Intuit & Neo4j: Graph-Powered Intelligence: Securing Data & Enhancing GenAI

Join us for an in-person tech meetup focused on real-world applications of graph technology and AI for an evening of fun, networking and food!

Expect sharp talks, technical insights, and open discussion with peers who are building, scaling, and experimenting with graph databases, AI, and modern data systems. Come for the content, stay for the solid conversations, good food, and a chance to connect with other.

RSVP SECURITY NOTE: For building security, you will be asked to enter your First and Last name, and OPTIONALLY, your email address to speed things up with badges upon arrival (INTUIT Security can send you a QR code to speed things up when you arrive. Don’t worry — we won’t use your email for anything else.)

Title: How Intuit Safeguards the Data of 100 Million Customers with Graph Speaker: Zach Probst, Software Engineer, Intuit

In today’s AI age, security threats are becoming more sophisticated and relentless, putting businesses at risk. At Intuit, safeguarding the financial information of over 100 million customers is paramount. To this end, Knowledge Graphs (KGs) have emerged as powerful weapons in our arsenal against these growing threats. Are you curious how this technology revolutionized cybersecurity at Intuit? We’ll unravel the complexities of securing cloud infrastructure by harnessing the power of KGs to improve our incident response times. We’ll also expand our graph to explore how we use Software Bill of Materials (SBOM) and KGs to seek out, prioritize and remediate vulnerabilities on our developer platform. By imparting you with the opportunities we see, we hope you join us in our effort to graph our way to a secure digital frontier.

Title: Vector and GraphRAG: Accuracy and Explainability in GenAI Applications

Speaker: Jennifer Reif, Developer Advocate at Neo4j

Accuracy and explainability are critical in GenAI applications. When information from AI-integrated solutions is inaccurate, it can impact business, people’s health, financial decisions, and even legal policies, which causes cascading repercussions. Having the best data at the right time is vital.

LLMs are not able to handle this on their own, but retrieval augmented generation (RAG) can help by providing curated data as context to an LLM, guiding it to an appropriate answer. This session will explore how vector and graph RAG address the shortcomings of LLMs, explaining their shared functionality as well as some ways they handle it differently. Finally, we will see how to build a GenAI application with RAG to see these concepts in action.