Agentforce Observe

This is the production debugging workflow for Agentforce agents. It queries session traces from Salesforce Data Cloud's STDM (Session Trace Data Model) to surface real user failures, then lets you reproduce issues locally with `sf agent preview` and edit the `.agent` file directly. The three-phase loop is observe, reproduce, improve. It auto-detects your agent name and file path, handles the CLI's known double-nesting bug on retrieve, and falls back to test suites plus local traces if STDM isn't activated in your org. Use this when you're chasing regressions or weird production behavior, not when you're drafting new agents or writing tests.

skills.sh installs: 5.8K
GitHub stars: 1.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add forcedotcom/sf-skills --skill agentforce-observe --agent claude-code

Installs into .claude/skills of the current project.

Files

Agentforce Observability

Improve Agentforce agents using session trace data and live preview testing.

Three-phase workflow:

Observe -- Query STDM sessions from Data Cloud (if available), OR run test suites + preview with local traces as fallback
Reproduce -- Use sf agent preview to simulate problematic conversations live
Improve -- Edit the .agent file directly, validate, publish, verify

Platform Notes

Shell examples below use bash syntax. On Windows, use PowerShell equivalents or Git Bash.
Replace python3 with python on Windows.
Replace /tmp/ with $env:TEMP\ (PowerShell) or %TEMP%\ (cmd).
Replace jq with python -c "import json,sys; ..." if jq is not installed.