Daily
Get a daily summary of customer conversations
Each evening you get one email on what customers asked about today and what's still open.
- Runs
- Daily
- Apps
- Intercom
- AI
- Yes, uses the built-in AI allowance
- Access
- read conversations
Send this to your assistant
Create a ClickRuntime automation: every weekday at 6pm, summarise today's Intercom conversations by topic and list the ones still open, then email it to me.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
The head of support wants to know what customers talked about today, but the only way to find out is to open Intercom and read. There are 150 conversations a day, so nobody reads them all, and the picture comes from whichever threads happened to catch an agent's eye. A confusing checkout error that hit forty customers is only recognized three days later, when somebody mentions it in a meeting.
Each day, ClickRuntime searches Intercom for conversations updated today, passes their content to built-in AI, and emails you a summary of the main themes, notable complaints and common questions. You get a readable picture of the day in a few minutes without reading individual conversations.
Support managers, product managers and founders who want to hear the voice of the customer without reading every thread will use it most.
What you get out of it
Recurring problems show up within a day
A bug or confusing screen that hits many customers appears as a theme in the summary. You can alert engineering the same day, instead of discovering the pattern after another round of complaints.
Product decisions use real customer language
Product managers get a daily sense of what people ask for and what confuses them. That grounds the roadmap in actual questions instead of in the loudest internal opinion. They can bring concrete examples of customer wording into planning meetings the very next morning.
Leaders stay close to customers
Founders and executives rarely read support threads, but they can read a short email. A daily summary keeps them informed about customer sentiment and avoids the disconnect that grows when leadership is far from the front line.
Shifts and teams stay aligned
When support is spread across time zones, the summary tells the next shift what happened earlier. People start work knowing which issues are active instead of reconstructing it from the inbox.
Knowledge base gaps are exposed
If the summary keeps mentioning the same how-to question, there is a missing or hidden help article. Writing it reduces the number of conversations the next day. Each one costs the team repeat conversations every day until somebody writes the missing article and links it in the messenger.
How it works
What happens, step by step
Every day, ClickRuntime collects the Intercom conversations updated that day.
AI groups them by topic, such as billing questions or login issues, and notes how many are still open.
You get one email with the summary.
Before it runs live
- Connect Intercom
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 Intercom steps into one automation
Under the hood
The code that runs this automation
import re, time
from clickruntime import on_trigger, http, credentials, ai, notify
def intercom(method, path, **kw):
r = http.request(method, f"https://api.intercom.io{path}", headers={
"Authorization": f"Bearer {credentials.secret('INTERCOM_TOKEN')}", "Intercom-Version": "2.11"}, **kw)
r.raise_for_status()
return r.json()
INBOX = "https://app.intercom.com/a/inbox/_/inbox/conversation/"
@on_trigger
def run(event):
since = int(time.time()) - 86400
convos = intercom("POST", "/conversations/search", json={
"query": {"field": "created_at", "operator": ">", "value": since}, "pagination": {"per_page": 150}})["conversations"]
lines = [f"{c['id']} [{c['state']}] {re.sub(r'<[^>]+>', '', c['source']['body'] or '')[:300]}" for c in convos]
summary = ai.generate("Group today's support conversations by topic with counts:\n" + "\n".join(lines),
max_output_tokens=500).text
still_open = "\n".join(f"{INBOX}{c['id']}" for c in convos if c["state"] == "open")
notify.email_me(f"Intercom today: {len(convos)} conversations", f"{summary}\n\nStill open:\n{still_open or 'none'}")
return {"conversations": len(convos)}FAQ
Common questions
Does the summary contain customer names or personal details?
How many conversations can it summarize in a day?
Can I get a summary for just one team or tag?
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
Review yesterday's closed conversations for quality
Each morning you get the five weakest conversations from yesterday, scored for tone and resolution.
See how it worksGet a weekly support volume and CSAT report
Every Monday you see conversations opened and closed and the average rating, compared with the week before.
See how it worksClose conversations waiting on the customer for a week
Conversations where the customer went quiet for 7 days are closed, and you get the list.
See how it worksKeep exploring
Set up “Get a daily summary of customer conversations” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.