Skip to content
← All AppsWeb SaaS

DeviceWatch

Keep up with FDA MAUDE reports for your devices without searching the database by hand. DeviceWatch gathers the reports, analyzes clinical narratives and drafts safety reports for qualified review.

My role
Independent developer
Status
Live web app

Inside the app

DeviceWatch demo review queue with Acknowledge, Flag and Reject actions
Review queueTriage controls beside sample adverse-event reports.
DeviceWatch report history listing sample PSUR, trend analysis and CAPA reports
Report historyGenerated report types, dates and review periods in the demo workspace.

From adverse event reports to review

Keeping up with MAUDE

Monitoring device reports means finding the relevant entries, reading the narratives and keeping a record of what needs attention. I built DeviceWatch to gather that material and put it into a review workflow.

Gathering and analyzing reports

Built on Next.js with Supabase for auth and data, DeviceWatch ingests MAUDE reports automatically, then uses Claude AI to parse clinical narratives, identify failure modes, classify severity and draft PSUR, trend analysis and CAPA reports for review.

Traceability and qualified review

The design includes audit trails, role-based access and data integrity controls to support regulated workflows. AI-generated assessments need traceable sources and qualified review before use in regulatory decisions.

Making assessments auditable

Building for regulated industries means every feature decision has compliance implications. Stripe billing, Resend transactional emails and Supabase RLS policies all had to be auditable. The AI prompts went through dozens of iterations to produce consistently structured clinical assessments.

Built with

Next.jsReactSupabaseClaude AIStripeResend

See the Full Product

Visit the marketing site for features, pricing and a free trial.