Skip to content

On a schedule

Get alerted to Front conversations with no reply

Customers waiting more than two hours are flagged to you once, before they write again.

Runs
On a schedule
Apps
Front
AI
Not needed
Access
shared resources read

Send this to your assistant

Create a ClickRuntime automation: every 30 minutes, post to #support in Slack any open Front conversation in the Support inbox that has had no reply for 2 hours.

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

The worst customer experience in a shared Front inbox is silence. A prospect asks about pricing, the conversation lands as unassigned, each teammate assumes someone else has it, and two days later the prospect has signed with a competitor. Nobody did anything wrong; the thread just never had an owner or a deadline.

On the schedule you pick, open and unassigned conversations in the inbox are listed, and the last message in each is checked. If the latest message is from the customer and it has been waiting longer than your threshold, a note goes to Slack. Each conversation is flagged once, not on every run, so the channel does not turn into noise.

It is most useful for sales inboxes, support teams promising a response window, and small businesses where a single missed email can cost a job.

What you get out of it

  • Silent customers get noticed

    A conversation where the customer wrote last and nobody replied is flagged as waiting, which removes the risk that an enquiry slips through because everyone assumed it was handled. Even the quietest inbox gets the same level of attention.

  • Response promises are kept

    If your policy is a reply within one business day, an alert at the threshold gives you a chance to meet it rather than discovering the breach in a review.

  • Alerts fire once per conversation

    Remembering what has been flagged prevents a repeating nag, so teammates stay responsive to the alert instead of muting the channel after day two. A noisy alert is quickly ignored, so one clear message is better.

  • Shared inboxes get an implicit owner

    The Slack message nudges someone to pick the thread up, turning the vague idea that the team will deal with it into a visible, claimable item. Someone picks it up without a meeting about who should.

  • Lost deals are reduced

    Prospects who write in with a pricing question tend to move on quickly, so catching their email while the answer still matters protects revenue you already paid to attract. One rescued reply can pay for a lot of time.

How it works

What happens, step by step

  1. On the schedule you set, ClickRuntime checks your Front inbox for open and unassigned conversations.

  2. It looks at the last message in each and keeps the ones where a customer has been waiting more than two hours.

  3. Those are posted to #support with the subject and a link. Each conversation is only flagged once.

Before it runs live

  • Connect Front

What you get

RunsOn a schedule
Get alerted to Front conversations with no replytoday, 9:00Succeeded
Slack · #supportFront conversations waiting over 2 hours: • Refund for order 1042: https://app.frontapp.com/open/cnv_8f2a

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
  • Add an AI step, for example to summarize, sort or draft a reply
  • Add another app, for example also send it to Slack
  • Combine it with other Front 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.
unreplied_conversation_alert.pyexample
import time
from clickruntime import on_trigger, credentials, http, notify, state, report_fetched

INBOX_ID = "inb_55c4"  # Support
API = "https://api2.frontapp.com"

@on_trigger
def run(event):
    headers = {"Authorization": f"Bearer {credentials.secret('FRONT_API_TOKEN')}"}
    convs = http.get(f"{API}/inboxes/{INBOX_ID}/conversations", headers=headers,
                     params={"q[statuses][]": ["assigned", "unassigned"], "limit": 100}).json()["_results"]
    alerted = set(state.get("alerted") or [])
    waiting = []
    for c in convs:
        msgs = http.get(f"{API}/conversations/{c['id']}/messages", headers=headers, params={"limit": 1}).json()["_results"]
        if msgs and msgs[0]["is_inbound"] and time.time() - msgs[0]["created_at"] > 2 * 3600 and c["id"] not in alerted:
            waiting.append(c)
    report_fetched(len(waiting))
    if not waiting:
        return {"waiting": 0}
    lines = [f"• {c['subject'] or '(no subject)'}: https://app.frontapp.com/open/{c['id']}" for c in waiting]
    notify.slack("Front conversations waiting over 2 hours:\n" + "\n".join(lines), channel="#support")
    state.set("alerted", list(alerted | {c["id"] for c in waiting})[-1000:])
    return {"waiting": len(waiting)}

FAQ

Common questions

How does it know a customer is waiting for a reply?
It looks at the last message in each open or unassigned conversation. If the most recent message is inbound from the customer and older than your threshold, the conversation counts as waiting. A teammate reply resets the clock.
Will I be alerted again if nobody replies?
No. Each conversation is posted once and then remembered. If you want a second, stronger alert after another day with no reply, say so and that escalation step can be added. You choose how many nudges are worthwhile.
Can I set a different wait time for each inbox?
Yes. A sales inbox might alert after 4 hours while a general inbox waits 24. You describe the thresholds per inbox and approve the updated rule before it starts running. Thresholds are just settings, so adjusting them takes a moment.
What permissions does it need?
shared resources read. Nothing else in your accounts is used.
Does it need AI?
No. It runs without AI, so it doesn't use your plan's AI allowance.
How many runs does it use?
One run each time it checks. Checks that find nothing new and stop right away aren't counted.
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 “Get alerted to Front conversations with no reply” from your assistant

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