Daily

Turn answered Slack questions into FAQ pages

Questions your team has already answered in Slack become FAQ articles in your Notion knowledge base.

Runs: Daily
Apps: Notion, Slack
AI: Yes, uses the built-in AI allowance
Access: Slack channels:history, reactions:read; Notion insert

Send this to your assistant

Create a ClickRuntime automation: every day, take threads in #help marked with a ✅ reaction, write each one up as a short FAQ article and add it to my Knowledge Base in Notion.

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

In a support or internal help channel, the same question is asked every few weeks: how to reset an integration, which form to use for expenses, why a report shows zero. A colleague answers well in a thread, everyone says thanks, and the answer disappears. The next person asks again, someone else spends ten minutes typing a similar reply, and the knowledge base stays empty because nobody has time to write it up.

Each day ClickRuntime looks for threads marked with a reaction such as a checkmark, fetches the replies, and uses its built-in AI to turn the question and the accepted answer into a short FAQ article. It creates the page in Notion and records the thread as done, so the same thread is not turned into an article twice.

Support teams, IT desks and community managers use it to grow a knowledge base from work they already do.

What you get out of it

Answers are captured once and reused
A well-answered thread becomes a page that can be linked the next time the question appears. The tenth person gets a link in ten seconds. The tenth person to ask gets a link within seconds, and the expert is not interrupted again.
Writing the article is no longer a chore
The AI drafts the question and answer from the thread, so a person only checks it. Knowledge base articles appear because someone added a reaction, which takes one second. Articles appear because someone added a reaction, which takes one second.
Fewer repeated questions for experts
Subject experts spend less of the week retyping the same answers. They answer once, mark the thread, and move on to work only they can do. They answer once, add the reaction and move on to work that only they can do.
The knowledge base reflects real questions
Articles come from what people actually ask, in their own words. That makes the help pages easier to search than ones written from the author's guess about what readers want.
Drift from outdated answers is reduced
Each article links back to its source thread and date. When a process changes, you can find and update the matching page instead of finding out via complaints. When a process changes, you can find and update the matching page instead of learning about it from complaints.

How it works

What happens, step by step

Every day, ClickRuntime looks in your #help Slack channel for answered threads marked with a ✅ reaction.
It skips threads it has already turned into articles and reads the full thread for each new one.
AI writes a clear question-and-answer FAQ article from the discussion.
The article is saved as a page in your Notion knowledge base.

Before it runs live

Connect Notion and share the database you want it to use
Connect Slack, then invite the app to the channel (type /invite @ClickRuntime there)

What you get

RunsDaily

Turn answered Slack questions into FAQ pagestoday, 9:00Succeeded

Notion · Knowledge BaseNew FAQ: How do I reset two-factor login for a teammate? (from a #help thread)

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 Google Sheets
Combine it with other Notion and Slack 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.

faq_articles_from_slack_threads.pyexample

from slack_sdk import WebClient
from clickruntime import on_trigger, credentials, http, state, ai

CHANNEL_ID = "C0123HELP"
DATABASE_ID = "your-knowledge-base-database-id"

@on_trigger
def run(event):
    slack = WebClient(token=credentials.connection("slack", "work"))
    done = set(state.get("done") or [])
    history = slack.conversations_history(channel=CHANNEL_ID, limit=200)["messages"]
    marked = [m for m in history if m.get("reply_count") and m["ts"] not in done
              and any(r["name"] == "white_check_mark" for r in m.get("reactions", []))]
    for m in marked:
        thread = slack.conversations_replies(channel=CHANNEL_ID, ts=m["ts"])["messages"]
        text = "\n".join(r["text"] for r in thread)[:8000]
        faq = ai.generate(text, max_output_tokens=500,
                          system="Turn this support thread into an FAQ article. No names.",
                          json_schema={"type": "object", "properties": {"question": {"type": "string"}, "answer": {"type": "string"}}}).json
        http.post("https://api.notion.com/v1/pages",
                  headers={"Authorization": f"Bearer {credentials.secret('NOTION_TOKEN')}", "Notion-Version": "2022-06-28"},
                  json={"parent": {"database_id": DATABASE_ID},
                        "properties": {"Name": {"title": [{"text": {"content": faq["question"][:200]}}]}},
                        "children": [{"object": "block", "type": "paragraph",
                                      "paragraph": {"rich_text": [{"text": {"content": faq["answer"][:2000]}}]}}]})
        done.add(m["ts"])
    state.set("done", sorted(done)[-1000:])
    return {"articles": len(marked)}

FAQ

Common questions

Which reaction triggers an article?

Any emoji you choose, such as a white check mark or a book. Only threads with that reaction are processed, so you decide what is good enough to become a page by adding it. Pick one that people will not use for other purposes.

Does the AI add information that was not in the thread?

It is instructed to use only the content of the thread. Because it is a draft in Notion, a person can review and edit the article before sharing the page with the wider team. Treat each page as a draft until a person has approved it.

Will private threads be included?

It reads channels the Slack connection has been added to. Choose a public help channel for a shared knowledge base, and avoid channels where people discuss customers or personal details. Keeping the source channel focused also keeps the knowledge base focused.

What permissions does it need?

Slack channels:history, reactions:read; Notion insert. 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.

DailyAI