OpenAI & GenAI Israel - LLM Engineering

OpenAI & GenAI Israel - LLM Engineering Event!
Date: Tue Apr 02 2024
Time: 17:00
Location: Totseret ha-Arets St 7
Come join us for an evening of innovation and collaboration at our LLM Engineering event! This is a great opportunity to network with like-minded individuals and learn about the latest advancements in AI technology. Whether you're a seasoned professional or just starting out in the field, this event will inspire and educate you. Don't miss out on this exciting opportunity to be a part of the future of AI in Israel!

#### Agenda:

### Building LLM-native apps with The Magic Triangle blueprint

In this talk, we explore the exciting yet challenging domain of Large Language Models (LLMs) in artificial intelligence. LLMs, with their vast potential for automating complex tasks and generating human-like text, have ushered in a new frontier in AI. However, the journey from initial experimentation to developing proficient, reliable applications is fraught with obstacles. The present landscape, akin to a Wild West, sees many stakeholders hastily crafting naive solutions that often underperform and fall short of expectations.

Addressing this disparity, we introduce the “Magic Triangle,” an architectural blueprint for navigating the intricate realm of LLM-driven product development. This framework is anchored on three core principles: Standard Operation Procedure(SOP), Prompt Engineering Techniques (PET), and Relevant Context. These principles collectively provide a structured approach for building robust and reliable LLM-driven applications.

#### About the speaker: Almog Baku

A seasoned tech and AI entrepreneur, currently acting as a consultant for LLM projects for serval Startups.

### Unlocking AI's Endless Opportunities with "Schematic Questioning"

Lili offers financial services for small businesses. To solve this, Lili introduced AccountantAI, which leverages businesses' financial data and accounting expertise to provide real-time answers to customer queries, just like a human accountant. This might sound like a straightforward solution, but in reality, it's a pretty tough challenge, especially when it comes to financial aspects.

In the session, we'll discuss our solution architecture and how we built the AI pipeline, which creates unique value for customers that cannot be achieved with other generic solutions. For that, we introduced a methodology that we call “schematic questioning”.

We’ll delve into the prompt engineering lifecycle and our solutions for handling non-legitimate questions while keeping a free text experience without limitations. Additionally, as a Fintech company, we’ll share our journey in tackling numerous regulations and how successfully we have provided customer-facing, real-time AI advisors.

#### About the speakers:

• Eyal Solnik, head of the Data group at Lili, with over a decade of experience leading data science and analytics teams in Fintech.
• Lior Polat, data scientist at Lili.