Complete Setup Guide

​

Overview

​

Step 1: Create Your Project

1. Go to the Projects section
2. Click Create Project
3. Enter a name (e.g., “Customer Analytics”)
4. Click Create

​

Step 2: Add a Connection

1. Click Add Connection in your new project
2. Choose Try Demo Data (or connect your real database)
3. For real databases, enter credentials and test the connection
4. Click Save

​

Step 3: Create a Data Model

1. Go to the Data Models tab
2. Click Create Data Model
3. Select your connection
4. Enter a name (e.g., “Analytics Model”)
5. Click Create

​

Configure the Data Model

1. Select tables - Uncheck any tables you don’t want exposed
2. Select columns - Uncheck sensitive columns (e.g., passwords, PII)
3. Add descriptions - Help AI understand your schema
4. Mark selectables - Flag columns with categorical values for AI filtering
5. Click Save

​

Set Up RLS (Optional but Recommended)

1. Click on a table
2. Go to the RLS tab
3. Write your filter rule:
   Copy

   Ask AI

   SELECT *
   FROM "orders"
   WHERE "company_id" = {{organization.company_id}}
   
4. Click Save

​

Step 4: Set Data Model to Production

1. Go to the Versions tab in your data model
2. Click Set as Production on the latest version
3. Wait for validation to pass

​

Step 5: Create an Agent OR Application

​

Option A: Create an Agent

1. Go to the Agents tab
2. Click Create Agent
3. Select your production data model
4. Click Create

​

Option B: Create an Application

1. Go to the Applications tab
2. Click Create Application
3. Select your production data model
4. Click Create

​

Step 6: Configure Your Agent/Application

​

For Agents: Add Golden Assets

1. Go to the Assets tab
2. Click Add Asset
3. Enter a sample question and SQL:
   • Question: “What are our top 10 products by revenue?”
   • SQL: SELECT product_name, SUM(amount) as revenue FROM orders GROUP BY product_name ORDER BY revenue DESC LIMIT 10
4. Click Save

​

For Applications: Build Templates

1. Click Add Dashboard
2. Name it “Overview Dashboard”
3. Add charts by clicking Add Chart
4. Configure each chart with your data
5. Arrange the layout
6. Click Save

​

Step 7: Go to Production

​

For Agents

1. Test the agent in admin view
2. Go to the Versions tab
3. Click Set as Production

​

For Applications

1. Preview each template
2. Click Publish on each template
3. Templates propagate to all spaces

​

Step 8: Add Project Organizations

1. Go to the Organizations tab
2. Click Add Organization
3. Enter the organization name (e.g., “Acme Corp”)
4. Add properties for RLS:
   Copy

   Ask AI

   {
     "company_id": "acme-123"
   }
   
5. Click Create

​

Step 9: Register End Users

​

Via UI

1. Go to the Users tab
2. Click Add User
3. Enter user name
4. Select organization and role
5. Add properties if needed
6. Click Create

​

Via API

curl -X POST https://api.upsolve.ai/api/v1/project/user/register \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "John Smith",
    "projectId": "YOUR_PROJECT_ID",
    "userRoleId": "READER_ROLE_ID",
    "projectOrganizationId": "ACME_ORG_ID",
    "properties": {
      "department": "sales"
    }
  }'

​

Step 10: Generate User Tokens

​

Via API

curl -X POST https://api.upsolve.ai/api/v1/project/user/token \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "userId": "USER_ID_FROM_REGISTRATION",
    "expiration": "24h"
  }'

{
  "token": "eyJhbGciOiJIUzI1NiIs..."
}

​

You’re Done!

• Chat with agents using natural language
• View dashboards with their filtered data
• Create their own charts and dashboards in their space

​

Quick Checklist

​

Next Steps

• Read about Row-Level Security in detail
• Learn about Agent configuration
• Explore Application templates