In this session, dbt product manager Jordan Stein will discuss how the dbt Semantic Layer is evolving to provide fast, trusted data for downstream stakeholders. Jordan will cover new features, integrations, and use cases across BI, embedded analytics, and LLMs. Brightside Health will share their experience, showcasing how they use the Semantic Layer to deliver fast, reliable, and secure embedded analytics to their customers.

Speakers: Jordan Stein Product Manager dbt Labs

Hans Nelsen CDO Brightside Health

Read the blog to learn about the latest dbt Cloud features announced at Coalesce, designed to help organizations embrace analytics best practices at scale https://www.getdbt.com/blog/coalesce-2024-product-announcements

In this talk, we will make the case that the success of enterprise AI depends on an investment in semantics and knowledge, not just data. Our LLM Accuracy benchmark research provided evidence that by layering semantic layers/knowledge graphs on enterprise SQL databases increases the accuracy of LLMs at least 4X for question answering. This work has been reproduced and validated by many others, including dbt labs. It's fantastic that semantics and knowledge are getting the attention it deserves. We need more.

This talk is targeted to 1) those who believe AI accuracy can be improved by simply adding more data to fine-tune/train models, and 2) the believers in semantics and knowledge who need help getting executive buy-in.

We will dive into: - the knowledge engineering work that needs to be done - who should be leading this work (hint: analytics engineers) - what companies lose by not doing this knowledge engineering work

Speaker: Juan Sequeda Principal Scientist and Head of AI Lab data.world

Read the blog to learn about the latest dbt Cloud features announced at Coalesce, designed to help organizations embrace analytics best practices at scale https://www.getdbt.com/blog/coalesce-2024-product-announcements

There is a lot of talk when it comes to how LLMs can best be deployed in the analytics space. What are implementation best practices? Are LLMs best suited with text-to-SQL or with a Semantic Layer underneath providing proper constraints?

These are fun discussions to have, but LLMs also present a massive opportunity for companies beyond normal analytics work. The team at Newfront has been building LLM-powered products for clients that are external facing, using a cross-functional group that consists of many data team members.

In this talk, they'll go over where data professionals fit best in building these sorts of products and how to get started in participating in direct value generation for your business.

Speaker: Patrick Miller Head of Data & AI Newfront

Read the blog to learn about the latest dbt Cloud features announced at Coalesce, designed to help organizations embrace analytics best practices at scale https://www.getdbt.com/blog/coalesce-2024-product-announcements

Entities, dimensions, and metrics. These things play crucial roles in allowing companies to create meaningful pictures of their data.

Max has spent the last 2.5 years using dbt with two different cleantech startups, experience he draws on to inform his approach to the challenge of matching and maintaining entities for more robust semantics. This talk will delve into the practical aspects of using the dbt Semantic Layer and Dot an LLM Slack plugin to provide matched insights directly to team members at Topanga.io.

Expect to learn about best practices in self-service, LLMs, data governance, and how to leverage the dbt Semantic Layer effectively. It’s a session geared toward beginners, intermediates, and pros alike

Speaker: Max Richman Head of Data and Financial Analysis Topanga.io

Read the blog to learn about the latest dbt Cloud features announced at Coalesce, designed to help organizations embrace analytics best practices at scale https://www.getdbt.com/blog/coalesce-2024-product-announcements

Have you ever wanted to build an AI chatbot to query your data platform? Transforming a business user's natural language question into a valid SQL query that answers their question has huge potential to unlock improved self-service analytics. However, even state-of-the-art LLMs are prone to hallucination, which makes it hard to generate SQL queries that are both conceptually and syntactically correct.

In this talk, you'll learn how the team at M1 Finance tackled this problem using MetricFlow’s rich semantic modeling along with LLM-based tool invocation. This approach enables them to reliably produce valid SQL queries from natural language questions, avoiding issues of hallucination or incorrect metrics.

Speakers: Kelly Wolinetz Senior Data Engineer M1 Finance

Brady Dauzat Machine Learning Engineer M1

Read the blog to learn about the latest dbt Cloud features announced at Coalesce, designed to help organizations embrace analytics best practices at scale https://www.getdbt.com/blog/coalesce-2024-product-announcements

Jonny will showcase how the team at EQT, one of the world's largest private equity firms, is leveraging the dbt Discovery API, data contracts, tagging, and other dbt features to power discovery through their intranet — and by extension, how this also enables the team to support LLMs for live querying of their data.

Speaker: Jonny Reichwald Analytics Lead EQT

Read the blog to learn about the latest dbt Cloud features announced at Coalesce, designed to help organizations embrace analytics best practices at scale https://www.getdbt.com/blog/coalesce-2024-product-announcements

This session is a practical guide to changing how you operate in response to the Cambrian explosion of AI and LLM technologies. In your future, everyone at the company will have access to an LLM with unfettered access to your data warehouse. Do you feel afraid? The Data team at Hex did too. They'll share how they had to change how they worked to adapt, and what data leaders and practitioners need to be thinking about for their own teams.

Speakers: Amanda Fioritto Senior Analytics Engineer Hex Technologies

Erika Pullum Analytics Engineer Hex Technologies

Read the blog to learn about the latest dbt Cloud features announced at Coalesce, designed to help organizations embrace analytics best practices at scale https://www.getdbt.com/blog/coalesce-2024-product-announcements