You are here:
Get AI Agent Tasks Ready for Run Time in Agentforce Supply Chain
Before you publish a blueprint, make sure that your AI agent tasks are tested and producing reliable results. This section walks you through how plans work, how to test them, and how to lock them for consistent run-time behavior in Agentforce Supply Chain.
Required Editions
| License Required |
|---|
This feature is a workspace that’s external to your Salesforce org and requires an Agentforce Supply Chain license. To purchase an Agentforce Supply Chain license, contact your Salesforce account executive. |
| User Permissions Needed | |
|---|---|
| To manage tasks in Agentforce Supply Chain: | Admin role or Creator role |
How the AI Agents Plan Their Work
AI agents in Agentforce Supply Chain create a plan before running a task and improve it each time the task runs from a test or workflow run.
- AI agents create a plan the first time that you test the task or run a workflow. For example, a document extraction task plan can include steps like read document, map values to fields, validate required fields, and write outputs.
- AI agents improve their plan each time you run the task, until you publish the associated blueprint.
- AI agents record their plan in the task's Activity tab, where you can review it after testing or running a workflow.
Test Your AI Agent Tasks
Test AI agent tasks in Agentforce Supply Chain with realistic sample data, hone instructions, and validate plans and results before publishing blueprints.
Reliable results require testing with realistic field values and files, and then improving the instructions for the AI agent based on the results. If you test with placeholder data, such as a task named Test Task, the AI agent can give misleading results.
- Open the task that you want to test.
- Click the Test tab.
- Click Run test and review the generated values and activity history.
-
If the task completes, but the results are incorrect, go back to the
Configure tab.
For .docx output tasks, verify that template variables exactly match the requested field names, such as
{{ supplier_name }}and{{ renewal_date }}.- Refine your instructions or other parts of the task.
- Run the test again.
-
If the task has a problem, open the task.
- Click Resolve problem.
- Select Re-run AI Agent.
- Decide whether to try the AI agent plan again or generate a new plan.
- To try again with the same plan, click Confirm.
- To try again with a new temporary plan for testing, select Generate a new plan., and then click Confirm.
- If the task completes correctly, create and run a workflow with sample data from the draft blueprint to validate task interactions.
- After results are consistently accurate, publish the blueprint to lock plans.
Publish Your Blueprint to Lock the Plan
Publishing a blueprint locks the AI agent's plan in Agentforce Supply Chain so it follows the same steps every time the workflow runs.
When you're happy with the AI agent's results and you're ready to lock the plan, publish your blueprint. The AI agent follows the locked plan every time the workflow runs.
If a locked plan fails, the agent reports a problem instead of trying a new approach. This makes failures visible and predictable so you can investigate and fix them. You can optionally choose to re-run the agent and generate a new, temporary plan to complete the task. This new plan is not saved to the blueprint.
If you change a published blueprint, such as renaming a requested field, the saved plan can become invalid. Re-test the task before publishing again to make sure that the plan is still accurate.
