SerpApi + Slack, a clean Google News digest
Keeping up with Google News sounds simple until you’re on your third tab, chasing the same story across five sources, and still not sure what matters.
This is the kind of Google News digest automation that saves analysts a headache. It also helps comms leads who need a clean brief fast, and founders who just want the signal without the scrolling.
You’ll set up an n8n workflow that pulls fresh headlines via SerpApi, uses OpenAI to sort and summarize them, then posts a tidy, categorized digest into Slack.
How This Automation Works
Here’s the complete workflow you’ll be setting up:
n8n Workflow Template: SerpApi + Slack, a clean Google News digest
flowchart LR
subgraph sg0["Sample Chatbot Flow"]
direction LR
n0@{ icon: "mdi:web", form: "rounded", label: "Google_news search", pos: "b", h: 48 }
n1@{ icon: "mdi:brain", form: "rounded", label: "OpenAI Chat Model6", pos: "b", h: 48 }
n2@{ icon: "mdi:memory", form: "rounded", label: "Simple Memory2", pos: "b", h: 48 }
n3@{ icon: "mdi:swap-vertical", form: "rounded", label: "Split Out Links", pos: "b", h: 48 }
n4@{ icon: "mdi:cog", form: "rounded", label: "Combine into one field", pos: "b", h: 48 }
n5@{ icon: "mdi:robot", form: "rounded", label: "Chat with Google News", pos: "b", h: 48 }
n6@{ icon: "mdi:play-circle", form: "rounded", label: "Sample Chatbot", pos: "b", h: 48 }
n6 --> n0
n2 -.-> n5
n3 --> n4
n0 --> n3
n1 -.-> n5
n4 --> n5
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 n6 trigger
class n5 ai
class n1 aiModel
class n2 ai
class n0 api
Why This Matters: News Monitoring Turns Into Busywork
Manual news monitoring has a sneaky cost. You start with “just a quick scan,” then you’re comparing headlines, opening duplicates, and trying to remember which link you already sent to the team. The worst part is the mental load: you’re not only reading, you’re constantly deciding what’s relevant, what’s noise, and how to summarize it in a way other people will actually read. After a week, you’ve spent hours and still feel behind. Honestly, it’s exhausting.
It adds up fast. Here’s where it usually breaks down.
- Searching Google News manually often produces a pile of near-duplicate headlines, so you waste time opening the same story in different wording.
- Even when you find good articles, turning them into a Slack-ready brief is another round of copy, paste, edit, and reformat.
- Important stories get missed because the scan depends on someone remembering to do it, usually when they’re busiest.
- Different people summarize differently, which means inconsistent briefs and more back-and-forth in the channel.
What You’ll Build: A Categorized News Digest Posted to Slack
This workflow turns a simple search prompt into a clear daily-style brief. It starts when someone enters a query (for example, “EV market 2025”) through an n8n chat trigger. n8n sends that query to SerpApi’s Google News search, pulls back the latest headlines, then separates each result into individual items so they can be processed cleanly. Next, it aggregates the titles and links into a structured list. Finally, an OpenAI agent summarizes what’s going on, groups stories into meaningful categories, and recommends the strongest article per category. You end with a digest people can skim in seconds, with clickable links when they want detail.
The workflow begins with an on-demand query, so you can run it whenever something breaks or a client asks for an update. SerpApi fetches current Google News results, then OpenAI turns raw headlines into a tidy set of categories and takeaways. From there, you can share it directly in Slack (and extend it later to Sheets or email if you want).
What You’re Building
| What Gets Automated | What You’ll Achieve |
|---|---|
|
|
Expected Results
Say you share a morning update for three topics (your industry, a key competitor, and a customer segment). Manually, a “quick” Google News scan can be about 20 minutes per topic, plus another 10 minutes to write a Slack-friendly summary, so you’re near 90 minutes. With this workflow, you type three queries over a few minutes, wait for processing, and post the digest. You usually get about an hour back, and the quality is more consistent.
Before You Start
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- SerpApi for Google News search results
- Slack to share the digest with your team
- SerpApi API key (get it from the SerpApi dashboard)
Skill level: Beginner. You’ll connect credentials, paste API keys, and tweak one prompt.
Want someone to build this for you? Talk to an automation expert (free 15-minute consultation).
Step by Step
A chat message triggers the run. You enter a query like “renewable energy today” in the workflow’s chat interface, which gives you on-demand control instead of a fire-and-forget batch job.
SerpApi pulls Google News results. n8n sends your query to the Google News lookup and receives a list of headlines, sources, and links in a structured response.
The workflow cleans and bundles the items. It splits the results into individual link items, then aggregates titles and URLs into a single list that’s easy for an AI model to reason about. This is the “make it readable” step.
OpenAI produces a categorized digest. The AI agent summarizes the news, groups it into categories, and selects the most relevant article per category. That output is what you paste or send into Slack, and it’s also the part you can customize for sentiment, keyword extraction, or executive-style bullets.
You can easily modify the categories to match your industry (or your stakeholders) based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Chat Trigger
This workflow starts when a user submits a chat prompt, which is captured by the trigger and passed into the news search.
- Add the Chat Intake Trigger node as the trigger for the workflow.
- Keep Options empty unless you need custom chat settings.
- Confirm the trigger is connected to Google News Lookup as shown in the execution flow.
Step 2: Connect Google News Search
Use SerpAPI to query Google News based on the incoming chat input.
- Add the Google News Lookup node and connect it after Chat Intake Trigger.
- Set Operation to
google_news. - Set Query (q) to
={{ $json.chatInput }}. - Set GL to
usin Additional Fields. - Credential Required: Connect your serpApi credentials.
Step 3: Split and Aggregate News Results
Split the news results into individual items and then aggregate titles and links for summary creation.
- Add Separate Link Items after Google News Lookup.
- Set Field to Split Out to
news_results. - Add Aggregate Titles & Links after Separate Link Items.
- Enable Merge Lists in Options.
- Under Fields to Aggregate, add title and link as fields.
Step 4: Configure the AI Summary Agent and Memory
Use the agent to summarize and categorize the news results, with memory to keep context per session.
- Add the OpenAI Chat Engine node and select the model
gpt-5-nano. - Credential Required: Connect your openAiApi credentials.
- Add Session Memory Buffer and set Session ID Type to
customKey. - Set Session Key to
={{ $('Chat Intake Trigger').item.json.sessionId }}. - Add News Summary Agent and set Text to
=news titles: {{ $json.title }} Links: {{ $json.link }} question: {{ $('Chat Intake Trigger').item.json.chatInput }}. - Set Prompt Type to
defineand System Message to=Take in the list of titles and the original search term. Group into 5 different categories, and send back 1 url's and title for each category they might be interested in.. - Connect OpenAI Chat Engine to News Summary Agent as the ai_languageModel and Session Memory Buffer to News Summary Agent as the ai_memory.
Step 5: Test and Activate Your Workflow
Validate that the chat trigger returns categorized news summaries and then enable the workflow for production use.
- Click Execute Workflow and send a chat input to Chat Intake Trigger.
- Verify that Google News Lookup returns items and Separate Link Items splits
news_results. - Confirm Aggregate Titles & Links outputs merged title and link arrays.
- Check News Summary Agent for a response grouped into five categories with a title and URL each.
- Once successful, toggle the workflow to Active to enable live chat handling.
Troubleshooting Tips
- SerpApi credentials can expire or be pasted incorrectly. If things break, check the SerpApi credential in n8n and confirm the API key matches your SerpApi dashboard.
- If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.
Quick Answers
About 30 minutes once you have your API keys.
No. You’ll connect SerpApi and OpenAI credentials, then tweak the prompt to match what you want in the digest.
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 usage costs, which are usually small for short summaries.
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, and you should. Most teams adjust the “News Summary Agent” instructions to change the number of categories (3 vs 10), add sentiment, or force a strict format like “Category: headline – link.” You can also tweak the “Google News Lookup” settings to focus on a region or language (for example, setting geography and language filters). If you want multi-topic briefings, duplicate the lookup and run several queries in one execution, then aggregate everything before the agent.
Usually it’s an invalid or expired API key. Copy a fresh key from your SerpApi dashboard and update the SerpApi credential in n8n, then reselect it in the “Google News Lookup” node. If it still fails, check your SerpApi plan limits and look at the n8n execution log to see the raw HTTP error from SerpApi.
For one query at a time, it can comfortably handle daily or hourly briefs; limits mostly come from your n8n plan, your server (if self-hosted), and SerpApi/OpenAI rate limits.
It depends on what you mean by “better.” If you want a real digest (categorize, pick best link, keep formatting consistent), n8n is usually the smoother option because you can shape the data, aggregate items, and run an AI agent without fighting platform limitations. It also gives you a self-hosting path, which matters if you run this often and don’t want to pay per task. Zapier and Make are fine for simpler, linear automations, like “new row in a sheet → send Slack message.” If you’re not sure, Talk to an automation expert and we’ll sanity-check the best fit.
Once this is set up, your team gets a clearer brief with less noise. And you get your mornings back.
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.
