Weekly
Get a weekly summary of your survey answers
Each Monday you get the main themes, the overall mood and a few notable quotes from last week's responses.
- Runs
- Weekly
- Apps
- Typeform
- AI
- Yes, uses the built-in AI allowance
- Access
- responses:read
Send this to your assistant
Create a ClickRuntime automation: every Monday at 9am, summarise last week's responses to my 'Product survey' Typeform: main themes, overall sentiment and 3 notable quotes. Email it to me.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
A customer survey with 300 open-text answers is a goldmine that nobody reads. The researcher or product manager who owns the Typeform opens the results page, scrolls through the first twenty comments, forms an impression and moves on. The strongest themes, like confusing pricing or a missing integration, never get counted, and the next planning meeting runs on anecdotes.
Each week, this fetches the responses collected since last week from your Typeform, passes the answers to an AI step that summarizes the mood and groups comments into themes with a sense of how common each is, and emails you the result. You get an overview in a couple of minutes of reading.
It works for customer satisfaction surveys, event feedback forms and employee pulse checks. Product and research teams can read it before their planning meeting.
What you get out of it
Open answers actually get read
Three hundred free-text comments become a one-page summary. The feedback you asked people to write is turned into something a busy team will genuinely take in, so the effort of collecting it pays off.
Themes are named and weighed
The summary groups similar comments and says which come up most. A complaint repeated forty times stands out from one raised twice, which helps you decide what deserves engineering time.
Sentiment trend week to week
Comparing summaries across weeks shows whether the mood is improving after a change. You can tell if a new onboarding flow reduced confusion, using what respondents wrote in their own words.
Quotes for the roadmap discussion
Representative phrases from respondents give your recommendations weight. Colleagues react to a customer's own words more than to a chart, and it helps to have the real wording ready. Real quotes keep roadmap debates grounded in customers.
Smaller teams get research capacity
A company without a dedicated researcher can still make sense of its surveys. The weekly rhythm keeps feedback flowing into decisions without anyone setting aside a day to code comments by hand.
How it works
What happens, step by step
Once a week, ClickRuntime collects every response your Typeform survey received in the last seven days.
AI reads the answers, picks out the main themes and judges the overall mood.
You get an email with the themes, the sentiment and a few telling quotes.
Before it runs live
- Connect Typeform
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
- Run it at a different time, more or less often, or only on weekdays
- 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 datetime import datetime, timedelta, timezone
from clickruntime import on_trigger, http, credentials, ai, notify
FORM_ID = "PRODUCT_SURVEY_FORM_ID"
def typeform(method, path, **kw):
r = http.request(method, f"https://api.typeform.com{path}",
headers={"Authorization": f"Bearer {credentials.secret('TYPEFORM_TOKEN')}"}, **kw)
r.raise_for_status()
return r.json() if r.content else None
@on_trigger
def run(event):
since = (datetime.now(timezone.utc) - timedelta(days=7)).strftime("%Y-%m-%dT%H:%M:%SZ")
items = typeform("GET", f"/forms/{FORM_ID}/responses", params={"since": since, "page_size": 1000})["items"]
texts = [a["text"][:500] for r in items for a in r.get("answers") or [] if a["type"] == "text"]
if not texts:
notify.email_me("Product survey: no responses last week", "Nothing to summarise.")
return {"responses": 0}
summary = ai.generate("Give the main themes, overall sentiment and 3 notable quotes:\n" +
"\n".join(f"- {t}" for t in texts), max_output_tokens=600).text
notify.email_me(f"Product survey: {len(items)} responses last week", summary)
return {"responses": len(items)}FAQ
Common questions
Does the AI see names and email addresses?
What if a week has very few responses?
Can it handle responses in other languages?
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 a daily count of responses per form
Each morning you see how many responses each form got yesterday, compared with last week.
See how it worksGet a weekly CSV of your responses
Every Friday you get the week's responses as a CSV, so you have your own copy.
See how it worksGet warned when a form stops getting responses
If a form that normally gets responses goes quiet for a day, you hear about it so you can check it.
See how it worksKeep exploring
Set up “Get a weekly summary of your survey answers” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.