This guide provides step-by-step instructions for creating and configuring a Outlook connector with Abacus.AI's.
Before starting, ensure you have access to: - Abacus.AI platform - A valid Outlook account - Administrative access to create connectors and projects
Navigate to the projects page by clicking on the ABACUS.AI logo.
Click on "Create a new project" to begin setting up your ChatLLM project.
Choose ChatLLM - Custom LLM Chat option from the available project types.
Enter a descriptive name for your project that reflects its purpose.
Select "Skip to project dashboard" to proceed directly to the project configuration.
Navigate through the following menu structure: - Select Advanced Option - Choose Tool Use - Select Outlook_tool
Click on "Train Model" to begin the training process.
Once training is complete: 1. Click on Models in the navigation 2. Select your newly trained model
Click on "Create a new deployment" to make your model available for use.
Enter a user-friendly name that your end users will see, then click "Deploy".
Click on the "Prediction Dash" option under the Deployment section.
Click on "Go to Abacus.AI Chat" to access the testing interface.
Grant admin consent for Abacus.AI
in App Registeration → API permissions.If you encounter issues:
1. Check deployment status is "Active"
2. Ensure proper authentication credentials
3. Error AADSTS50105: Your administrator has configured the application abacus_outlook_user_connector
(Application ID) to block users unless they are specifically granted ('assigned') access to the application.
- Go to Azure Portal → Microsoft Entra ID → Enterprise applications.
- Search for abacus_outlook_user_connector
.
- Open the app → Users and groups → Add user/group.
- Select users/groups → (optional) choose role → Assign.