AI-Drafted Follow-Up Emails Personalized to Every Prospect's History
Built an AI system that drafts, sends, and tracks personalized follow-up emails on its own.
Manually re-reading meeting notes and writing a personalized follow-up email from scratch for every prospect
~6 hrs/week
The Challenge
Following up with a prospect after a call meant a rep re-reading the meeting notes, remembering what got discussed, checking the calendar for open slots, and writing a personal email from scratch, for every single prospect in the pipeline. Once reps got busy, follow-ups went out generic, late, or not at all.
The Solution
I built an AI follow-up system that drafts personalized emails using a prospect's real history. A Draft Generator pulls the prospect's record, meeting history, and past follow-up emails from Airtable, merges it all together, and hands that context to an AI Agent along with a relevant case study and message template pulled from Airtable, so the draft actually references what was discussed instead of reading like a generic sequence. A Send workflow picks up the draft, checks real calendar availability as a callable tool the AI Agent can query, sends the finished email through Gmail, and logs the result back to Airtable as Sent or Error. A retry path waits and rechecks failed sends instead of losing them silently, and a manual override lets a rep regenerate a single email's subject and body from the template if the AI draft needs a human pass.
How It Works
The Results
Follow-up emails go out referencing the actual conversation and the right case study instead of a generic template, without a rep spending time writing them by hand. Send status tracks itself in Airtable, so a failed send gets retried instead of just disappearing, and a rep only steps in when a specific email genuinely needs a human touch.
Tools & Technologies Used
How To Create This
- Pull the prospect's record, meeting history, and past follow-up emails from Airtable and merge them into one context object
- Look up a relevant case study and message template from Airtable as callable tools for the AI Agent, so drafts reference proof points instead of generic claims
- Use an AI Agent with a structured output parser to draft the follow-up sequence based on that merged context
- Build a Send workflow that gives the AI Agent a calendar-availability tool so it can reference real open slots when drafting the email
- Send the finished email through Gmail and log the result back to Airtable with a Sent or Error status
- Add a wait-and-retry path for failed sends, and a manual override workflow to regenerate a single email from the template when a human needs to step in
Related Case Studies
AI-Powered Ticket Routing From a Single Slack Mention
An AI agent that reads a plain Slack @mention and turns it into a fully assigned ClickUp ticket, across IT, EA, and other departments, with no form to fill out.
Closed-Loop Sales Automation System Across Calendly, Close CRM, ClickUp & Slack
A suite of connected n8n workflows that carry a booked call all the way through pre-call prep, CRM sync, audit QA, and daily reporting, so no rep has to touch five separate tools by hand.
