Veeva AI Agents

Note

The functionality described on this page is only available to customers who have licensed Veeva AI.

Veeva AI agents use a Large Language Model (LLM) to perform agent actions in your Vault. Agent configuration determines both the available actions and how the LLM responds to the user in Veeva AI Chat. For example, depending on configuration, different agents may give different responses when executing the same action.

Agents are Vault-specific, meaning they cannot interact with data on other Vault domains or outside of your Vault.

Before developing with Veeva AI, you should be familiar with the following concepts:

• Agent: Contains the agent configuration definition, which includes the set of available agent actions, the agent objective, agent context, and any configured agent tools.
• Agent Objective: Defines the agent’s roles and responsibilities, similar to a job description.
• Agent Context: Defines the information an agent knows about your Vault, allowing the agent action to use this information when creating a response. Agent context can include both object and document metadata and document content. With Vault Java SDK, your organization can create custom context types.
• Agent Action: The actions users can execute with Veeva AI, such as Summarize Document and Translate Record. Agents perform agent actions based on the provided agent objective, context, and instructions. If the action is configured for Veeva AI chat, users can execute agent actions in the Vault UI through Veeva AI chat. Developers can also execute actions through Vault API or Vault Java SDK. Agent actions include the following attributes:
  • Agent Action Description: Defines the purpose of the agent. While the primary goal of the description is to provide the purpose of this action to users and Vault Admins, Vault sends this information to your LLM to help it understand the agent action.
  • Agent Action Instructions: Defines how to run the agent action. Your LLM uses these instructions to understand how to prepare and present output for the action.
• Agent Tools: You can assign agent tools to agent actions. When executing an agent action, your LLM can request agent tools and use Vault’s tool response to complete the action. With Vault Java SDK, your organization can create custom agent tool types.