¶ Intelligence & AI Domain
The Intelligence & AI domain enables AI models, agents, and toolchains to participate as governed, explainable actors in Fuse workflows.
Rather than treating AI as a black box, this domain turns it into a composable, auditable component that can be invoked, monitored, and refined alongside human, policy, and system steps.
Fuse treats AI as a native domain — allowing models and agents to be:
- Triggered by workflows
- Routed dynamically based on context
- Constrained by identity and policy
- Monitored and explained in real time
From autonomous agents to human-in-the-loop collaboration, this domain ensures AI operates with transparency and control.
- Prompt Execution & Routing — Dynamically select and execute AI models based on input, role, or policy
- Tool Orchestration — Use AI to select and invoke tools or services within workflows
- Session Management — Track multi-turn conversations, context threads, and memory
- Explainability & Feedback Loops — Make decisions observable and reviewable by humans
- Bias Detection & Drift Monitoring — Log AI performance and identify anomalies
- Scoped AI Access — Limit tool/model access by user, domain, or security token
- AI SDK Integration — Extend Fuse to support custom models and inference endpoints
| Layer |
Intelligence & AI Role |
| Integration |
Connect to external model APIs or inference servers |
| Automation |
Use AI to trigger or evaluate logic based on inputs |
| Orchestration |
Invoke AI as part of step logic, approval, or decision |
| Interoperability |
Apply context, roles, and feedback during AI execution |
- A user uploads a document. Fuse routes the file through an AI model to classify, summarize, and flag it for review.
- An AI assistant helps a tax preparer fill out a complex return, and routes ambiguous cases to human approval.
- A multilingual AI agent selects the appropriate language model and handles client support chats inline.
¶ Extending the Domain
Use these frameworks to enhance AI workflows: