Per-Step Scoring: an Agentforce Architecture Guide

What is Per-Step Scoring in Agentforce architecture?

In Agentforce architecture, score subagent, action, and response steps individually so hidden step failures surface behind a polished final answer. This guide explains the design decisions, controls, and implementation checks needed to apply the pattern in production.

An agent can produce a confident, well-written final answer while a step in the middle silently failed. A subagent may have returned nothing, an action may have errored and been retried, or a retrieval step may have found irrelevant records. If you only evaluate the final response, none of this is visible.

Per-step scoring evaluates each stage of execution - subagent calls, action invocations, and response generation - as its own measurable unit. This turns observability from reading transcripts into tracking quality at the point where it is created.

Watch the steps, not just the answer

• A correct final answer can conceal a failed subagent handoff, a skipped action, or a degraded tool response.
• Each step type fails differently, so each needs its own scoring criteria rather than one generic quality score.
• Step-level scores create leading indicators that predict final-answer quality before users report problems.
• A failing step that is compensated downstream still counts as a defect and should be recorded, not excused.

Score each execution stage

1. Use session tracing to enumerate every subagent, action, and response step in a conversation and confirm none are dropped from evaluation.
2. Define per-step pass criteria: correct subagent selection, valid action inputs, successful action execution, and grounded response content.
3. Run test batches in Agentforce Testing Center and review step-level results alongside the final response, not instead of it.
4. Track step failure rates over time in analytics and alert when a specific step type degrades even while final answers hold steady.