PRODUCT OVERVIEW
Agentforce Testing Copilot
Generates and runs Agentforce test conversations, then uses AI-assisted evaluation to assess the results.
PRODUCT FAMILY
Testing and QA
BUILT FOR
Cross-industry
PLATFORM
Salesforce
LICENSE
MIT
PRICING
Free
VERSION
1.0.0
THE NEED
The problem it solves
Manual conversation-by-conversation testing makes it difficult to evaluate agent quality, safety, and handling of sensitive information at scale.
THE PRODUCT
How it works
Agentforce Testing Copilot helps teams evaluate Agentforce agents from within Salesforce. It discovers agent coverage, generates test conversations, executes them, and uses a language model to evaluate the results. Teams can investigate failures and use assisted remediation for supported issues. It brings test generation, execution, evaluation, and diagnosis into one workflow.
CAPABILITIES
Key features
Agent discovery across org agents, topics, and actions
AI-generated test cases from actual agent configuration
Execution with LLM-based response judging
Root-cause analysis for failed tests
Autopilot fixing for well-understood failure patterns
Cross-channel visual testing for real browser-rendered conversations
USE CASES
Where it helps
Regression testing for Agentforce prompt, topic, and action changes
QA coverage for production Agentforce agent portfolios
Cross-channel validation for Messaging for Web and Experience Cloud
Release confidence for teams scaling beyond manual chat testing