Pull real enquiries out of social media noise
Use AI to read your social comments and DMs, summarise the genuine leads, log them to a sheet, raise a ticket, and alert the team — while the noise gets filtered out automatically.
What this looks like
One step on screen at a time. Read it, do it, tap Next.
Pull real enquiries out of social media noise
Step 1 of 12
Get incoming comments into the workflow
Create a workflow and add a Webhook node as the entry point for incoming comments or messages, or a Schedule Trigger paired with a HTTP Request node if you're polling an export instead.
Checkpoint
A test POST to the webhook URL produces an item in the workflow.
Before you begin
Tick these off as you sort them. Stopping halfway to create an account is how a fifteen-minute build becomes an hour.
0 of 9 ready
Ticks are saved on this device, so you can come back to them.
- Know-how
This depends on your platform — a webhook from your social tool, an export you poll, or a form your team pastes messages into. Decide this before building the trigger.
- Have ready
Columns for Platform, Author, Message, Summary, Category, Date. This becomes your record of what came in, genuine or not.
- Account
Tickets get raised here automatically, so make sure the project and issue type you plan to use already exist.
- Credential
Generate one from your Atlassian account settings and add it as a credential.
Atlassian API tokens - Permission
Genuine leads get posted here in near real time.
The basics — ticked once, remembered everywhere
- Account
Either the hosted version or a self-hosted install. Everything here works the same on both — the only visible difference is the shape of your webhook URLs.
Create a workspace - Know-how
Adding a node, connecting two of them, and pressing Execute. If any of that is new, the free primer covers it in about ten minutes.
- Credential
You will paste at least one secret during setup. A password manager beats a notes app, and it stops you pasting a live key into a chat window by accident.
The shape of the workflow
The nodes you will end up with, left to right, in the order you add them.
4 things to set here- 1Webhook — the trigger — everything starts here
- 2Set — Normalise the incoming fields
- 3OpenAI — Classify and summarise with AI
- 4Code — Parse the AI's response
Skip the node hunting
Import a starter file with every node for this build already on the canvas, named after its step and wired in order, each one carrying a sticky note with the values to enter. You still connect your own accounts and fill the fields — that is what the walkthrough takes you through — but you never start at a blank canvas.
In n8n: Workflows → Import from file.
What you will build
Jump straight to any step, or print the list and tick it off beside your n8n tab.
- 1Get incoming comments into the workflow
- 2Normalise the incoming fields
- 3Classify and summarise with AI
- 4Parse the AI's response
- 5Log everything to the sheet
- 6Branch on category
- 7Raise a Jira ticket for leads and support issues
- 8Alert the team in Slack for leads
- 9Test the full range of message types, then activate
- 10Send a clearly genuine enquiry
- 11Send an obvious spam comment
- 12Review a week of logged entries against the AI's categories
If something goes wrong
Everything ready?
Start walkthrough