Platform Architecture
Velatir consists of five main components that work together to provide comprehensive AI governance:Traces
Individual AI interactions captured from your systems
Sessions
Groups of related traces forming a complete interaction
Policies
Rules that evaluate traces - pre-built and custom compliance policies
Workflows
Visual node-based routing with triggers, conditions, and human gates
Review Tasks
Created when a workflow requires human approval
Channels
Where approvals happen - Slack, Teams, email, or web dashboard
How Components Work Together
Trace Created
Your AI system sends a trace through API, SDK, or integration. Traces can be Inlet (incoming request), Response (outgoing), or Signal (passive event).
Session Grouping
Traces with the same session ID are grouped together, providing full context for an interaction.
Policy Assessment
Each trace is evaluated against active policies (pre-built and custom rules).
Workflow Execution
If a workflow is configured, triggers are evaluated. Matching triggers execute the workflow nodes.
Human Intervention
If the workflow hits a human intervention node, a review task is created and sent to the configured channel.
Decision & Completion
Human approves, declines, or requests changes. The trace is marked complete and logged.
Key Principles
1. Traces Are the Foundation
Every AI interaction is captured as a trace. This gives you complete visibility into what your AI systems are doing.2. Sessions Provide Context
A single user conversation or workflow run generates multiple traces. Sessions group these together so reviewers see the full picture.3. Workflows Control the Flow
Visual, node-based workflows let you define exactly how traces should be handled based on policy results, risk levels, or custom conditions.4. Review Tasks Are Created When Needed
Not every trace needs human review. Review tasks are only created when a workflow’s human intervention node is triggered.5. Work Where You Work
Approvals happen in your existing tools - Slack, Teams, email, or the web dashboard.Trace Lifecycle
Every trace follows this pattern:- Received - Trace arrives from your system
- Assessed - Policies evaluate the trace
- Workflow Executed - Triggers checked, nodes executed
- Completed/Rejected - Final state based on workflow outcome or human decision
Trace Directions
| Direction | Description | Example |
|---|---|---|
| Inlet | Incoming request to an AI system | User asks chatbot a question |
| Response | Outgoing response from AI | Chatbot’s answer |
| Signal | Passive event or notification | System log, tool call |
Review Task States
Review tasks (created by human intervention nodes) can be:| State | Description |
|---|---|
| Pending | Waiting for human decision |
| Processing | Being worked on |
| Approved | Human approved the request |
| Rejected | Human declined the request |
| Change Requested | Human wants modifications |
Integration Options
Velatir integrates into your existing AI workflows through:- Direct API - REST endpoints for custom integrations
- SDKs - TypeScript/JavaScript and Python libraries
- n8n Node - Official node for workflow automation
- LangChain - Middleware for LangChain applications
- MCP Server - Model Context Protocol for AI agents
- Browser Extension - Monitor LLM interactions in browsers