Oracle Fusion AI Agent Studio: Agent Migration Process

In this blog we will understand the process of migrating AI Agents from one environment to the other in Fusion AI Agent Studio. This process was introduced starting with 26A release and helps us export/import individual AI agents as needed.

I've also covered some of the observations/shortcomings in this process based on my experience. Hope they help the readers.

The steps below describe the Export/Import process for an AI Agent starting from 26A.

Export AI Agent from the Source environment

1. In Source instance:

Navigate to Tools -> AI Agent Studio

Go to AI Agent Studio -> Agent Teams

2. From the Agent Teams tab, locate the agent team you want to export and click the download icon

 
3. While exporting an AI Agent, we need to enter below details:

Partner Name: <Company Name>

Description: Agent description

Partner Image: <Company Logo>

 

In the Preview section we can se how our agent would look like:

4. Once the export details are entered, verify details shown in Preview section and click Export to download the JSON file to your local system. 

5. In above example, the exported file would be 'BENEFITS_POLICY_ADVISOR.json'.

We can open the .JSON file and inspect if it exported all the desired details from the source environment:

Import AI Agent into the Target environment

1. Go to the target environment.

2. Navigate to AI Agent Studio -> Agent Teams

3. Click Import button.

 

4. Select the downloaded JSON file and click Open.

 

5. Once the AI Agent is imported, it can be found under Draft tab. The version of the imported agent gets reset to 1.

6. Use the Edit button to edit the imported agent team.

7. Publish the agent team after making the necessary configurations.

Export/Import Observations

Post-import manual steps (Official list mentioned by Oracle):

- Document tool: Upload and republish the document to ensure its content is correctly processed in the new environment.

- Email tool: Reconfigure the email tool to make sure necessary alerts are generated properly in the new environment.

- External REST tool: Reconfigure authentication settings for external REST API tools.

Additional observations based on my testing:

- This process exports and retains the LLM configuration/assignments for the agent. No reconfiguration needed in this case.

- It doesn't export Security configurations/role assignments for the agent. Needs manual reconfiguration/assignment upon import.

- It exports and retains the Questions (3 custom questions) as expected. No reconfiguration needed in this case.

- The Import process doesn't ask if you want to overwrite, in case the agent already exists. My existing agent version was 7 and upon reimporting it was reset to 1 in the Draft area.

- We need to mention Partner details (Name, agent description and even upload company Logo) during export.

This seems like a good way of branding as the agent shows company name and logo during export.

It’s a good feature that will help end users in identifying our own custom agents.

But I observed that the Company Name and Logo doesn’t appear anywhere upon import, or even after publishing the imported agent.

The branding information is not shown anywhere in AI Agent Studio or on the tiles in AI Chat section.

- Document tool loses the actual document - This is expected since Oracle has already published this behavior.

- All above points apply for Export/Import of a seeded agent as well as a fully custom agent (no difference in behavior).

- All above points apply for Export/Import of a Published agent as well as a Draft agent (no difference in behavior).

- Irrespective of the status of an agent in the source environment (Draft or Published) was, it goes in a Draft status in the target environment upon import.

Read More

How to Configure Cascading LOV Parameters in Oracle Fusion ESS job Using Value Sets

In this blog, I will explain the step by step process to implement cascading LOV parameters in Oracle Fusion ESS Job using Value Sets. In the end, we will have a custom ESS Job with two parameters where Parameter 2 value will dynamically change based on the value selected in Parameter 1.

Let's dive in.


Register a new List of Values Source

- Navigate to Setup & Maintenance

- Search for the task 'Manage Enterprise Scheduler Job Definitions and Job Sets for Financial, Supply Chain Management, and Related Applications'

- Go to 'Manage List of Values Sources' Tab

- Create a new LOV Source

    - Application: Application Toolkit

    - Name: Give desired name (I'm using AJ_LOV_Source as an example)

    - LOVType: Predefined

    - LOV Source definition Name: oracle.apps.fnd.applcore.flex.vst.model.publicView.ValueSetValuePVO

- Save and close


Create custom Value Sets

- We are going to create 3 Value Sets in my example:

    - Value Set 1 (AJ_Vset_1): This will be the main Value Set our Parameter 1 will refer to. This Value Set will have two values - AJ_BU and AJ_LE, which are essentially 2 separate Value Sets.

    - Value Set 2 (AJ_BU): This is the Value Set that holds Business Units

    - Value Set 3 (AJ_LE): This is the Value Set that holds Legal Entities


Create Value Set 1 (AJ_Vset_1):

- Navigate to Setup & Maintenance and search for Manage Value Sets

- Create a new Value Set named AJ_Vset_1

- Set the desired Module, set Data Type to Character and SubType to Test with length 150

- Assign two values to this Value Set - AJ_BU and AJ_LE

Create Value Set 2 (AJ_BU):

- Create a new Value Set named AJ_BU

- Set the desired Module, set Data Type to Character and SubType to Test with length 150

- Assign two values to this Value Set - BU1 and BU2

Create Value Set 3 (AJ_LE):

- Create a new Value Set named AJ_LE

- Set the desired Module, set Data Type to Character and SubType to Test with length 150

- Assign two values to this Value Set - LE1 and LE2

ESS Job Configuration

- Navigate to Setup & Maintenance

- Search for the task 'Manage Enterprise Scheduler Job Definitions and Job Sets for Financial, Supply Chain Management, and Related Applications'

- Create the custom ESS Job, enter the essential details like Display name, Path, Report ID (for BIP report) etc.

- In my example, I've created a test job named AJ Test as shown below

- Navigate to Parameters section

- Create Parameter 1 as follows:

    - Data Type: String

    - Page Element: List of Values

    - List of Values Source: AJ_LOV_Source (from Step 1 above)

    - Attribute: Value

    - Display Attributes: Value

- Save and close

- Select Parameter 1 and click on Manage Dependencies icon.

- Move 'ValueSetCodeCriteria' to the Selected View Criteria section

- Set the Default Value to 'AJ_Vset_1'. This is our main value set that will show list of values for other 2 value sets.

- This configuration tells the ESS engine that Parameter 1 should refer to 'AJ_LOV_Source' LOV which is a generic LOV that refers to ValueSetValuePVO source and the dependency configuration adds a where clause indicating that the engine should display values from the Value Set AJ_Vset_1


- Now create Parameter 2 as follows (similar to Parameter 1 definition):

    - Data Type: String

    - Page Element: List of Values

    - List of Values Source: AJ_LOV_Source (from Step 1 above)

    - Attribute: Value

    - Display Attributes: Value

- Select Parameter 2 and click on Manage Dependencies icon.

- Move 'ValueSetCodeCriteria' to the Selected View Criteria section

- This time, we will set the Mapped Parameter value to Parameter 1.

This configuration tells the ESS engine that Parameter 2 should refer to 'AJ_LOV_Source' LOV which is a generic LOV that refers to ValueSetValuePVO source and the dependency configuration adds a where clause indicating that the engine should display values from the Value Set returned by Parameter 1

- Save and close the ESS Job definition.

Test the output

- Navigate to Tools -> Scheduled Processes

- Search for our custom job (AJ Test in my case)

- The Process Details popup will show us the two parameters - Parameter 1 and Parameter 2

- When we click on Parameter 1, it shows us the two values AJ_BU and AJ_LE

- If we select the value AJ_BU in Parameter 1 then the Parameter 2 automatically shows us the 2 BUs from the dependent Value Set

- And if we select the value AJ_LE in Parameter 1 then the Parameter 2 automatically shows us the 2 LEs from the dependent Value Set

And that's it! With these configurations in place, we've established the cascading LOV parameters in Oracle Fusion ESS job using custom Value Sets.
The example I provided uses simple Independent Value Sets with static values but this pattern can be extended to fit other types of LOVs as per your actual requirements.

Read More

Fusion Query Studio: Run SQL queries against Oracle Fusion from within VS Code

If you are a developer or a power user who has spent real time in building queries, reports or even troubleshooting data in Oracle Fusion, you are already know that there's no easy way to run a SQL query against Fusion database and see the results. The only out-of-the-box way is to create a data model in BI Publisher and test your queries, lookup and analyze the data.
This is because Fusion is SaaS and we don't get a database connection like other on-prem systems might be able to provide; but this limitation slows us down since we have to go through multiple steps just to query the data.

I'd been wondering what if there's a simple tool that lets you connect to Fusion environments, run your queries against it and simply see the results. A simple basic framework that just works.

I'd been working on building such a solution and it's now live for everyone to use.

Introducing Fusion Query Studio - A VS Code extension that lets you connect to a Fusion environment and run your queries against it from within the editor.

Fusion Query Studio features

Multiple saved connections: Store your multiple Fusion environments (Dev, Test, and Prod etc.) side by side with passwords encrypted in the Windows Credential Vault.

Live results table: The results table provides features such as sort by columns, null values highlighting etc.

Query history: The extension stores your last 50 queries automatically. You can access them from Query History panel and re-run without retyping it.

Simple CSV export: Export the query results to a file with a single click.

AI Chat integration: Ask VS Code's native AI Chat (GitHub Copilot) to build and run a query for you through the extension. AI will ask/tell you which connection it used, show you the actual SQL it built, and it will run it in background using the Fusion Query Studio extension and present you the results. You can also copy-paste the AI-generated query in the Query Editor panel, run it and see the results in the results panel.

SSO-based login: This feature is not available in the current version but it's on the roadmap.

Getting Started

1. Install the extension:

Search for Fusion Query Studio in VS Code Marketplace  and Install the extension

Install:

2. Launch the extension:

You'll see the Fusion Query Studio icon show up in the activity bar on the left side of VS Code.

3. Add a connection: 

In the Connections panel, click the + button.

Follow the 4 step wizard and provide below details:

Connection name: Connection name of your choice.

Base URL: Your Fusion environment's URL. e.g. https://fa-ebfa-dev1.us1234.oraclecloud.com

If you want to use Basic Authentication, select Basic Auth method:

Username: User name of the account under which the SQL queries will be executed.

Password: Password of the above user. This gets encrypted and stored in the Windows Credential Vault. It's never written to disk in plaintext.

You will see a confirmation that says the connection is saved.

If you want to use Single sign-on (SSO) method, select SSO method:

You will be presented with a browser pop-up and will be taken to the login page of your Fusion POD. Login using your SSO credentials, as you usually do to login to your Fusion environment:

Once the login is successful, the browser window will be automatically closed and you will see a confirmation message in the VS Code:

Please Note: In case you see an error message that says 'Could not verify/deploy utility report', then you may need to verify a few things:

- Verify if your connection details are correct (Base URL, Username and Password)
- Verify that the User account you are using has roles/permissions to create/execute BI publisher reports.

4. Test the connection:

Click ▶ icon in front of your connection name (Fusion_Dev in my example) to test the connection.

If there are no errors, we should see the confirmation message.

5. Edit / Delete the connection:

You can Edit or Delete the connection by clicking the respective icons in front of your connection name.

Edit:

Delete:

6. Open the Query Panel:

Click Open Query Panel icon ▶ in the toolbar to open the Query Panel. This is the most easy and common way to access the query panel.

Optionally, you can run the command Fusion Query Studio: Open Query Panel from the Command Palette (Ctrl+Shift+P) to do the same.

From Toolbar:

From Command Palette:

You should be presented with the Query Panel as shown below:

7. Run a query: Select the desired connection from drop-down, write your SQL in the top panel and hit the Run button (or press Ctrl+Enter).This will execute your SQL query and present the results to you in the results panel.

Things to remember:

- You can control how many rows come back by adjusting the Limit value.

- Please skip the trailing semicolon. Don't end your query with ;

- Click Cancel to stop any running query.

- Adjust the divider between the editor and the results pane to resize it.

8. Let AI Chat write the query for you:

Open VS Code's built-in AI Chat (using GitHub Copilot) and describe your requirements. Fusion Query Studio seamlessly plugs into the AI Chat of VS Code.
It will ask you which saved connection to use, will build the query and show it to you before running it,  and finally present you the results.

- Describe the requirements of your query and ask it to run it using using Fusion Query Studio:

- Review the Connection details, verify the query and allow AI Chat to run the query using Fusion Query Studio:

- AI Chat will show you the entire query, run it against the selected connection and show you the results:

Query:

 Results:

- You can also copy the AI-generated query and run it manually in the Fusion Query Studio

Copy the query:

Paste it in Query Panel:

Run the query and see the results:

- You can click on CSV button to download the query result in a CSV format

- Query History panel stores your last 50 queries. You can click on any of them and they will be automatically pasted in Query Panel so that you can rerun without rewriting them.

Try it out

If you're building against Oracle Fusion Cloud environments and you're constantly following multi-step process in BI Analytics, just to test your query or validate the data - give Fusion Query Studio a shot. It's available for free on the VS Code Marketplace. If you run into anything or have ideas for what it should do next, please reach out to me at amodjjoshi@gmail.com. Happy Querying 😊

Read More