Overview
This guide walks you through setting up Velatir to monitor your AI systems.Step 1: Create a Project
- Log in to your Velatir dashboard
- Click Create Project
- Give your project a name and description
- Click Create
Step 2: Enable Policies
- Go to Policies in the dashboard
- Browse the available pre-built policies
- Enable the policies relevant to your use case
- Optionally create custom policies for your specific requirements
Step 3: Create a Workflow
- Go to Workflows in the dashboard
- Click Create Workflow
-
Add nodes to your workflow:
- Policy Trigger - Triggers when a policy matches
- Human Intervention - Creates a review task for approval
- Notification - Sends alerts to your team
- Rejection - Rejects the trace
- Connect the nodes to define your approval flow
- Save and activate your workflow
Step 4: Connect a Channel
- Go to Channels in the dashboard
- Connect your preferred channel:
- Slack - Approve directly in Slack
- Microsoft Teams - Use adaptive cards
- Email - Reply-to-approve workflow
- Human intervention nodes will now send approval requests to your connected channels
Step 5: Integrate Your AI System
Choose an integration method that fits your stack:Browser Extension
Monitor LLM interactions across 200+ AI platforms
n8n Node
Add approval gates to n8n workflows
LangChain
Native middleware for LangChain agents
MCP Server
Model Context Protocol for AI agents
TypeScript SDK
Official TypeScript/JavaScript library
Python SDK
Official Python library