/drink, networking with speakers and fellow developers.

Agenda:
- 5:00pm~5:50pm: Checkin, food/drink and networking
- 5:50pm~6:00pm: Welcome, Community update
- 6:00pm~7:30pm: Tech talks and Q&A
- 7:30pm~8:00pm: Open discussion and Mixer
- 8:00pm: closing and head to bar

Tech Talk: Enhancing Context Provision for LLMs: Beyond RAG and Prompts
Speaker: Han Wang (Tecton)
Abstract: What is the most effective way to provide context to LLMs? Practitioners often emphasize two main strategies: building vector databases and crafting "optimal" prompts. While both are crucial for the success of Generative AI applications, they have inherent limitations. Vector search relies on similarity, which isn't always the best method for information retrieval. Conversely, incorporating all available context into a single prompt is neither effective nor efficient. In this talk, we will examine various scenarios to illustrate why traditional prompt engineering and Retrieval-Augmented Generation (RAG) approaches fall short. We will explore additional methods for providing context in GenAI applications. Furthermore, we will demonstrate how to leverage Tecton's new GenAI features to rapidly build and test an agentic workflow.

Tech Talk: Multimodal AI and vision inferencing with Gemini
Speaker: Katie Nguyen (Google)
Abstract: What are the applications of multimodality with Gemini? This session will cover a variety of different multimodal use cases with an emphasis on vision inferencing to provide ideas on how you can apply multimodality to practical business scenarios. We'll talk through each of these use cases and demonstrate them with code examples using both Gemini 1.5 Pro and Gemini 1.5 Flash.

Tech Talk: AI or not AI?
Speaker: Satoru Hayasaka (KNIME)
Abstract: The latest innovation in generative AI technology are LLMs. You can exploit LLMs to solve many tasks that were incredibly challenging just last year. Some say you can solve anything with GenAI. Or can you? Recently, I decided to reshape an old application of mine for fraud detection, by introducing AI in it. The application dealt with finding contracts with suspicion of frauds and then to alert the affected customers of the issue. The applications had three main parts: accessing the contracts; discovering suspicious frauds; creating and sending the alert email in the customer's preferred language. I tried to introduce AI in all those parts, sometimes successfully, sometimes unsuccessfully. This talk is a summary of both my successful and failed attempts to solve everything with AI.

Speakers/Topics:
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, 10900 NE 4th St, Floor 21, Bellevue, WA 98004

Sponsors:
We are actively seeking sponsors to support AI developers community.  Whether it is by offering venue spaces, providing food, or cash sponsorship. Sponsors will not only speak at the meetups, receive prominent recognition, but also gain exposure to our extensive membership base of 20,000+ AI developers in Seattle or 400K+ worldwide.

Community on Slack/Discord
- Event chat: chat and connect with speakers and attendees
- Sharing blogs, events, job openings, projects collaborations
Join Slack (search and join the #seattle channel) | Join Discord