Software Engineering Daily

Agentic AI at Glean with Eddie Zhou

Apr 22, 2025

Eddie Zhou, a founding engineer at Glean and a former Google employee, dives into the dynamic world of agentic AI. He discusses how Glean has evolved from a basic search tool to a robust platform enhancing productivity through AI. The conversation covers the integration of AI with enterprise data, the challenges of task delegation in multi-agent systems, and the importance of personalized search capabilities. Zhou also highlights the balance between innovation and efficiency in AI development, emphasizing the need for thorough evaluation frameworks in implementing new systems.

43:17

Creator website

Episode guests

Eddie Zhou

AI Summary

AI Chapters

Episode notes

Podcast summary created with Snipd AI

Quick takeaways

Glean has evolved from a simple search tool to a reasoning agent that enhances productivity by anticipating users' needs and enabling actionable insights.

The effectiveness of agentic AI systems hinges on the quality and context of the data accessed, emphasizing the importance of company-specific knowledge integration.

Deep dives

Evolution of Glean's Vision

Glean started as an enterprise search solution aimed at improving knowledge workers' access to information. Initially, the focus was on streamlining the process of searching for data relevant to tasks, but the vision has since expanded to include a reasoning agent that can assist with decision-making and productivity. This evolution reflects a broader understanding of users' journeys, as Glean now aims to help users by anticipating their informational needs and enabling them to act on the information they retrieve. By assisting with tasks both before and after information retrieval, Glean reinforces its commitment to enhancing the efficiency of knowledge workers.

Intro

3min

Navigating Agentic AI in Enterprises

14min

Navigating the Complexities of Agent Systems

4min

Navigating Tool Limitations and Personalized Search in AI Agents

3min

Navigating Identity in Multi-Agent Systems

7min

Balancing Innovation and Efficiency in AI Development

3min

Evaluating AI: Balancing Metrics and Insights

9min

Glean is a workplace search and knowledge discovery company that helps organizations find and access information across various internal tools and data sources. Their platform uses AI to provide personalized search results to assist members of an organization in retrieving relevant documents, emails, and conversations. The rise of LLM-based agentic reasoning systems now presents new opportunities to build advanced functionality using an organization’s internal data.

Eddie Zhou is a founding engineer at Glean and previously worked at Google. He joined Sean Falconer to discuss the engineering and design considerations around building agentic tooling to enhance productivity and decision-making.

Sean’s been an academic, startup founder, and Googler. He has published works covering a wide range of topics from AI to quantum computing. Currently, Sean is an AI Entrepreneur in Residence at Confluent where he works on AI strategy and thought leadership. You can connect with Sean on LinkedIn.