What Glean Is and the Enterprise Graph
How Glean connects your company's work
You'll be able to
- Explain what enterprise search does and how it differs from web search
- Describe the Enterprise Graph as entities and their related signals
Read first
Day 1 Lab
- Pick one project you work on.
- List the entities around it: people, customers, related projects.
- For each entity, name two "signals" — a doc, a ticket, a message, a channel.
- Sketch how those connect. That shape is what the graph models for you.
Working Example: An Entity and Its Signals
The Enterprise Graph models high-value entities and the network of signals around each one. Verified against enterprise_graph.
Entity: Project "Atlas"
├─ People: owner @maya, contributors @raj @lin
├─ Customer: Acme (linked opportunity)
└─ Signals:
• Design doc (Drive) • 12 Jira issues (Sprint 7)
• #atlas Slack channel • 3 support tickets (Zendesk)
• Launch deck (Drive) • PR #482 (GitHub)Search for "Atlas" and Glean can rank these together — not because the word matches, but because the graph knows they belong to the same entity. That relationship is the difference between enterprise search and a keyword box.
Check for understanding
Name one entity and two related signals the graph might connect to it.
Check yourself
1. What does Glean's Enterprise Graph primarily connect?
2. When is a natural-language question better than keywords?
3. Your top result is the wrong TYPE of thing entirely. That is a...
4. What does a result's snippet tell you?
5. What does `type:document onboarding` do?
6. `app:slack quarterly roadmap` returns...
7. In one sentence, what does `from:me` do?
In 10 seconds
“Glean is enterprise search over all your work apps. Its Enterprise Graph links entities — people, projects, customers — to their signals: docs, tickets, messages. That web is why answers feel relevant.”
Keyword vs. Natural-Language Questions