Skip to content

Every 15 minutes

Sort Page comments and flag complaints

Questions and complaints on your posts reach you within 15 minutes, while praise and spam stay out of your way.

Runs
Every 15 minutes
Apps
Facebook Pages
AI
Yes, uses the built-in AI allowance
Access
pages_read_engagement, pages_read_user_content

Send this to your assistant

Create a ClickRuntime automation: every 15 minutes, sort new comments on my Facebook Page into question, complaint, praise or spam, and email me the questions and complaints with links.

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

On a busy Facebook Page, the comments that matter most are buried among likes, tags and emoji. A customer asking whether an item ships to Canada, or complaining that an order never arrived, waits as long as a friend saying nice photo. Unanswered questions look like neglect to everyone who scrolls past, and complaints left public can grow into a thread of agreement. The cost shows up as lost sales and a Page that looks unattended.

Every 15 minutes, ClickRuntime pulls the new comments on your Page's posts and has its built-in AI sort them into questions, complaints and everything else. Only the first two reach you, with the comment text, the author and a link to the post.

It is especially useful when one person handles social media alongside other duties.

What you get out of it

  • Answer questions while they matter

    A buyer asking about sizing is deciding whether to purchase right now. A flagged question reaches you within fifteen minutes, so the answer arrives before they move to a competitor's page.

  • Contain complaints before they spread

    A public complaint attracts others with the same experience. Seeing it quickly lets you reply with an apology and a fix, which limits the thread and shows other readers that someone is listening.

  • Ignore the noise safely

    Praise, emoji and tags do not need action. Filtering them out removes most of the volume, so a notification means something specific and does not train you to ignore the feed.

  • Spot recurring product issues

    When three flagged comments in a week mention the same late delivery or broken part, the pattern is visible in your notifications. That evidence helps you take the problem to operations.

  • Share social workload fairly

    Because flagged items come with links, you can forward a complaint to support or a question to sales. Each team handles what belongs to them without everyone reading every comment.

How it works

What happens, step by step

  1. Every 15 minutes ClickRuntime collects new comments on your 10 most recent Facebook Page posts, so none is checked twice.

  2. AI labels each comment as a question, a complaint, praise or spam.

  3. Questions and complaints are emailed to you with a link to each comment, while praise and spam are left alone.

Before it runs live

  • Connect Facebook Pages

What you get

RunsEvery 15 minutes
Sort Page comments and flag complaintstoday, 9:00Succeeded
Email · 2 Facebook comments need you[complaint] My order from last week still hasn't arrived https://www.facebook.com/104857600000000/posts/7731?comment_id=91

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
  • 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 Facebook Pages 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.
ai_comment_triage.pyexample
from datetime import datetime, timezone
from clickruntime import on_trigger, credentials, http, state, ai, notify, report_fetched

G = "https://graph.facebook.com/v21.0"
PAGE_ID = "104857600000000"

def page_token():
    user = credentials.connection("facebook", "work")
    return http.get(f"{G}/{PAGE_ID}", params={"fields": "access_token", "access_token": user}).json()["access_token"]

@on_trigger
def run(event):
    token = page_token()
    since = state.get("since") or int(datetime.now(timezone.utc).timestamp()) - 900
    posts = http.get(f"{G}/{PAGE_ID}/posts", params={"limit": 10, "access_token": token}).json()["data"]
    comments = [c for p in posts for c in http.get(f"{G}/{p['id']}/comments", params={
        "since": since, "fields": "message,permalink_url", "access_token": token}).json()["data"]]
    report_fetched(len(comments))
    if not comments:
        return {"summary": "Nothing new"}
    numbered = "\n".join(f"{i}. {c['message'][:300]}" for i, c in enumerate(comments))
    labels = ai.generate("Label each comment question, complaint, praise or spam. One label per line, same order.\n" + numbered,
                         max_output_tokens=10 * len(comments)).text.lower().split()
    flagged = [f"[{l}] {c['message']}\n{c['permalink_url']}" for c, l in zip(comments, labels) if l in ("question", "complaint")]
    if flagged:
        notify.email_me(f"{len(flagged)} Facebook comment(s) need you", "\n\n".join(flagged))
    state.set("since", int(datetime.now(timezone.utc).timestamp()))
    return {"comments": len(comments), "flagged": len(flagged)}

FAQ

Common questions

Does it reply to the comments?
No. It only flags questions and complaints and tells you where they are. A separate version drafts replies for your approval. Nothing is posted publicly under this one without you. You keep control of what, if anything, goes public.
How does it tell a question from a complaint?
The AI reads the comment's wording and intent, not just question marks. A comment like 'still waiting on my order' counts as a complaint even without punctuation. You can adjust the categories if you want, for example, 'pricing questions'. Edge cases can land in either group, and you can review the flagged ones quickly.
Will it read comments on old posts?
It checks new comments on recent posts on each run. Replies on posts older than the lookback window may be missed, and the window can be extended if your older posts keep attracting comments. Ask for a longer window if you promote evergreen posts.
What permissions does it need?
pages_read_engagement, pages_read_user_content. 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 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 “Sort Page comments and flag complaints” from your assistant

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