# Daily LiveChat support health check posted to Slack

> Every weekday at 8am, get a short Slack read on yesterday's live chat performance against the same weekday last week, with the agents to coach named.

- Workflow type: agent
- Services: LiveChat, Slack
- Categories: Customer Support, Operations
- Published: 2026-08-07

## What it does

- Compares yesterday's live chat numbers with the same weekday one week earlier, so a normal Monday-versus-Sunday swing never looks like a crisis
- Writes a short narrative that leads with what actually changed, instead of dumping every metric into the channel
- Flags anything that moved more than 20 percent, plus satisfaction dipping below 85 percent and visitors giving up in the queue
- Names your strongest and weakest rated agents so team leads have something concrete to coach on

## What you'll need

- A LiveChat account with access to your reporting
- A Slack workspace and the channel you want the check posted into
- At least two weeks of chat history, so there is a prior week to compare against

## Prompt

Every weekday at 8am, post a support health check for yesterday into our Slack channel.

Work with two date windows. Window A is yesterday. Window B is the same weekday one week earlier, which is seven days before yesterday. Always compare A against B rather than against the day immediately before, because support volume is strongly seasonal by day of week and comparing a Monday against a Sunday produces false alarms.

For each of the two windows, pull these LiveChat reports: Total Chats, First Response Time, Response Time, Chat Duration, Chat Ratings, Queued Visitors Left, and Agent Performance. These are LiveChat Reports API methods, which are GET calls taking from and to query parameters, plus optional distribution, timezone, agents, groups and tags. Set from and to to cover the full day in our workspace timezone.

Compute the week-over-week percent change for every metric. Derive the satisfaction rating from Chat Ratings as good ratings divided by total rated chats. From Agent Performance and the per agent ratings, identify the agent with the strongest rating and the agent with the weakest rating across the yesterday window.

Write a short narrative that leads with what actually changed. Do not open with a table or a list of every number. The first line should say what moved and whether it matters. Supporting numbers come after, and metrics that held steady get compressed into a single line rather than one line each.

Flag any metric that moved more than 20 percent against the prior week, in either direction. Call out explicitly when the satisfaction rating falls below 85 percent, since 85 percent and above is the benchmark for healthy live chat, and treat anything below 70 percent as urgent. Call out explicitly when Queued Visitors Left has climbed, because visitors abandoning the queue means unanswered demand rather than merely slower service.

Name the two agents with the strongest and weakest ratings, with their actual numbers, so the team lead has something concrete to coach on. Only name an agent when they handled enough rated chats for the number to mean something. If the sample is too small, say so instead of naming someone off one or two ratings.

Post the finished message to Slack with Send a Message, into the support channel. Keep the whole message under twelve lines. Use Slack formatting, so single asterisks for bold. Always post, even on a quiet day: when nothing crossed a threshold, say so in a line or two rather than skipping the post.

If yesterday had very few chats, note the small sample rather than reporting large percentage swings as if they were signal. If a report returns no data for one of the two windows, say which comparison is unavailable and carry on with the rest.

## How to customize

- Change when it runs, or extend it to weekends if your team covers them
- Adjust the thresholds: the 20 percent swing alert and the 85 percent satisfaction floor
- Send it to a private channel or straight to the support lead as a direct message
- Add or drop metrics, for example if queue wait time matters more to you than chat duration

## Example output

*Support check: Tue 6 Aug vs Tue 30 Jul*
Response times slipped and the queue is leaking. Everything else held.

• First response time 48s, up 31% on last Tuesday, over the 20% line
• Visitors who left the queue: 14, up from 6. Worth checking 1pm to 3pm cover.
• Satisfaction 82%, below the 85% mark for a second week running
• Steady: total chats 212 (up 4%), chat duration 7m 10s (flat), response time 1m 55s (up 9%)
• Strongest ratings: Priya Raman, 96% good across 41 rated chats
• Weakest ratings: Tom Alvarez, 71% good across 34 rated chats

Suggested focus: early afternoon queue cover, and a ratings review with Tom.

## FAQ

### Why compare with the same weekday instead of just yesterday and the day before?

Support volume follows a strong weekly rhythm. A Monday almost always looks busier than the Sunday before it, so comparing consecutive days generates alarms about problems that do not exist. Lining Tuesday up against the previous Tuesday shows you real change instead of the normal shape of your week.

### Will it still post on a quiet day when nothing has changed?

Yes. It posts every weekday so the team gets a reliable signal. If nothing crossed a threshold it says so in a line or two rather than padding the message out.

### What if only a handful of chats came in yesterday?

It notes the small sample instead of reporting dramatic percentage swings. Two chats turning into four is a 100 percent increase and means nothing, and the check is written to say that rather than raise a false alarm.

### Do I need a particular LiveChat plan?

You need a LiveChat account whose plan includes the reporting section, since the check reads the standard chat volume, response time, ratings and agent performance reports you already see in LiveChat.

### Can it post to a private channel?

Yes, as long as the Slack account you connect is a member of that channel. You can also send it as a direct message if you would rather the support lead sees it before the wider team.

Use this prompt in General Input: https://www.generalinput.com/prompts/daily-livechat-support-health-check-posted-to-slack