How Does Agent Script Give Admins More Control?
The discussion highlights the new Agentforce Builder with its Agent Script feature, which introduces a hybrid reasoning engine giving admins more control and predictability over AI agents. Instead of copying old agents, admins are encouraged to learn and build new agents using Agent Script, which combines AI autonomy with human-directed behavior scripting. The new builder includes a visual Canvas mode and AI assistant to simplify script creation. This approach lets admins iteratively improve AI agents in Salesforce, balancing automation with hands-on customization for better user experiences.
- Agent Script enables admins to control AI agent behavior with a human-in-the-loop approach.
- The new Agent Builder uses a hybrid reasoning engine, requiring fresh agent builds instead of copy-pasting old ones.
- Canvas mode provides a visual representation of Agent Script for easier script development and understanding.
- Start building new agents with Agent Script before migrating existing ones to learn and adapt.
- Leverage the AI assistant in Agent Builder to help create and refine AI agent scripts.
Today on the Salesforce Admins Podcast, we talk to Joshua Birk, Senior Director of Admin Evangelism at Salesforce. Join us as we chat about how to get started with Agent Script and how it helps admins build better AI agents. You should subscribe for the full episode, but here are a few takeaways from our conversation with Joshua Birk. What is Agent Script? Big changes are coming to how admins build AI agents with Salesforce, and so I’ve brought Josh Birk on the pod to help us understand what’s going on with the new Agentforce Builder. There are backend updates to the Atlas Reasoning Engine, but Agent Script is where the rubber meets the road for admins. It’s a simple, high-level scripting language that lets you create complex instructions and actions for your agent to follow. Agent Script puts the human in the loop for all the little decisions an AI makes, helping you build more predictable and reliable agentic solutions.