Moosa Memon
← Index of work

An appointment setter that books inside the Instagram DM

SetterFlow: qualifies inbound Instagram leads through ordinary conversation, filters out the ones who aren't a fit, and books the rest onto the calendar without ever leaving the thread. No booking link, no channel switch. Built for coaches, consultants and agencies selling high-ticket offers.

Type
Agents
Stack
Python / LLM / n8n / Calendar API / Instagram DMs
Status
Complete; conversation graph with greet → qualify → book states and tagged outcomes

Problem

High-ticket offers get sold in DMs, and the moment a setter sends a booking link the conversion drops: the lead has to leave the app, land on a page, pick a slot, come back. Human setters avoid this by asking for a time in the thread. The agent had to do the same, and it had to qualify honestly first, because a booked call with someone who can’t invest wastes the closer’s hour.

System

A state graph: greet opens with a question about why they reached out; qualify walks through goal, timeline and investment level in natural turns rather than a form; leads that don’t fit get a warm exit and a tag; the ones that do get offered three real slots from the calendar in the thread and a confirmed booking on the reply. Each transition tags the contact (setterflow-qualified, setterflow-booked) so the CRM and follow-up automations key off state, not guesswork.

Worth knowing

The qualifying questions are ordered the way a good human setter orders them (motivation, urgency, budget last) because asking about money first kills the conversation. The agent owns the wording; the slot list comes from the calendar, so it can only offer times that actually exist, which is the same “tools own the truth” rule as the WhatsApp booking agent elsewhere on this site.

Have a workflow that looks like this?

Most of these start as a messy, manual process someone got tired of. Twenty minutes is usually enough to sketch how I'd approach yours.