"Glean Chat offers an experience very similar to OpenAI's ChatGPT, but limited to an enterprise's content and resource boundaries, Jain said. When a user makes a natural language-based query, the company's search technology uses APIs to check all the content and activity - including information in applications - pertaining to the query before storing it in a customer's cloud environment. The data stored is then fed to large language models (LLMs), which have been trained on that particular enterprise's data,"
"Glean is built on five layers consisting of infrastructure, connectors, a governance engine, the company's knowledge graph, and an adaptive AI layer, according to the company. In order to connect to an enterprise's applications and content repositories, Glean Chat uses its self-developed connectors to link to applications and data sources such as Salesforce, Zendesk, Jira, GitHub, Slack, Figma, Workday, Okta, Outlook, OneDrive, Google Drive, Box, Dropbox, SharePoint, as well as storage offerings from AWS, Google Cloud, and Microsoft among others."
Glean Chat is a generative-AI assistant add-on that enables conversational search across an enterprise's applications and content repositories while returning source-cited results. The system queries connected applications and activity via APIs, stores relevant data in the customer's cloud, and feeds that data to LLMs trained on the enterprise's data to produce results. Results include links to source information from documents, conversations, and applications. The architecture layers infrastructure, connectors, a governance engine, a knowledge graph, and an adaptive AI layer. Self-developed connectors integrate many SaaS apps and cloud storage providers. A governance layer enforces enterprise security and policy boundaries.
Read at Computerworld
Unable to calculate read time
Collection
[
|
...
]