Each new Typeform response
Sort support requests by urgency
Every new support form response is classified with AI, and urgent ones are posted to Slack straight away.
- Runs
- Each new Typeform response
- Apps
- Typeform, Slack
- AI
- Yes, uses the built-in AI allowance
- Access
- Typeform responses sent to the trigger link; Slack post to one channel
Send this to your assistant
Create a ClickRuntime automation: when someone submits our support form in Typeform, use AI to sort it as urgent, normal or spam. Post urgent ones to #support in Slack with a one-line summary.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
Most support inboxes treat every message the same way: first in, first out. That works until a customer who was charged twice, or who can't log in before a launch, waits behind a dozen "how do I change my password" questions. By the time someone reads the urgent request, the customer has been waiting for hours and has started looking for other ways to be heard.
This template reads every new request the moment it arrives, decides whether it is urgent, normal or spam, and posts the urgent ones to your team's Slack channel with a one-line summary. Your team sees what matters first, without anyone having to watch the form all day.
What you get out of it
Urgent issues get attention right away
Billing errors, outages and blocked accounts reach a person in minutes, even when the queue is long or the team is busy with other work.
A better experience for customers
A fast reply when something is really wrong is what customers remember. Handling the worst moments quickly builds trust and keeps people coming back.
Fewer bad reviews and public complaints
Customers who feel ignored write one-star reviews and post on social media. Answering urgent problems before frustration builds lowers that risk.
Fewer disputes and chargebacks
A customer who was charged twice and gets no reply often goes to their bank. Spotting payment problems early lets you refund before a dispute is raised, which saves fees and protects your account with the payment provider.
Less time spent sorting
Agents no longer read every message just to decide what to answer first. Spam is filtered out and normal requests stay in the queue, so the team spends its time on replies.
A record you can learn from
Every request is logged with its label and summary, so you can see how many urgent issues come in, when they happen and what they are about.
How it works
What happens, step by step
Typeform sends each new response to the automation's trigger link.
ClickRuntime checks Typeform's signature, so only real responses run.
The script sends the message text to the AI model and gets back a label and a one-line summary.
Urgent requests are posted to #support. Everything else is logged in the run history.
Before it runs live
- Connect Slack
- Add a webhook in Typeform pointing at the trigger link
- Save Typeform's signing secret as a secret
What you get
Build your own
Need it to work differently?
Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.
Changes you can ask for
- Act only on the items that match your own rules, and skip the rest
- Change what the AI looks for, or how it writes the result
- Add another app, for example also send it to Google Sheets
- Combine it with other Typeform and Slack steps into one automation
Under the hood
The code that runs this automation
from clickruntime import on_event, ai, notify, log
@on_event
def handle(event):
answers = event.json["form_response"]["answers"]
message = " ".join(a.get("text", "") for a in answers)
result = ai.generate(
f"Support request:\n{message[:2000]}",
system="Label the request urgent, normal or spam and summarise it in one line.",
json_schema={"type": "object", "properties": {
"label": {"enum": ["urgent", "normal", "spam"]},
"summary": {"type": "string"}}},
)
if result.json["label"] == "urgent":
notify.slack(f"Urgent: {result.json['summary']}", channel="#support")
log.info("triaged", result.json)
return result.jsonFAQ
Common questions
Does this need an AI account?
What if the AI gets the label wrong?
Can I change what counts as urgent?
Does it work with other help desks or forms?
Can urgent requests go to email or a different channel?
Does each request count as a run?
What permissions does it need?
Does it need AI?
How many runs does it use?
Can I change how it works?
Related
You might also like
Get told only about the responses that are leads
Each response is sorted into lead, support or spam, and only leads reach you, with a one-line summary.
See how it worksSort support requests by topic and urgency
Each support form submission gets a category and urgency, and urgent ones reach you in Slack.
See how it worksGet every new Typeform response by email
Each time someone fills in your form, the answers land in your inbox with the question titles.
See how it worksKeep exploring
Set up “Sort support requests by urgency” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.