CI/CD

💬 In plain words: The most common Agentforce deployment failure is a partial metadata set. An agent deployed without its underlying custom actions, flows, Apex classes, prompt templates, or permission sets looks active in Setup, yet fails quietly when users interact with it. The definitive test for your release pipeline is deleting the agent from a disposable scratch org and redeploying everything solely from Git with zero manual clicks.

💬 In plain words: Your Salesforce Agentforce agent is a code file, not hidden settings buried in a database. Saving an agent creates Bot , BotVersion , and GenAiPlannerBundle metadata files. Because it is just a file, standard software rules apply: put it in Git, review pull requests, run automated tests, and deploy it cleanly across environments.

💬 In plain words: Because Large Language Models (LLMs) generate probabilistic output, your test suite scores will bounce around slightly even if you haven't touched a single line of code. To find your noise floor , run your exact same test suite three times without making any changes. The mathematical spread between those three scores is your normal variance. If a score change happens inside that spread, it means nothing. ⚡ Key Points AI test scores vary naturally; a drop in your score is not always a bug. Without measuring your baseline variance (the noise floor), your test scores are uninterpretable. Your Continuous Integration (CI) gate threshold must be set just outside the observed spread. Always re-measure your noise floor when you add a significant chunk of new test cases to your suite.

💬 In plain words: Testing Center is your dedicated AI validation hub. Located directly inside Agentforce Studio (right next to Agent Builder and Observability), it replaces manual trial-and-error testing. It can automatically generate test cases, simulate full multi-turn conversations using different user personas, and mathematically score the results against rules you define. ⚡ Key Points Location: Testing Center is a native, dedicated tab in Agentforce Studio, completely removed from traditional Salesforce Setup. Expected vs. Actual: Every test case requires you to define an expected subagent and an expected action, allowing for direct comparison. Scale with AI: Instead of writing hundreds of tests by hand, use AI-generated cases to instantly build synthetic interactions. Custom Evaluations: Score your agents using strict deterministic rules (Strings/Numbers) or an LLM-as-a-Judge. Cost Awareness: Running these automated test suites c...