Configuring Agentic AI Features

Overview

This document provides a detailed step-by-step guide to perform the required upgrade actions for Agentic AI after the deployment of the 8.2.0.1 tag. The process involves adding necessary packs, updating stream definitions, executing pipelines, and ingesting datasets to ensure optimal system functionality.

Step 1. Add Required Packs

With InternetWithout Internet

1. Navigation Path : Go to Main Menu → Configuration → RDA Administration → Packs → Upload Packs from Catalog

Below is a summary of the current pack names and their respective versions

Pack Name	Pack Version
AI Projects Administration App	2026.3.9
Base Project Agentic Artifacts	2026.3.5

2. Upload the following pack.

- Pack Name: AI Projects Administration App
- Pack Version: 2026.3.9

3. Activate the uploaded pack.

Important

If Base Project Agentic Artifacts pack is previously present in the setup, then we need to deactivate the previous base pack and then upload and activate the newer version Base Project Agentic Artifacts.

Requirements for Base Project Agentic Artifacts Pack

Ensure a valid license is added before activating the Base Project Agentic Artifacts Pack. The license can be added by navigating to Main Menu -> Administration → License.
Confirm that an organization is set up, along with the required user groups and users.
Note that the Base Project Agentic Artifacts Pack is supported only in single-tenant setups (i.e., setups with only one organization).

4. Navigation Path : Go to Main Menu → Configuration → RDA Administration → Packs → Upload Packs from Catalog

5. Upload the following pack.

- Pack Name: Base Project Agentic Artifacts
- Pack Version: 2026.3.5

6. Activate this pack as well.

7. Make sure that streams ai_mcp_toolsets and ai_mcp_prompt_templates have unique_key as version in pstream definition. (Also, the stream definitions are provided below in "Step 2")

8. Once the pack is activated, restart the portal-backend to register the toolsets.

Note

Verify both packs are successfully activated before proceeding to the next steps.

1. Download the following packs

https://github.com/cloudfabrix/rda_packs/blob/main/AI%20Projects%20Administration%20App/2026.3.9/AI_Projects_Administration_App-2026.3.9.tar.gz

https://github.com/cloudfabrix/rda_packs/blob/main/Base%20Project%20Agentic%20Artifacts/2026.3.5/Base_Project_Agentic_Artifacts-2026.3.5.tar.gz

2. Navigation Path : Go to Main Menu → Configuration → RDA Administration → Packs → Upload Pack

Below is a summary of the current pack names and their respective versions

Pack Name	Pack Version
AI Projects Administration App	2026.3.9
Base Project Agentic Artifacts	2026.3.5

3. Upload the following pack.

- Pack Name: AI Projects Administration App
- Pack Version: 2026.3.9

4. Activate the uploaded pack.

Requirements for Base Project Agentic Artifacts Pack

Ensure a valid license is added before activating the Base Project Agentic Artifacts Pack. The license can be added by navigating to Main Menu -> Administration → License.
Confirm that an organization is set up, along with the required user groups and users.
Note that the Base Project Agentic Artifacts Pack is supported only in single-tenant setups (i.e., setups with only one organization).

5. Navigation Path : Go to Main Menu → Configuration → RDA Administration → Packs → Upload Pack

6. Upload the following pack.

- Pack Name: Base Project Agentic Artifacts
- Pack Version: 2026.3.5

7. Activate this pack as well.

8. Make sure that streams ai_mcp_toolsets and ai_mcp_prompt_templates have unique_key as version in pstream definition. (Also, the stream definitions are provided below in "Step 2")

9. Once the pack is activated, restart the portal-backend to register the toolsets.

Note

Verify both packs are successfully activated before proceeding to the next steps.

Step 2. Update Pstream Definitions

Note

This step is only required if AI Projects Administration App is already in the setup.

This step is necessary if AI Projects Administration App is included in the setup from the 8.2 build, as it updates the definition of streams. This update is skipped during pack activation since the streams already exist.

Navigation Path : Go to Main Menu → Configuration → RDA Administration -> Persistent Streams and search for the below pstreams to update -

Stream Name: ai_mcp_toolsets

{
    "system_defined": "no",
    "_mappings": {
        "properties": {
            "tools": {
                "type": "float"
            }
        }
    },
    "unique_keys": [
        "ai_project_name",
        "toolset_name",
        "version"
    ]
}

Example Screenshot

Stream Name: ai_mcp_prompt_templates

{
    "unique_keys": [
        "prompt_template_name",
        "ai_project_name",
        "version"
    ],
    "system_defined": "no"
}

Stream Name: rda_shared_conversations

{
    "system_defined": "no",
    "_mappings": {
        "properties": {
            "shared_timestamp": {
                "type": "date"
            }
        }
    },
    "unique_keys": [],
    "retention_days": 60
}

Stream Name: rda_workflow_trigger_stream

{
  "unique_keys": [
  "trigger_name",
  "ai_project_name"
 ],
  "system_defined": "no",
  "retention_days": 60
}

Additional Steps for Projects Added to the Setup in 8.2

Please follow Step 3 and Step 4 below only if the setup includes any projects on the ai_projects page other than the Base project, in order to add the new column “version”.

Step 3. Execute Pipelines

Navigation Path : Go to Main Menu → Configuration → RDA Administration → Pipelines -> Published Pipelines -> click the three-dot menu next to the desired pipeline -> select Run. If necessary, enable "Inspect Pipeline Traces" for further debugging. Please ensure that each pipeline completes successfully before proceeding.

Run the following pipelines and wait for their successful completion.

add_version_toolset

add_version_prompt_template

Upon the successful execution of each pipeline, corresponding datasets will be generated. You can find the datasets by navigating to Main Menu → Configuration → RDA Administration → Datasets. Then, proceed to the next step

Note

Monitor the execution for any failures and check the logs as necessary.

Step 4. Ingest Datasets

Ingest the following datasets into their respective streams

Navigation Path : Go to Main Menu → Configuration → RDA Administration → Datasets → Select the Dataset -> Click on Ingest to Stream -> Click on Ingest as shown in the below screenshot

Ingest the following datasets into their respective streams

Dataset	Target Stream
`ai_mcp_toolset`	ai_mcp_toolset
`ai_mcp_prompt_template`	ai_mcp_prompt_template

Example Screenshots