On a schedule

Get a Slack alert for chats rated bad

A bad rating shows up in Slack with the visitor's comment and a link to the transcript.

Runs: On a schedule
Apps: LiveChat
AI: Not needed
Access: chats--all:ro

Send this to your assistant

Create a ClickRuntime automation: when a LiveChat chat is rated bad, post the agent's name, the visitor's comment and the transcript link to #chat-quality in Slack.

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

Add to ChatGPT Add to Claude

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

Why use it

Why teams use this automation

A customer who rates a LiveChat conversation as bad is telling you that something went wrong: the agent was rude, the answer was wrong or the problem was not solved. In most support teams that signal lands in a report that nobody looks at until the end of the month, by which time the customer has left a review, canceled or told others about their experience.

On its schedule, ClickRuntime lists recent archived chats in LiveChat, keeps only those where the customer's rating is bad and posts them to Slack with the customer, the agent and a link to the transcript. The support lead sees them in time to apologize, fix the problem and coach the agent while the case is still fresh.

It is aimed at support managers who want to react to unhappy customers quickly.

What you get out of it

Unhappy customers get a second chance
A message from a manager the same day, apologizing and solving the problem, can turn a bad experience into loyalty. Waiting weeks removes that chance. That is cheaper than any win-back campaign you could run.
Coaching happens while the chat is fresh
An agent who is shown a bad chat the same day remembers what happened and can learn from it. A review a month later is mostly forgotten and feels like criticism.
Patterns in problems appear
If several bad ratings in a week come from the same issue, such as a billing bug, the channel shows it. That points to a fix in the product rather than in the training.
Reviews and churn are reduced
Customers who feel heard are less likely to post a public complaint or leave. Reaching out quickly protects your reputation online, where one bad experience can reach many people. That protects revenue you might never have known was at risk.
Quality is measured on real feedback
Rather than sampling random chats, you look at the ones customers marked as bad. That focuses your review effort on the conversations that matter most. That makes reviews fairer and far more useful.

How it works

What happens, step by step

Every 15 minutes ClickRuntime checks LiveChat for chats rated bad since its last check, so each one is posted only once.
For each one it picks out the agent who handled it and the visitor's comment.
A message goes to your #chat-quality Slack channel with the agent, the comment and a link to the chat transcript.

Before it runs live

Connect LiveChat

What you get

RunsOn a schedule

Get a Slack alert for chats rated badtoday, 9:00Succeeded

Slack · #chat-qualityBad rating for Theo: "Felt rushed, question not answered" https://my.livechatinc.com/archives/R8KQ2

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 LiveChat 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.

bad_rating_alert.pyexample

from datetime import datetime, timezone
from clickruntime import on_trigger, credentials, http, state, notify, report_fetched

@on_trigger
def run(event):
    since = state.get("since") or datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%S.000000Z")
    chats = http.post("https://api.livechatinc.com/v3.5/agent/action/list_archives",
                      json={"filters": {"from": since, "properties": {"rating": {"score": {"values": [0]}}}}},
                      headers={"Authorization": f"Bearer {credentials.connection('livechat', 'work')}"}).json()["chats"]
    report_fetched(len(chats))
    if not chats:
        return {"summary": "Nothing new"}
    for c in chats:
        agent = next((u["name"] for u in c["users"] if u["type"] == "agent"), "unknown agent")
        comment = c["thread"].get("properties", {}).get("rating", {}).get("comment", "no comment")
        notify.slack(f"Bad rating for {agent}: \"{comment}\"\nhttps://my.livechatinc.com/archives/{c['id']}",
                     channel="#chat-quality")
    state.set("since", max(c["thread"]["created_at"] for c in chats))
    return {"posted": len(chats)}

FAQ

Common questions

How often does it check for bad ratings?

It runs on a schedule, for example every 30 minutes or hourly, and looks at archived chats since the last check. A chat is only rated and archived after it ends, so alerts come shortly after the conversation closes rather than during it.

Does it catch ratings that customers change later?

The automation looks at the rating when it checks the chat. If a customer changes their rating after the check, the alert for that chat will not be updated. Only a rating that is bad at the time of the check is reported.

Can the alert include the full transcript?

It links to the chat in LiveChat by default, since full transcripts are long and contain personal data. If you want the last few messages in Slack to give context, that can be included, ideally in a private channel.

What permissions does it need?

chats--all:ro. 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.

On a schedule