Define what your agent is built to achieve, map the observability tools that measure it, and build the plan that connects your KPIs to testing and monitoring before your agent goes live.
Required Editions
| Available in: Lightning Experience |
| Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type. |
Effective testing starts before you run a single test. Most measurement plans fail in one of two ways:
- Success is stated so abstractly that nothing can be instrumented.
- People measure what is easy to measure and quietly redefine success as that.
Agentforce surfaces a wide range of signals and metrics across several tools. Without a plan that connects them to the outcomes your organization tracks, it’s easy to measure the wrong things, draw the wrong conclusions, and optimize in the wrong direction. These topics prepare you for the test phase of the Agent Development Lifecycle so that your testing is grounded in clear goals, not guesswork.
- Define Agent Success
Agentforce surfaces a lot of data. Without a clear sense of what your agent is supposed to accomplish, that data creates noise instead of direction. Defining success before you start measuring is how you know which signals matter, which ones to ignore, and when your agent is actually improving. - Understand Agentforce Observability KPIs and Tools
Observability isn't a single tool. It's a layered toolchain that includes infrastructure that captures agent activity, development tools to test your agent pre-deployment, and monitoring tools that surface trends and session-level details after deployment. - Build an Agent Testing and Observability Plan
A test plan and a monitoring plan turn your definition of agent success into something measurable. The test plan helps identify regressions before they reach production and shows that the agent is ready for deployment. The monitoring plan helps you recognize and address areas for improvement after go-live.