Johns Hopkins academic project

AI Inbox Triage & Drafting Assistant

A human-reviewed system for turning a crowded inbox into prioritized work, grounded summaries, and safer first-response drafts.

Scope: midterm project for Applied Generative AI study at Johns Hopkins, submitted under the assignment title AI Email Secretary. It uses a synthetic business scenario and sample email dataset; it is not connected to a live inbox and does not send messages autonomously.

  1. Sample inbox
  2. Previous-day filter
  3. 51 messages reviewed
  4. 23 critical messages
  5. Summarize and draft
  6. Evaluate against source
  7. Human review

Problem

A manager facing a mixed inbox needs to separate genuine emergencies and same-day deadlines from routine updates, informational messages, and spam. A useful assistant must reduce review time without mistaking urgent language for actual urgency—or making commitments on the manager’s behalf.

Approach

  1. Filter by fixed rules. Apply the Yesterbox method with pandas so only the previous day’s messages enter the workflow.
  2. Classify with guardrails. Sort messages into six defined categories while checking the full body, recipient, context, and actual deadline.
  3. Generate one item at a time. Produce source-grounded summaries, next steps, and first-response drafts for each critical email.
  4. Protect consequential decisions. Prevent the model from inventing approvals, commitments, attendance, attachment reviews, or unsupported facts.
  5. Evaluate against the source. Use a second model to score each draft for relevance, clarity, and actionability, with every score traceable to the original email.

Result

The workflow processed all 51 previous-day messages in the sample dataset. It identified 23 critical messages, generated complete summaries for 13 urgent and 10 deadline-driven emails, produced 23 first-response drafts, and evaluated all 23 drafts against their source messages.

The lower actionability score exposed the project’s most useful next step: make safe follow-up timing, ownership, and requests for missing information more specific without allowing the model to fabricate a decision.

Limits

The assistant supports triage and drafting; it does not make or send decisions. A person must verify classifications, facts, dates, and commitments before any response is sent.

← Back to AI & Media Operations