Skip to content

The moment it happens

Sort support requests by topic and urgency

Each support form submission gets a category and urgency, and urgent ones reach you in Slack.

Runs
The moment it happens
Apps
Typeform
AI
Yes, uses the built-in AI allowance
Access
webhooks:write

Send this to your assistant

Create a ClickRuntime automation: when my 'Support' Typeform gets a response, sort it by category (billing, bug, account, other) and urgency, and post the urgent ones to #support in Slack.

Paste it into your assistant. It tells you what it will send or change before it runs live.

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A support form that dumps everything into one inbox leaves the team to sort it. Billing questions, bug reports, feature requests and password problems arrive mixed together, and a person has to read each before deciding who handles it and how fast. Urgent outages are read last when they arrive late in the day, and nobody can say which topics generate the most requests.

Each time someone submits your Typeform, an AI step reads the request and assigns a topic and an urgency level. The flow keeps a running count per category and posts urgent requests to your team channel straight away, so the right person sees the right request.

It suits small support teams that do not yet have a full help desk. Counts build up in the background to show where requests come from.

What you get out of it

  • Urgent requests get seen first

    A customer reporting that they cannot log in is flagged as urgent and posted straight away. The team responds to the serious cases while routine ones wait in the queue.

  • Requests reach the right person

    Topic labels let billing questions go to finance and bugs go to engineering. Fewer handoffs and forwarded emails mean customers get answers from the right person sooner. Handoffs and forwarded emails drop quickly across the team.

  • Counts show where the pain is

    The running totals per category reveal that a third of requests are about one feature. That is a clear argument for fixing the product or writing a help article. Planning conversations get real numbers to work with.

  • Consistent labels

    A tired person will label requests differently from one day to the next. The AI applies the same categories every time, which makes the counts comparable week to week. Weekly comparisons become much more trustworthy than before.

  • Helps small teams scale

    A team of two can handle growing volume without hiring just to sort mail. Triage happens instantly and the humans spend their time answering. Sorting never becomes the bottleneck on a small team.

How it works

What happens, step by step

  1. When a support request comes in through your form, ClickRuntime picks it up straight away.

  2. AI reads it and decides the topic, such as billing or login, and how urgent it is.

  3. It keeps a running count of requests per topic.

  4. Urgent requests are posted to your #support Slack channel with the sender's email and the issue, so someone can jump on them.

Before it runs live

  • Connect Typeform
  • Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens
Sort support requests by topic and urgencyjust nowSucceeded
Slack · #supportUrgent billing request Email: ap@acme.example · Issue: We were charged twice this month.

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.
  • 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 Slack
  • Combine it with other Typeform steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.
support_request_categorisation.pyexample
from clickruntime import on_event, ai, notify

def answers(resp):
    titles = {f["id"]: f["title"] for f in resp["definition"]["fields"]}
    out = {}
    for a in resp["answers"]:
        value = a.get(a["type"])
        if isinstance(value, dict):
            value = value.get("label") or ", ".join(value.get("labels", []))
        out[titles.get(a["field"]["id"], a["field"]["id"])] = value
    return out

@on_event
def handle(event):
    resp = (event.json or {}).get("form_response", {})
    if resp.get("definition", {}).get("title") != "Support":
        return {"posted": False}
    text = "\n".join(f"{q}: {a}" for q, a in answers(resp).items())[:3000]
    r = ai.generate(text, system="Categorise this support request.", max_output_tokens=60,
                    json_schema={"type": "object", "properties": {
                        "category": {"type": "string", "enum": ["billing", "bug", "account", "other"]},
                        "urgent": {"type": "boolean"}}}).json
    if r["urgent"]:
        notify.slack(f"Urgent {r['category']} request\n{text}", channel="#support")
    return r

FAQ

Common questions

Can I define my own categories?
Yes. You list the topics that match your business, such as billing, bug, how-to and feedback, with a short description of each. The AI chooses from your list, and you can edit it as you learn.
What does urgent mean here?
You define it. Common choices are anything about being unable to use the product, payment failures or security concerns. Everything else is normal priority, and you can add a middle level if needed. You can add a middle level too.
Does it reply to the customer?
No. It categorizes and notifies, and your team writes the reply. If you want an acknowledgment sent automatically, that can be added, but it would be shown to you for approval first. Sending an automatic acknowledgment is possible.
What permissions does it need?
webhooks:write. Nothing else in your accounts is used.
Does it need AI?
Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.
How many runs does it use?
One run for each event the app sends.
Can I change how it works?
Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

Set up “Sort support requests by topic and urgency” from your assistant

Copy the prompt above, or connect your assistant first. Free plan, no credit card.