An active Instagram fills the DM inbox with a mix of real leads, support questions, and spam that nobody sorts. This agent triages every inbound message through Manychat, tagging each one by intent.
An active Instagram fills the DM inbox with a mix of real leads, support questions, and spam that nobody sorts. This agent triages every inbound message through Manychat, tagging each one by intent.
It drafts an on-brand reply, pushes qualified leads to your CRM, and routes anything sensitive to a person. Genuine buyers get a quick response instead of waiting behind a pile of spam, and your team stops scrolling DMs by hand.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Classify each DM as a lead, a support question, spam, or a collaboration request.
pending
Draft a reply for the matching intent and apply the right tags to the contact.
pending
Send qualified leads to your CRM and route anything sensitive to a human inbox.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Classify this Instagram DM into lead, support, spam, or collab, and draft a short on-brand reply.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.