The Task Resolution metric, which scores agent outcomes for agents created with the new Agentforce Builder, is generally available. Tune and improve your agent’s effectiveness based on knowing how well it understands and resolves a user’s task. Deliver more meaningful outcomes that satisfy the user’s intent as expressed in a given conversation.
Where: This change applies to Lightning Experience in Enterprise, Performance, Unlimited, and Developer editions with Foundations or Agentforce 1 editions. Setup for AI agents is available on the desktop site.
When: The Task Resolution metric is available starting February 20th, 2026.
How: Confirm that Einstein Audit and Feedback is turned on in your org. If not, follow the instructions in Set Up Einstein Generative AI Audit and Feedback. Then, build your agent using the new Agentforce Builder (Beta). Once your agent is operational in a production or sandbox environment, outcomes are automatically scored (Fully Resolved, Partially Resolved, and Unresolved) across all agent types. Scores and accompanying explanations are streamed directly to a Data Model Object (DMO) in Data 360. Build your own Data 360 dashboards and reports and run queries to spot trends, interpret results, and remedy agent issues.