Channel Insider content and product recommendations are editorially independent. We may make money when you click on links to our partners. View our editorial policy here.

Glean, a work AI platform, recently announced the expansion of Glean Agents, an open, horizontal environment for building, deploying, orchestrating, and governing AI agents at work.

Glean’s AI agents are developed with broad LLM choice, expanded MCP server support for agent interoperability, complex workflow automation, and built-in governance. These are secure and enterprise-ready to enable employees and teams to build, use, and scale agents.

“AI agents should be in the hands of every employee and driving outcomes across the entire enterprise,” said Arvind Jain, Founder and CEO of Glean. “Glean Agents turns that vision into a reality with an open, interoperable platform that integrates across systems, supports leading LLMs, and makes it easy to build and scale agents that actually move the business forward.”

The expansion gives enterprises more tools to move beyond the experimentation phase of Agentic AI and to operationalize agents among employees and departmental workflows with visibility, control, and trust for enterprise success.

Glean provides enterprises with control over where their AI agents run and which models they use, enabling them to experiment, adapt, and adopt the latest AI innovations without lock-in.

The features of Glean Agents environment include:

• Democratized access to agents: Glean’s natural language agent builder enables employees to build agents by describing desired outcomes in everyday, natural language, and then share them through Glean’s agent library, driving efficiency and collaboration at work.
• Choose the best model for every agent task: Glean’s agent builder can also now support per-step model selection and temperature control to optimize agent quality, speed, and cost.
• Access rapid innovation from the entire model ecosystem: Through the new Glean model hub, agents are provided access to models across Amazon Bedrock, Google Vertex AI, and Azure OpenAI. The Glean universal model key can unlock 15+ leading commercial and open-source models to eliminate the complexity of procuring models individually.
• Power agent interoperability at scale: With a new MCP Server, agents are enabled on any platform to securely leverage Glean Search and Assistant to access data indexed in Glean or coordinate directly with Glean agents to accomplish joint tasks.
• Build and control Glean agents with code: New Glean Agents API provides a core building block to construct and run agents with code and facilitate open agent-to-agent communication and orchestration.
• Evaluate and optimize agent outcomes: Builders are given step-by-step insight into agent behavior by integrated evaluation frameworks and observability tools, enabling rapid diagnosis of issues, deeper understanding of multi-step processes, and faster iteration for more accurate outcomes.

Glean also provides a library of prebuilt starter agents to accelerate adoption and deliver instant value across both business-critical and personal workflows.

The features of the AI agent library include:

• More than 30 prebuilt agents across sales, engineering, IT, and HR, that are ready to customize and deploy for common tasks such as prospecting, ticket resolution, code review, and help desk automation. These prebuilt agents jump-start adoption, shorten time-to-value, and help teams realize business impact faster.
• New personal agents to help employees with daily tasks, including meeting prep, action item summaries, and performance reviews, all of which are powered by each user’s personal knowledge graph for added context.
• Deep research agents that help employees with complex questions by combining company and world knowledge to deliver thorough, citation-backed research with detailed analysis and flexible depth based on user needs.

With great AI power, comes great responsibility in securing organizations to scale AI safely. Glean enables organizations to scale AI safely by ensuring data is AI-ready and that autonomous agents operate securely to drive meaningful work.

The AI platform secures AI by:

• Protecting against AI-specific threats with built-in safeguards that prevent prompt injection and jailbreak attempts in the Glean platform to ensure agents behave securely in every environment.
• Reducing sensitive data risk with new sensitive content dashboards that automatically detect and remediate overshared sensitive data across 100+ systems. The dashboards are powered by AI security models that are layered over infotype detection and give teams clearer visibility over data exposure.
• Access is managed with precision through a new, expanded permissions infrastructure, allowing customers to control who can run, view, or edit agents with sophisticated, granular access controls, thus ensuring secure, responsible AI use aligned with organizational policies.

Recently, Microsoft unveiled 11 new Security Copilot AI agents for cybersecurity tasks and relieved cyber teams of tedious work. Learn more about how these agents were created to meet the demand of secure AI.