Gopniyaगोपनीय

Clinics want cloud AI to write discharge advice in Hindi. The note carries Aadhaar, ABHA and phone numbers, names and home addresses. This agent strips them inside your browser, sends the cloud model only placeholders, checks its answer, and puts the real values back on your side.

Loading the local Python runtime…

Clinic side · this browserraw text stays here


        
      

Answer, restored on the clinic side

Run the agent to see the answer with the real values back in place.
perimeter

    Cloud side · Workers AIgemma-4-26b

    What the cloud model receives

    
          

    What the cloud model returns

    Nothing sent yet.

    Measured on synthetic notes. No field deployment yet.

    Loading measurements…

    Protection recall counts an identifier as protected only when every character of it is covered. Precision counts a redaction as correct when it overlaps a labelled identifier.

    All test notes are synthetic and generated from templates. The held-out set was written by a separate author who did not see the detection code. Real notes will be messier; the numbers above are an upper bound until a clinic pilot measures them on real text.

    Redaction runs in your browser through Pyodide. Only the redacted note crosses the perimeter. The demo endpoint re-checks for identifiers and refuses text that still contains them, caches answers, and stops after a small daily number of model calls.