Skip to main content
Learn about the differentiating factors and research fuelling FactsR here. This guide is a more hands-on API guide.

​
Purpose and Behaviour of FactsR

Rather than summarizing the full conversation in one go, FactsR breaks the workflow into four core steps:
1

Extract

The Corti LLM pulls out clinically relevant facts.
2

Refine

Each fact is automatically evaluated along medically-relevant criteria and improved through an agentic feedback loop to ensure accuracy, structure, and clinical relevance.
3

Human Review

Clinicians can quickly review, discard, or adjust facts. This design keeps clinicians in control, ensuring that AI augments rather than replaces clinical judgment.
4

Compose

Generate the final, EHR-ready document using only validated facts, structured according to standard formats like SOAP or other formats facilitated via custom templates.

​
How to Extract Facts with FactsR

Facts can be extracted in both a real-time and asynchronous workflow.
Click on the cards to learn more…

Real-time

Extract facts in real-time as the ambient conversation unfolds.

Asynchronous

Extract facts via REST, independent of a WebSocket audio stream, from a text input.