← Home
Gradient Dissent · August 12, 2024 · 48m
From Enterprise Search to Agentic AI: Glean's Journey
Arvind Jain discusses Glean's evolution from enterprise search to an agentic AI platform — how understanding organizational knowledge graphs enables AI agents that can act, not just find.
This summary was generated from show notes and public descriptions, not from a full transcript review. Details may contain inaccuracies.
Canon
•
Jain explains that Glean's breakthrough was indexing not just documents but the relationships between documents, people, and workflows. Who created what, who read what, who shared what with whom — the relationship graph is more valuable than the content graph.
Highlights
•
The shift from search to agents in enterprise AI changes the stakes: incorrect search results waste time; incorrect agent actions waste money and trust
Jain describes the stakes increase: when Glean was a search engine, a bad result cost the user 30 seconds. As an agent that can draft emails, schedule meetings, and update databases, a bad action costs real money, damages customer relationships, or violates compliance requirements.Was this useful?