A HIPAA-compliant ambient AI co-pilot for home health clinicians. It transcribes the patient visit live and turns it into OASIS-E1 and follow-up notes, on Android and iOS.
Flutter engineer, 10-person team
- Mobile (Flutter & iOS)
- Full-Stack & SaaS
- AI & Automation
- Flutter (Dart)
- Azure Speech-to-Text
- OpenAI API
- Azure SQL
- Firebase
- Android & iOS
- CI/CD (GitHub)
- Figma
Home health clinicians lose hours typing visit notes after each patient. AutoMynd records the visit with live Azure Speech-to-Text and turns it into OASIS-E1 and follow-up notes the clinician reviews. In a 10-person team at a Sri Lankan partner company, I built the Med-Recon medication flow, auto-correction for live transcripts, and the mapping that uses OpenAI to place extracted answers into the right survey questions. I also handled encrypted, HIPAA-aligned data storage in the app, fixed UI bugs and published releases to Google Play and the App Store.
- 01Transcript to survey mapping. OpenAI reads the live transcript and fills the matching OASIS questions, so clinicians review answers instead of typing them.
- 02Live transcript auto-correction. I cleaned up Azure Speech-to-Text output as it streamed in, so the text that feeds the notes is accurate from the start.
- 03Med-Recon flow. I built the medication reconciliation step inside the visit, giving clinicians a guided way to review the patient's med list on the spot.
- 04HIPAA-aligned storage. Patient data kept in the app is encrypted and handled under HIPAA rules, and I shipped the releases to Google Play and the App Store.