Summary
The purpose of this article is to provide a high-level understanding of owlONE, its purpose, and its core features.
Body
OwlONE: FAU's Custom AI Platform
OwlONE is FAU's branded version of nebulaONE®, securely hosted in FAU's Microsoft Azure environment to provide generative AI through chat and configurable agents. Users can start with ONEchat for general-purpose conversations, select purpose-built agents, or build their own.
Getting Started
Any FAU student, faculty, or staff member can immediately start building and testing their own personal agent—no request or approval needed. Simply sign in with your FAU account:
- Go to owlONE
- Select Explore Agents.
- Click Create under My Agents.
Helpful links to get you going:
Agent Knowledge Sources
Beyond text responses, owlONE supports task-driven workflows and integrations with institutional systems. When you build an agent, you can ground its logic using four distinct, multi-source knowledge vectors:
File-based libraries (RAG)
Upload datasets, course materials, or proprietary papers. Retrieval-Augmented Generation grounds responses in your documents.
Dynamic web grounding
Point your agent at specific public URLs or university web pages so its knowledge reflects real-time operational updates.
Live API integrations*
Build custom API calls within the configuration panel to securely interact with external servers, apps, or databases and fetch live data streams.
Model Context Protocol (MCP)*
Connect your agent to deep institutional data warehouses using standardized, secure OAuth-based frameworks.
* Reserved for Official agents.
Agent lifecycles
To maintain university governance, owlONE uses a tiered publishing system:
- Personal agents are developed and tested by their creator and shared or embedded with a link if desired.
- Official agents are published for broader use following review through FAU's IT governance and service catalog processes to ensure security, data compliance, and institutional alignment. Request an official agent.
Tokens and usage
OwlONE operates on a token-based consumption model: usage is driven by how much content is processed during each session. While FAU does not currently charge departments for usage, understanding tokens helps ensure efficient, scalable use of the platform.
What impacts token usage:
- User prompts and responses (longer conversations use more tokens)
- File uploads and document analysis
- Agent workflows that trigger APIs or multi-step processes
- Model selection (more advanced models consume more tokens per task)
TIP: You can view token usage for a conversation by clicking on the 'show execution details' icon provided with each response.
Choosing a model
Agent builders may select from the models allowed for that agent type. Different models vary in supported features, response characteristics, speed, and token efficiency—higher-capability models generally consume more tokens per task. The model selector's efficiency indicator and the usage panel can help compare options.