This module develops the analytical skill of verifying Dragon Copilot-generated draft sections—history, assessment, and plan—against the source clinician-patient conversation to confirm accuracy before EHR finalization. Learners will be able to systematically compare draft content to known conversation content and identify discrepancies requiring correction. This verification capability is critical for preventing documentation errors from becoming part of the permanent patient record.

This module builds the evaluative judgment to assess Dragon Copilot note quality across three dimensions—completeness, clinical relevance, and workflow fit—as notes recur across multiple documentation scenarios over time. Learners will be able to apply a quality evaluation framework to identify patterns, rate overall note quality, and provide actionable feedback to improve templates and workflows. This capability enables health administration professionals to move beyond individual note review toward systematic quality management of AI-generated documentation.

In this project, you verify and finalize a complete Dragon Copilot documentation package, executing the full workflow from ambient capture configuration through source-conversation verification to quality evaluation for a multi-note batch representing a realistic half-day clinic session, including three encounters (configuration for all three; verification for two). You'll produce a finalized documentation package that demonstrates your ability to configure, verify, and evaluate AI-generated clinical notes at operational volume. This deliverable mirrors the daily work of clinical documentation staff who manage Dragon Copilot output quality in real healthcare settings.