Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Building Glean and the Future of Enterprise AI

Weights & Biases via YouTube

Overview

Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore the evolution of enterprise AI through this 44-minute podcast episode featuring Arvind Jain, CEO and founder of Glean, discussing his company's journey from enterprise search to building agentic AI tools. Learn how Jain's early adoption of transformer models in 2019 positioned Glean for success before generative AI became mainstream, and discover the technical foundations that enabled the company's transformation from search to comprehensive AI-powered enterprise solutions. Examine the critical challenges of implementing enterprise LLMs, including security considerations, hallucination suppression techniques, and strategic decisions around model fine-tuning versus using out-of-the-box solutions. Gain insights into the practical applications of small, purpose-trained models and understand the security implications of embedding enterprise data. Discover Jain's entrepreneurial journey, including lessons learned from his previous startup Rubrik and the contrarian bet he made on enterprise search when it wasn't considered a promising market. Understand how Google's culture influenced his approach to building teams and products, and explore his vision for the future where every professional will have access to AI-powered teams that can maintain evergreen documentation, perform churn analysis, and act as force multipliers rather than replacements for human workers. Learn about practical implementation strategies including golden set methodologies for measuring model improvements, citation-based approaches to reducing hallucinations, and designing AI agents that know when to escalate to human assistance.

Syllabus

0:00 Intro
01:00 What Glean is and how it works
02:39 Starting Glean before the LLM boom
04:10 Using transformers early in enterprise search
06:48 Semantic search vs. generative answers
08:13 When to fine-tune vs. use out-of-box models
12:38 The value of small, purpose-trained models
13:04 Enterprise security and embedding risks
16:31 Lessons from Rubrik and starting Glean
19:31 The contrarian bet on enterprise search
22:57 Culture and lessons learned from Google
25:13 Everyone will have their own AI-powered "team"
28:43 Using AI to keep documentation evergreen
31:22 AI-generated churn and risk analysis
33:55 Measuring model improvement with golden sets
36:05 Suppressing hallucinations with citations
39:22 Agents that can ping humans for help
40:41 AI as a force multiplier, not a replacement
42:26 The enduring value of hard work

Taught by

Weights & Biases

Reviews

Start your review of Building Glean and the Future of Enterprise AI

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.