Gearset's Agentforce metadata deployment solution streamlines the process of deploying AI-powered configurations in Salesforce, including the AI Agent metadata (GenAiPlanner). Agentforce AI Agents engage customers autonomously across channels in natural language.

This guide will explain how to successfully deploy the AI Agent (GenAiPlanner) metadata with Gearset.

Make sure to use at least API version 60 for the comparison. Read the prerequisite section of the How to deploy GenAi metadata guide to find out how to do this.

The Einstein bot and botVersion associated to the Agent that you want to deploy must exist on the target org — otherwise the agent will not be visible.

You'll need to include Einstein bot, botVersion & GenAiPlanner in your metadata comparison filter.
​

To deploy the GenAiPlanner metadata type, you need to make sure that all the GenAiFunction and GenAiPlugin dependencies exist on the target environment. If they don't, then you'll need to deploy them alongside the GenAiPlanner for the validation/deployment to be successful.

Note:

If the GenAiPlanner is New then the associated Einstein bot and botVersion will also need to be deployed to the target org otherwise the deployed GenAiPlanner will not be visible on the target org. It's recommended to always deploy any changes to the Einstein bot and botVersion alongside the GenAiPlanner.

Example:

This GenAiPlanner is dependent on the following GenAiFunction:

It's also dependent on the following GenAiPlugins:

If any of these GenAiFunctions or GenAiPlugins aren't already in the org, or being deployed to the org alongsidethe GenAiPlanner, then the validation/deployment will fail.
​
We will be adding more problem analyzers over time to help highlight any missing GenAiFunction or GenAiPlugin dependencies before you validate or deploy your Agentforce agents.