Every hour

Announce each new blog post on LinkedIn and X

When you publish an article, it's shared on LinkedIn and X within half an hour, with copy written for each.

Runs: Every hour
Apps: LinkedIn, X
AI: Yes, uses the built-in AI allowance
Access: LinkedIn w_member_social; X tweet.write

Send this to your assistant

Create a ClickRuntime automation: every 30 minutes, check my blog feed. For each new article, write a LinkedIn post and a short X post, share both with the link, and remember the article.

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 SaaS startup's team writes good engineering articles, but sharing them depends on whoever wrote them remembering to post. Some get shared on LinkedIn only, some nowhere.

Every new article is now shared on both networks within half an hour of publishing, with a LinkedIn post that explains why it matters and a short X version.

What you get out of it

Every article reaches readers
Nothing published goes unshared.
Written for each network
A fuller LinkedIn post and a short X post.
Shared fast
Posts go out while the article is new.
Never twice
Each article is remembered once shared.

How it works

What happens, step by step

Every 30 minutes, ClickRuntime checks your blog feed.
It skips articles already shared.
AI writes a LinkedIn post and a short X post for each new article.
Both are published with the article link, and the article is remembered.

Before it runs live

Connect LinkedIn
Connect X

What you get

RunsEvery hour

Announce each new blog post on LinkedIn and Xtoday, 9:00Succeeded

LinkedIn · NorthwindWe cut our build times from 14 minutes to 3. Here's what actually made the difference (it wasn't more machines).

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 LinkedIn and 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.

share_each_new_blog_post_on_linkedin_and_x.pyexample

import feedparser
from clickruntime import on_trigger, credentials, http, ai, state, report_fetched

AUTHOR = "urn:li:organization:12345"

@on_trigger
def run(event):
    shared = state.get("shared") or []
    new = [e for e in feedparser.parse("https://northwind.example/engineering/feed").entries if e.link not in shared]
    report_fetched(len(new))
    if not new:
        return {"summary": "No new articles"}
    for e in new:
        posts = ai.generate(f"Article: {e.title}. LinkedIn post (under 700 chars) and X post (under 220 chars).", max_output_tokens=400,
                            json_schema={"type": "object", "properties": {"linkedin": {"type": "string"}, "x": {"type": "string"}}}).json
        http.post("https://api.linkedin.com/rest/posts",
                  headers={"Authorization": f"Bearer {credentials.connection('linkedin', 'work')}", "LinkedIn-Version": "202409"},
                  json={"author": AUTHOR, "commentary": posts["linkedin"], "visibility": "PUBLIC", "lifecycleState": "PUBLISHED",
                        "distribution": {"feedDistribution": "MAIN_FEED"}, "content": {"article": {"source": e.link, "title": e.title}}})
        http.post("https://api.twitter.com/2/tweets", json={"text": f"{posts['x']} {e.link}"},
                  headers={"Authorization": f"Bearer {credentials.connection('x', 'work')}"})
        shared.append(e.link)
    state.set("shared", shared[-300:])
    return {"shared": len(new)}

FAQ

Common questions

Will it share my old articles?

No. On the first run it records the articles already in your feed and only shares new ones.

Can it share from the company page?

Yes. Connect LinkedIn with page admin access and name the page in the prompt.

Can authors be tagged?

Yes, if you list each author's LinkedIn and X handles in the prompt.

What permissions does it need?

LinkedIn w_member_social; X tweet.write. 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.

The moment it happensAI