Google Sheets + LinkedIn: draft posts from trending news
Keeping up with LinkedIn content sounds simple until you’re staring at a blank cursor, juggling tabs, and trying to turn “a thing you read” into a decent point of view. The worst part is how repeatable it is, which is exactly why Sheets LinkedIn drafts automation works so well here.
If you’re a marketing manager, you feel the calendar pressure. A founder doing their own thought leadership feels it too. Same with a content consultant who has to ship ideas every week without burning out.
This workflow pulls topics from Google Sheets, finds relevant news, scrapes and cleans the articles, then writes first-person LinkedIn-style drafts with GPT-4o and saves them back to your sheet for review.
How This Automation Works
Here’s the complete workflow you’ll be setting up:
n8n Workflow Template: Google Sheets + LinkedIn: draft posts from trending news
flowchart LR
subgraph sg0["Run on Schedule (Daily) Flow"]
direction LR
n0@{ icon: "mdi:cog", form: "rounded", label: "No Operation, do nothing", pos: "b", h: 48 }
n1@{ icon: "mdi:play-circle", form: "rounded", label: "Run on Schedule (Daily)", pos: "b", h: 48 }
n2@{ icon: "mdi:database", form: "rounded", label: "Fetch Topics with Empty Comm..", pos: "b", h: 48 }
n3@{ icon: "mdi:swap-vertical", form: "rounded", label: "Loop Through Each Topic", pos: "b", h: 48 }
n4@{ icon: "mdi:cog", form: "rounded", label: "Wait Before News Search", pos: "b", h: 48 }
n5["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Search News with Dumpling AI"]
n6@{ icon: "mdi:swap-vertical", form: "rounded", label: "Split Returned News Articles", pos: "b", h: 48 }
n7["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Scrape Article Content with .."]
n8@{ icon: "mdi:cog", form: "rounded", label: "Aggregate Scraped Article Co..", pos: "b", h: 48 }
n9["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/code.svg' width='40' height='40' /></div><br/>Clean Article Content"]
n10@{ icon: "mdi:robot", form: "rounded", label: "Generate LinkedIn Commentary..", pos: "b", h: 48 }
n11@{ icon: "mdi:database", form: "rounded", label: "Append Commentary Back to Sh..", pos: "b", h: 48 }
n9 --> n10
n3 --> n0
n3 --> n4
n1 --> n2
n4 --> n5
n5 --> n6
n6 --> n7
n11 --> n3
n8 --> n9
n2 --> n3
n10 --> n11
n7 --> n8
end
%% Styling
classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
classDef disabled stroke-dasharray: 5 5,opacity: 0.5
class n1 trigger
class n10 ai
class n2,n11 database
class n5,n7 api
class n9 code
classDef customIcon fill:none,stroke:none
class n5,n7,n9 customIcon
Why This Matters: Consistent LinkedIn posts without the scramble
The “I should post on LinkedIn” goal usually dies in the same place: the gap between reading something interesting and turning it into a post worth publishing. You open an article, skim it, then bounce to another tab to find context. Then you try to summarize it, but it comes out flat or too “newsroom,” not like you. Meanwhile, your calendar still expects two or three posts this week, and you’re spending about 45 minutes to get one draft you don’t even like. Honestly, that’s why consistency feels impossible.
It adds up fast. Here’s where it breaks down in real life.
- You keep redoing the same research steps: search, open results, skim, copy key lines, repeat.
- Manual copy-paste from articles drags junk along (links, ads, “related stories”), so the summary gets messy.
- When the draft doesn’t sound like you, you end up rewriting from scratch instead of polishing.
- No single place to manage “topics → drafts,” so your pipeline is always half-built and hard to scale.
What You’ll Build: A daily news-to-draft LinkedIn pipeline in Sheets
This automation starts on a daily schedule, checks your Google Sheet for topics that still don’t have a draft, and works through them one by one. For each topic, it calls Dumpling AI’s News Search endpoint to find relevant articles, then scrapes the full text from the best matches. After that, the workflow aggregates the scraped content, cleans it to remove clutter, and sends a readable version to GPT-4o with a prompt designed to produce first-person LinkedIn commentary. Finally, it writes the finished draft back into the same Google Sheet, right next to the topic you started with. You wake up to drafts you can actually edit and publish, not a pile of “someday” ideas.
The workflow begins with a schedule trigger and a “retrieve unfilled topics” query in Google Sheets. Dumpling AI handles both discovery (search) and extraction (scrape), which means you’re not managing a dozen sources manually. GPT-4o then turns cleaned article text into a LinkedIn-ready draft and stores it back in Sheets for review.
What You’re Building
| What Gets Automated | What You’ll Achieve |
|---|---|
|
|
Expected Results
Say you keep 10 topics in your Google Sheet and you want 5 LinkedIn drafts per week. Manually, a single “topic → search → read → summarize → write” loop can easily take about 45 minutes, so you’re looking at roughly 4 hours weekly just to get first drafts. With this workflow, the daily run does the research and drafting while you’re offline; you spend about 10 minutes per draft reviewing and adjusting the voice. That’s a few hours back every week, without lowering quality.
Before You Start
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Google Sheets for topic intake and draft storage.
- Dumpling AI to search news and scrape article text.
- OpenAI API access (GPT-4o) (get it from your OpenAI dashboard’s API keys page).
Skill level: Intermediate. You’ll connect accounts, add API keys, and lightly adjust prompts and sheet columns.
Want someone to build this for you? Talk to an automation expert (free 15-minute consultation).
Step by Step
A daily schedule kicks things off. n8n runs this once per day, so you don’t need to remember to “go generate drafts.” It’s the difference between a habit you hope to keep and a system that runs regardless.
Google Sheets supplies the backlog. The workflow reads your topic rows and intentionally targets only the ones without generated commentary, so it won’t recreate drafts you already reviewed.
Dumpling AI finds and extracts the raw material. First it searches the news for your topic, then it scrapes article text from the results. A short wait is included to avoid hitting rate limits when several topics process back-to-back.
GPT-4o writes the draft and Sheets stores it. After aggregation and cleaning, the prompt produces a first-person commentary draft suitable for LinkedIn, then the automation writes it back next to the original topic so you can edit, approve, and publish.
You can easily modify the Google Sheet columns to match your existing content tracker based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Schedule Trigger
This workflow starts on a daily schedule and immediately pulls topics from Google Sheets.
- Add the Daily Schedule Trigger node and set your preferred schedule interval in Rule.
- Connect Daily Schedule Trigger to Retrieve Unfilled Topics.
Step 2: Connect Google Sheets
Pull topics that still need commentary and prepare them for iteration.
- In Retrieve Unfilled Topics, set Document to
News articlesand Sheet toSheet1. - Enable Options → Return First Match and set a filter on lookupColumn to
generated commentary. - Credential Required: Connect your googleSheetsOAuth2Api credentials in Retrieve Unfilled Topics.
- Connect Retrieve Unfilled Topics to Iterate Topic Items.
⚠️ Common Pitfall: If your sheet headers don’t include Topic and generated commentary, the filters and mapping will not work correctly.
Step 3: Set Up Topic Iteration and News Lookup
Each topic is processed in batches, then the workflow searches for related news and splits the results.
- Use Iterate Topic Items to batch process the topics pulled from Google Sheets.
- Note that Iterate Topic Items outputs to both Idle Pass-Through and Delay Before Search in parallel.
- Connect Delay Before Search to Dumpling News Lookup to pace external API calls.
- In Dumpling News Lookup, set URL to
https://app.dumplingai.com/api/v1/search-newsand Method toPOST. - Set JSON Body to
={ "query": "{{ $json.Topic }}", "country": "US", "page": 3, "language": "en" }. - Credential Required: Connect your httpHeaderAuth credentials in Dumpling News Lookup.
- In Split News Results, set Field to Split Out to
news.
⚠️ Common Pitfall: If $json.Topic is empty, the news search will return irrelevant or empty results—ensure your sheet rows contain valid topics.
Step 4: Scrape, Aggregate, and Sanitize Article Content
This section extracts article content, aggregates it, and cleans it before sending to AI.
- In Scrape Article Text, set URL to
https://app.dumplingai.com/api/v1/scrapeand Method toPOST. - Set JSON Body to
={ "url": "{{ $json.link}}" }. - Credential Required: Connect your httpHeaderAuth credentials in Scrape Article Text.
- In Aggregate Article Text, aggregate the field
contentusing Fields to Aggregate. - Keep the default cleaning logic in Sanitize Article Text to produce
cleaned_contentfor the AI prompt.
Step 5: Set Up AI Commentary Generation
Generate a LinkedIn-ready commentary from the cleaned article text.
- In Create LinkedIn Commentary, set Model to
chatgpt-4o-latest. - Use the provided prompt content with expressions like
{{ $('Retrieve Unfilled Topics').item.json.Topic }}and{{ $json.cleaned_content }}. - Credential Required: Connect your openAiApi credentials in Create LinkedIn Commentary.
If your AI output is too long, tighten the character limit in the prompt within Create LinkedIn Commentary.
Step 6: Configure Output to Google Sheets
Write the generated commentary back to the original sheet.
- In Update Sheet Commentary, set Operation to
appendOrUpdate. - Map columns using Columns → Mapping Mode set to
defineBelow. - Set Topic to
={{ $('Retrieve Unfilled Topics').item.json.Topic }}and generated commentary to={{ $json.message.content }}. - Set Matching Columns to
Topicto update the correct row. - Credential Required: Connect your googleSheetsOAuth2Api credentials in Update Sheet Commentary.
- Confirm Update Sheet Commentary connects back to Iterate Topic Items to process the next topic.
⚠️ Common Pitfall: If your sheet lacks a unique Topic column, the update may overwrite unintended rows.
Step 7: Test and Activate Your Workflow
Validate the workflow with manual tests, then enable automated runs.
- Click Execute Workflow and confirm Dumpling News Lookup and Scrape Article Text return content.
- Verify Create LinkedIn Commentary outputs a response and Update Sheet Commentary writes to the correct row.
- Check that Iterate Topic Items loops through all unfilled topics without errors.
- Toggle the workflow to Active to run it on the daily schedule.
Troubleshooting Tips
- Google Sheets credentials can expire or need specific permissions. If things break, check the n8n credential settings and confirm the connected Google account still has edit access to the sheet.
- If you’re using Wait nodes or external scraping, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses from the Dumpling AI endpoints.
- Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever, especially in the GPT-4o “Create LinkedIn Commentary” step.
Quick Answers
About 30 minutes if your APIs are ready.
No. You’ll connect accounts and paste in API keys. The included code step is already built; you might only tweak it if your scraped text needs different cleanup.
Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in OpenAI API costs and Dumpling AI API usage (usually cents per run, depending on how many articles you scrape).
Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.
Yes, pretty easily. You can change the Google Sheets “Retrieve Unfilled Topics” step to pull different columns (like audience, product line, or region), then adjust the GPT-4o prompt in “Create LinkedIn Commentary” to match that context. Many teams also swap the daily schedule for a Telegram Trigger so they can drop a topic in chat and generate a draft on demand. If you want longer posts or a newsletter tone, that’s mostly prompt work plus an extra “write back” column.
Most of the time it’s an invalid or expired Dumpling AI API key, or the endpoint permissions don’t include /search-news and /scrape. Also check the HTTP Request node headers and confirm you’re sending the key exactly as Dumpling expects. If you’re running many topics at once, rate limiting can show up as empty responses; the Wait node is there for a reason, so increase it a bit.
On n8n Cloud, it depends on your plan’s monthly executions, and on self-hosting it mainly depends on your server. Practically, most teams run 5–30 topics per day without issues, as long as the Wait node keeps you under API limits.
Often, yes. This workflow isn’t just “move data from A to B”; it loops over topics, branches, waits for rate limits, aggregates scraped text, and runs a cleanup step before writing to Sheets. n8n handles that kind of logic cleanly, and self-hosting can keep costs predictable when volume grows. Zapier or Make can still work if you only process one topic at a time and don’t need much text cleanup, but the moment you want batching and scraping control, they get fiddly. If you’re torn, Talk to an automation expert and you’ll get a straight recommendation.
You set the topics once, and the workflow keeps your draft queue full. Then you just add judgment, voice, and timing.
Need Help Setting This Up?
Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.
