-> Create dataset from DrMalpani's previously sent mails. -> Train AI to reply like Dr. Malpani

Input = patient email (thread) + files if any Output = Doctor's reply + future thread thread: is a conversation ---x--- Ram has built the email syncing repo Check Task Updates of Row 115 1. coordinate with ram to get the dataset + prep dataset 2. train model (fine tune gemini or openai model) 3. respond to new email using trained model 4. share example responses (should contain: input, expected_output, actual_output) (end goal expectation: AI drafts email; client can approve it) There will be separate modules of: 1. AI replies 2. Lead qualification 3. Analysis: key info extraction Siddhant: divide it into sub-tasks first