Salesforce Agentic Orchestration and Flow
Summary
The article highlights new Salesforce Flow enhancements introduced in the Summer ’25 release that enable embedding Agentforce AI agents directly into various Flow types for richer automation. It solves the challenge of extracting structured, specific data from unstructured AI agent responses via Structured Outputs, allowing those outputs to be used downstream in automated actions seamlessly. Additionally, it previews upcoming MCP Server support to broaden integration possibilities by connecting any agent technology to all Salesforce actions. Salesforce teams can now orchestrate automated processes that smartly combine AI agent reasoning with deterministic business logic safely and effectively.
Takeaways
- Embed Agentforce agents into Screen, Autolaunched, and Record-Triggered Flows via the Action element.
- Use Structured Outputs to define and extract specific data values from AI agent responses.
- Map structured outputs as flow resources for downstream processing and integrations.
- MCP Servers will soon enable connecting any agent tech to all Salesforce invocable actions.
- Combine agent reasoning with deterministic flow logic for controlled and safe automations.
Innovation in agentic orchestration is accelerating rapidly, and our automation product teams have been hard at work improving Flow to make it easier than ever to bring agents and human-centered work together. With the Summer ’25 release, we’ve introduced powerful new capabilities that help you embed Agentforce agents into your automations and extract structured data from agent responses. I also have an update on how we’re tapping into MCP to make Flow and Action Platform capabilities available to the full power of all actions —connect any agent technology to the full power of Salesforce actions. Add agents to automation with Flow & Agentforce As of Summer ‘25 release, you can now easily insert Agentforce agents into most flows. This video from Liz Awad, one of our product managers, demonstrates a flow that features two different embedded Agentforce agents.