What it is
Explainable AI is the practice of making an AI system show why it reached an answer or took an action, so people can check, trust and correct it. Methods include citing source documents, showing confidence scores, and exposing reasoning traces. It goes beyond simple grounding citations to the 'why' behind the agent's logic.
Why it matters
Admins and compliance teams need to justify AI-driven decisions to regulators, auditors, and customers, especially in regulated industries. Explainability builds the trust required for broader AI adoption across sensitive workflows.
Key components
- reasoning traces
- confidence scoring
- source citations
- decision audit logs
How it connects
In Agentforce, the Trust Layer's audit trail and the reasoning steps the Atlas Reasoning Engine records are the building blocks admins use to explain agent decisions to business stakeholders.
Good to know
Ask vendors whether reasoning traces are retained and queryable — not just the final answer — before deploying agents in regulated workflows.
Related terms
AI Governance Framework
The set of policies, roles and controls that decide which AI a company uses, on what data, and who answers for the results.
Atlas Reasoning Engine
The AI brain inside Agentforce that plans multi-step actions, evaluates options, and decides what to do next — all grounded in your Salesforce data.
Hallucination
When an AI confidently generates information that is factually wrong — the primary risk in any AI deployment without proper grounding.
Trust Layer
Salesforce's AI trust and safety framework that ensures agents operate within compliance boundaries, prevent misuse, and maintain data security.
