Email Digital Twin
AI-powered email persona and draft engine for Gmail workflows.
ET
Email Twin
Case study visual placeholder
Architecture flow
4 layersProblem
Generic AI email replies rarely match a person's actual writing habits, creating drafts that require heavy editing before they feel usable.
My Role
Designed the product flow, OAuth-backed email analysis path, backend integration, and prompt structure for reply generation.
Solution
A Chrome Extension and Node.js backend authorize Gmail access, analyze sent-mail writing signals, and generate multiple draft styles with Gemini.
Stack
Case study
Problem
Generic AI email replies rarely match a person's actual writing habits, creating drafts that require heavy editing before they feel usable.
Proof signal
Chrome Extension · OAuth2 Gmail API · 4 draft variants · Gemini LLM
My Role
Designed the product flow, OAuth-backed email analysis path, backend integration, and prompt structure for reply generation.
Core product work
- Email history analysis
- Tone and formality modeling
- Formal, concise, casual, and context-adjusted drafts
Solution
A Chrome Extension and Node.js backend authorize Gmail access, analyze sent-mail writing signals, and generate multiple draft styles with Gemini.
Chrome Extension with a Node.js backend. OAuth2 authorizes Gmail access, sent mail is analyzed for behavioral writing signals, and Gemini generates Formal, Concise, Casual, and Context-Adjusted variants.
Architecture Highlights
OAuth2-backed Gmail integration
Recursive MIME extraction and PII-safe writing-persona analysis
Multiple draft variants for different reply contexts
Challenges and Tradeoffs
- Keeping AI-generated replies useful without overstating persona accuracy.
- Handling private email data through an explicit OAuth-based flow.
Impact / Outcome
- Built a working prototype for personalized AI email drafting.
- Integrated real Gmail API access instead of relying on pasted sample text.
- Made generated drafts easier to compare by producing multiple variants.
Learnings
- Personalized AI products need clear user control and fallback paths.
- Prompt quality improves when generation is grounded in concrete behavior signals.
Next Steps
- Add stronger privacy controls and explicit local/remote processing boundaries.
Keep exploring