[[{“value”:”

🚀 Series Overview: Custom Agentic Chatbot with SAP AI Core and Joule Studio

• Part 1 — Building the Custom AI Agent Backend
• Part 2 (1) — Deploying the Agent on AI Core (Environment & Containerization)
• Part 2 (2) — Deploying the Agent on AI Core (Deployment & Testing)
• Part 3 (1) — Setting Up Joule Studio Connection (Destination & Environment)
• Part 3 (2) — Creating a Joule Skill (Design & Release)
• Part 3 (3) — Testing and Sharing on Work Zone

Part 2 (2) — Deploying the Agent on AI Core (Deployment & Testing)

https://api.<region>.hana.ondemand.com/v2/inference/deployments/<deployment-id>

{
“message”:”what is current weather in Seoul?”,
“conversation_id”:”test-session-2″
}

Example:

If everything is configured correctly, you’ll receive a JSON response from your deployed chatbot. Your custom agentic chatbot is now live on AI Core. 🎉

👉  In Part 3, we’ll cover how to configure BTP Destinations so Joule Studio can securely call this endpoint.

“}]] 

 [[{“value”:”🚀 Series Overview: Custom Agentic Chatbot with SAP AI Core and Joule StudioPart 1 — Building the Custom AI Agent BackendPart 2 (1) — Deploying the Agent on AI Core (Environment & Containerization)Part 2 (2) — Deploying the Agent on AI Core (Deployment & Testing)Part 3 (1) — Setting Up Joule Studio Connection (Destination & Environment)Part 3 (2) — Creating a Joule Skill (Design & Release)Part 3 (3) — Testing and Sharing on Work Zone Part 2 (2) — Deploying the Agent on AI Core (Deployment & Testing) In this continuation of Part 2 (1), we’ll focus on putting everything together:Register the ServingTemplate in AI CoreCreate a Configuration and DeploymentTest the live REST endpoint Step 1. Register the ServingTemplatePush the YAML file to your connected Git repository. SAP AI Core will automatically detect it and register it as:Scenario: high-level use caseExecutable: specific deployable artifact Step 2. Create ConfigurationLink the YAML-defined Executable to runtime parameters.Configuration Name: any unique name (e.g., agent-chat-config)Scenario: auto-populated from scenarios.ai.sap.com/nameVersion: as defined in ai.sap.com/versionExecutable: auto-registered from executables.ai.sap.com/nameReview and click Create to save. Step 3. Create DeploymentLaunch the service from the configuration:Click Create DeploymentSet the durationDeployOnce deployment is active, your chatbot is live and accessible via a REST inference endpoint. Step 4. Test the EndpointWhen the deployment is successful, AI Core generates a secure endpoint, for example:https://api.<region>.hana.ondemand.com/v2/inference/deployments/<deployment-id>Validate that your deployed Endpoint works correctly by sending test requests via Postman or cURL. Refer to this tutorial.Postman Example:Method: POSTURL: https://api.<region>.hana.ondemand.com/v2/inference/deployments/<deployment-id>/planHeader:AI-Resource-Group: woojin-agent (Resource group name defined in AI Core)Content-Type: application/json (Request body format)Body (Json){
“message”:”what is current weather in Seoul?”,
“conversation_id”:”test-session-2″
}Example: If everything is configured correctly, you’ll receive a JSON response from your deployed chatbot. Your custom agentic chatbot is now live on AI Core. 🎉👉  In Part 3, we’ll cover how to configure BTP Destinations so Joule Studio can securely call this endpoint.  “}]] Read More Technology Blog Posts by SAP articles 

#SAPCHANNEL