Weekly

Get a weekly report on what people say on X

Every Monday you see the main themes from the past week on your topic and five post ideas.

Runs: Weekly
Apps: X
AI: Yes, uses the built-in AI allowance
Access: tweet.read

Send this to your assistant

Create a ClickRuntime automation: every Monday at 9am, search X for posts about 'remote work' from the last 7 days and email me the main themes, the general mood and 5 ideas for posts.

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

Anyone building an audience on X, from a SaaS founder to a local brand, wants to know what people in their niche are actually discussing. The usual method is scrolling search results for twenty minutes, copying a few interesting posts and hoping a pattern appears. It is subjective, it rarely happens weekly, and good post ideas sit unspotted in the conversation.

Once a week, recent posts mentioning your chosen keywords are searched on X. ClickRuntime's built-in AI reads them, identifies the main themes and the overall sentiment, and proposes post ideas based on what people are asking or complaining about. The report is emailed to you.

Content marketers and community managers use it to feed their editorial calendar with topics their audience already cares about. The report gives you a weekly view of your niche that no single search could.

What you get out of it

Post ideas come from real demand
Writing about questions people are already asking in your niche beats guessing, because the topic has an audience before you publish. That reduces the risk of spending a week on content nobody wanted.
You see the mood around a topic
A weekly sentiment read shows whether people are excited, frustrated or confused about something, which shapes how you phrase your own posts. Tone matters as much as topic, because the same subject needs a different post when people are angry.
Complaints become opportunities
When users repeatedly grumble about a competitor's pricing or a missing feature, you find out, and you can address it in a post or a product decision. That is often the best opening for a post that positions you as the solution.
Research takes minutes, not an evening
Reading a structured report once a week is shorter than scrolling X for twenty minutes and does not depend on you having a free hour. The hour you save goes toward writing the posts that the report suggests.
Trends are tracked over time
Comparing weekly reports shows which themes grow and which fade, giving you a feel for where the conversation in your niche is heading. Spotting a rising theme early lets you publish while few others are covering it.

How it works

What happens, step by step

Once a week, ClickRuntime searches X for recent posts about your keywords.
AI reads them and pulls out the main themes, the overall mood and a few content ideas.
You get an email summarising what people said this week, with the themes, the mood and the ideas listed.

Before it runs live

Connect X

What you get

RunsWeekly

Get a weekly report on what people say on Xtoday, 9:00Succeeded

Email · What people said about remote work this weekThemes: return-to-office mandates, async meetings, home office costs. Mood: tired but pragmatic. Idea 1: "The 3 meetings we replaced with a doc"

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 X 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.

content_insights_from_what_s_being_said.pyexample

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

@on_trigger
def run(event):
    auth = {"Authorization": "Bearer " + credentials.connection("x", "main")}
    start = (datetime.now(timezone.utc) - timedelta(days=6, hours=23)).strftime("%Y-%m-%dT%H:%M:%SZ")
    tweets = http.get("https://api.x.com/2/tweets/search/recent", headers=auth, params={
        "query": '"remote work" -is:retweet lang:en', "start_time": start, "max_results": 100,
    }).json().get("data", [])
    if not tweets:
        return {"tweets": 0}
    text = "\n".join(f"- {t['text'][:200]}" for t in tweets)
    report = ai.generate(
        "From these posts about remote work, list the main themes, describe the overall mood in one line, "
        "and suggest 5 ideas for posts.\n\n" + text,
        max_output_tokens=600,
    ).text
    notify.email_me("What people said about remote work this week", report)
    return {"tweets": len(tweets)}

FAQ

Common questions

What search terms does it use?

The keywords or phrases you provide, such as your product name, a competitor or a topic like zero-waste packaging. Your AI assistant can add several searches and exclude retweets or other noise to keep the results relevant.

How many posts does it analyse each week?

It reads the recent posts returned by the X search, and the volume depends on your API access and the popularity of the keywords. A narrow keyword set yields a focused report, while a broad one is summarised at a higher level.

Is the sentiment analysis reliable?

It is a useful indication rather than a measurement. Short posts, slang and sarcasm can mislead any automated reading, so treat the themes as prompts to explore, and open a few of the underlying posts before acting on a surprising finding.

What permissions does it need?

tweet.read. 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 (weekly). 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.

Every few hours / dailyAI