The moment it happens
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.
- Runs
- The moment it happens
- Apps
- Typeform
- AI
- Yes, uses the built-in AI allowance
- Access
- forms:read, webhooks:write
Send this to your assistant
Create a ClickRuntime automation: when a new Typeform response comes in, sort it into lead, support or spam, and email me only the leads with a one-line summary.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
A contact form on a busy site gets all kinds of messages: sales inquiries, angry customers, spam, job applicants and people who typed in the wrong box. If someone has to read every Typeform response to find the two that matter, hot leads sit for hours and complaints escalate. A sales lead who contacts a buyer in five minutes is far more likely to win the deal than one who writes back tomorrow.
The moment a response is submitted, this passes the answers to an AI step that decides what kind of message it is, such as a hot lead, a complaint or neither, and writes a one-line summary. It notifies you only for the categories you choose, with the summary and the answers.
Sales and support leads use it to focus on what needs a quick human reply.
What you get out of it
Hot leads get a fast reply
A buyer asking for pricing is flagged within seconds of submitting. Responding while they are still on your site, or at least at their desk, makes the difference between a sale and a lost inquiry.
Complaints get attention early
An unhappy customer who is flagged as a complaint can be called before they post a bad review. Early response turns many angry messages into retained customers. It also protects your public reputation online.
Notifications only when they matter
Casual messages, spam and general questions do not interrupt anyone. You are told only about the categories you picked, so alerts keep their value and are not ignored. A tired reader would take far longer on the same pile.
One-line summaries speed up reading
The summary gives you the gist before you open the response. You can decide in a few seconds whether to drop what you are doing, and pass the response to the right person.
Same standard for every response
A person triaging at 4 pm on Friday is tired and rushed, while the AI applies the same criteria every time. Fewer important messages are overlooked because of a bad day.
How it works
What happens, step by step
When someone submits your Typeform, ClickRuntime receives the response straight away.
AI reads the answers, decides whether it is a lead, support, spam or something else, and writes a one-line summary.
Only the categories you care about, such as leads, are sent on.
You get an email with the summary, and everything else stays quiet.
Before it runs live
- Connect Typeform
- Paste your automation's link into the other app's webhook settings
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 Slack
- Combine it with other Typeform steps into one automation
Under the hood
The code that runs this automation
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):
qa = answers((event.json or {}).get("form_response", {}))
text = "\n".join(f"{q}: {a}" for q, a in qa.items())[:3000]
result = ai.generate(text, system="Classify as lead, support or spam and give a one-line summary.",
json_schema={"type": "object", "properties": {"kind": {"type": "string", "enum": ["lead", "support", "spam"]},
"summary": {"type": "string"}}},
max_output_tokens=80).json
if result["kind"] == "lead":
notify.email_me(f"New lead: {result['summary'][:150]}", text)
return resultFAQ
Common questions
How does it decide what counts as a hot lead?
What happens to spam submissions?
Can the AI answer the customer?
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
Sort 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 worksSort support requests by urgency
Every new support form response is classified with AI, and urgent ones are posted to Slack straight away.
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 “Get told only about the responses that are leads” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.