Daily

Get a morning summary of what people messaged

Each day a Slack post groups yesterday's inbound messages into themes, complaints and questions.

Runs: Daily
Apps: Sprout Social
AI: Yes, uses the built-in AI allowance
Access: API token

Send this to your assistant

Create a ClickRuntime automation: every morning at 8:30, summarise yesterday's inbound Sprout Social messages into top themes, complaints and common questions, and post it to #social 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 social media manager at a consumer brand opens Sprout Social's Smart Inbox every morning to a few hundred messages across Instagram, Facebook, X and LinkedIn: product questions, shipping complaints, a few compliments, and some spam. Reading all of them just to know what people are talking about takes an hour before any replies are written. Leadership asks what customers are saying, and the honest answer is a feeling, backed by whichever messages the manager happened to remember.

Each morning, ClickRuntime queries Sprout for inbound messages from the last 24 hours, and its built-in AI groups them into themes, complaints and questions, with a few representative quotes for each. The summary is posted to a Slack channel before the working day starts, so the team knows what to expect before opening the inbox.

Community managers, support leads and brand teams that need a daily read on sentiment will find it especially useful.

What you get out of it

The day starts with a clear picture
Knowing that most messages concern a delayed delivery or a broken discount code lets the team prepare replies and escalate early, instead of working it out one message at a time.
Complaints are escalated sooner
A cluster of similar complaints is easy to miss message by message, but obvious in a summary. Support and operations can then act on the cause the same morning, not after a week.
Leadership gets real answers
When an executive asks what customers are saying, the manager can point to a dated summary with examples instead of offering an impression. That supports better decisions on messaging and product.
Repeat questions reveal content gaps
If forty people ask the same question about sizing or returns, a post or FAQ is clearly needed. The daily summary shows which questions keep arriving, and how often. Writing one clear answer once saves the team from typing it a hundred times.
Manager time goes to replies
Sorting messages by hand eats the first hour of every day. Handing the sorting to a summary leaves the manager free to write thoughtful responses to the people who need them. Better replies are what customers actually notice, and they reflect well on the brand.

How it works

What happens, step by step

Every day ClickRuntime collects the messages people sent your social profiles in the last 24 hours through Sprout Social.
AI reads them and sums them up as the main themes, complaints and common questions.
The summary is posted to your #social Slack channel with the number of messages. On a day with no messages, nothing is posted.

Before it runs live

Connect Sprout Social

What you get

RunsDaily

Get a morning summary of what people messagedtoday, 9:00Succeeded

Slack · #social*Yesterday's inbound messages (143)* Themes: shipping times, new colours. Complaints: late EU deliveries.

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

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 Sprout Social 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.

daily_ai_summary_of_inbound_messages.pyexample

from datetime import datetime, timedelta, timezone
from clickruntime import on_trigger, credentials, http, ai, notify

API = "https://api.sproutsocial.com/v1"

def sprout():
    h = {"Authorization": f"Bearer {credentials.secret('SPROUT_API_TOKEN')}"}
    cid = http.get(f"{API}/metadata/client", headers=h).json()["data"][0]["customer_id"]
    return h, cid

@on_trigger
def run(event):
    h, cid = sprout()
    now = datetime.now(timezone.utc)
    msgs = http.post(f"{API}/{cid}/messages", headers=h, json={
        "filters": [f"created_time.in({(now - timedelta(days=1)).isoformat()}..{now.isoformat()})", "activity_type.eq(INBOUND)"],
        "fields": ["text", "network"], "limit": 200}).json()["data"]
    if not msgs:
        return {"messages": 0}
    text = "\n".join(f"- [{m['network']}] {(m.get('text') or '')[:300]}" for m in msgs)[:30000]
    summary = ai.generate(f"Summarise these social messages into: top themes, complaints, common questions.\n{text}",
                          max_output_tokens=500).text
    notify.slack(f"*Yesterday's inbound messages ({len(msgs)})*\n{summary}", channel="#social")
    return {"messages": len(msgs)}

FAQ

Common questions

Which networks does the summary cover?

It covers any network connected to your Sprout Social account that delivers inbound messages, such as Instagram, Facebook, X and LinkedIn. If you want only one network or one brand profile, the query can be narrowed.

Does the summary quote real customers?

It can include short representative quotes next to each theme, which helps your team see the tone. If privacy is a concern, you can ask for themes only, with no names or handles in the post.

What counts as a theme?

The AI groups messages by what they are about, for example delivery delays, pricing questions or praise for a product. The number of themes depends on the day. You can also ask it to focus on particular topics.

What permissions does it need?

API token. Nothing else in your accounts is used.

Does it need AI?

Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.

How many runs does it use?

One run each time it runs (daily). Checks that find nothing to do 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.

Weekly