Agentforce AI Agents engage customers autonomously across channels in natural language.
This guide will explain how to successfully deploy the AI Agent (GenAiPlanner) metadata via Gearset.
Prerequisites
You must 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 Bot
version associated to the Agent that you want to deploy must exist on the target org otherwise the agent will not be visible.
What metadata is needed in the filter?
In your metadata filter you will need to include Einstein bot
, Bot version
& GenAi planner
.
β
How to deploy through Gearset
To be able to deploy a GenAiPlanner
metadata type, you need to make sure that all the GenAiFunction
and GenAiPlugin
dependencies exist on the target, if they don't then you need to deploy them along side the GenAiPlanner
for the validation/deployment to be successful.
Note:
If the GenAiPlanner
is New
then the associated Einstein bot
and Bot version
will also need to be deployed to the target org otherwise the deployed GenAiPlanner
will not be visible on the target org. It is recommended to always deploy any changes to the Einstein bot
and Bot version
alongside the GenAiPlanner
.
Example:
This GenAiPlanner
is dependent on the following GenAiFunction
:
EmployeeCopilot_AnswerQuestionsWithKnowledge
It is also dependent on the following GenAiPlugins
:
EmployeeCopilot_GeneralCRM
SvcCopilotTmpl_OrderInquiries
SvcCopilotTmpl_GeneralFAQ
Customer_Service_Assistant
If any of these GenAiFunctions
or GenAiPlugins
are not on the org or being deployed to the org along with the GenAiPlanner
then the validation/deployment will fail.
β
We will be adding Problem Analyzers over time to help highlight any missing GenAiFunction
or GenAiPlugin
dependencies before a validation or deployment occurs.