Overview
Let clinicians switch between dictation and ambient capture in the same visit and still end up with one note. Dictated sentences land in the right section, unchanged from the transcript.
How it works
Dictation and ambient capture attach to the same visit. For each section of the template the clinician chooses whether the content comes from dictation, the ambient conversation, extracted facts, or a mix. Dictated sentences are placed in the right section without rewording. Where dictation and ambient both cover a section, the dictation is kept and the ambient content only fills gaps, and a check makes sure the dictated sentences are unchanged in the final text. Sentences that don’t fit any section are shown as unallocated. The clinician reviews before signing.
What Corti handles
- Medical speech recognition for both dictation and conversation
- Placing dictated sentences into template sections
- Writing the ambient parts of the note from the conversation
- Checking that dictated text survives unchanged
What you build
- The switch between dictating and ambient capture in your interface
- Which source each template section should use
- The review screen and saving the signed note
Make it yours
- Write the instructions the agent follows
- Choose the language people speak
- Start from a ready-made template, or write your own
- Pick the model the agent runs on
- Let punctuation be added automatically, or only when someone says it
- Decide the structure and writing style of each document
- Connect the tools and data sources it can use
- …and much more