Tavily + Gmail: AI news briefings, ready to forward
You open ten tabs, skim twenty headlines, copy a few links, then still worry you missed the one story your team will ask about. It’s noisy. And it eats the first hour of your day.
This Tavily Gmail digest automation hits marketing leads and founders first, honestly. But client-facing consultants feel it too, because staying “current” becomes a daily chore instead of a quick habit.
This workflow pulls the top AI news, summarizes it with an AI agent, and sends a clean email you can forward in seconds. You’ll see how it works, what you need, and what to tweak so it matches your topics and voice.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Tavily + Gmail: AI news briefings, ready to forward
flowchart LR
subgraph sg0["Schedule Flow"]
direction LR
n0@{ icon: "mdi:play-circle", form: "rounded", label: "Schedule Trigger", pos: "b", h: 48 }
n1@{ icon: "mdi:robot", form: "rounded", label: "AI News Agent", pos: "b", h: 48 }
n2@{ icon: "mdi:brain", form: "rounded", label: "OpenRouter Chat Model", pos: "b", h: 48 }
n3@{ icon: "mdi:wrench", form: "rounded", label: "Tavily News Search", pos: "b", h: 48 }
n4@{ icon: "mdi:robot", form: "rounded", label: "News Output Parser", 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/code.svg' width='40' height='40' /></div><br/>Prepare News Query"]
n6@{ icon: "mdi:message-outline", form: "rounded", label: "Send a message", 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/code.svg' width='40' height='40' /></div><br/>Format for Gmail"]
n1 --> n7
n7 --> n6
n0 --> n5
n4 -.-> n1
n5 --> n1
n3 -.-> n1
n2 -.-> n1
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 n0 trigger
class n1,n4 ai
class n2 aiModel
class n3 ai
class n5,n7 code
classDef customIcon fill:none,stroke:none
class n5,n7 customIcon
The Problem: Daily news tracking turns into tab overload
Keeping up with AI news sounds simple until you do it every day. You bounce between social feeds, newsletters, and search, trying to separate real moves (product launches, regulation updates, funding news) from recycled takes. Then comes the messy part: turning what you found into something a team can actually read. Links go missing, context gets lost, and your “quick share” becomes a mini writing assignment before you’ve even had coffee.
It adds up fast. Here’s where it usually breaks down in the real world.
- Someone has to search, evaluate sources, and decide what’s actually worth sharing.
- Even when you find good stories, summarizing them cleanly takes about an hour across the week.
- Manual formatting is surprisingly painful, especially when you want a consistent “digest” style.
- If the process depends on one person, the briefing stops the moment they get busy.
The Solution: A daily AI briefing email generated and sent automatically
This n8n workflow runs on a schedule you control, builds a fresh search query for the day, and hands it to an AI agent. That agent uses Tavily’s news search to pull up-to-date AI stories from the web, then uses an OpenRouter-connected chat model to pick the most important items and summarize each one. The output is forced into a strict JSON structure (title plus an array of stories), so it stays consistent even when the news is chaotic. Finally, a code step converts that structured summary into a polished HTML email, and Gmail sends it to your inbox (or whoever needs it).
The workflow starts with a daily scheduled trigger. Then it assembles a query, gathers and summarizes the top stories, and formats everything into an email that looks like you wrote it on purpose. Gmail delivers the digest so you can forward it immediately, or route it elsewhere later.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you want to share 5 solid AI stories each weekday with your team. Manually, that’s usually about 10 minutes to find candidates, another 20 minutes to read enough to summarize, plus 10 minutes to format and send, so around 40 minutes a day. With this workflow, you spend maybe 5 minutes scanning the finished Gmail digest and forwarding it with one line of context. The “work” happens in the background while you do something else.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Tavily for real-time AI news search.
- OpenRouter to run the LLM that summarizes.
- Gmail (Google account) to send the email via OAuth2.
- Tavily + OpenRouter API keys (get them from your Tavily and OpenRouter dashboards).
Skill level: Intermediate. You’ll connect credentials, edit a prompt, and adjust a couple of code-based text fields.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
A daily schedule kicks things off. The workflow runs at the time you choose, so the briefing shows up before standup, before your first client call, or whenever you actually read email.
A query is assembled for today’s news. A code step builds a search prompt that targets the categories you care about, so you’re not relying on a static keyword that goes stale.
An AI agent searches and writes the digest. The agent uses Tavily to fetch relevant articles, then an OpenRouter chat model evaluates what matters and produces structured summaries (title plus story list) you can trust and reuse.
A formatted Gmail email gets sent. Another code step turns the structured output into a readable HTML newsletter-style email, and Gmail delivers it to your chosen recipient(s).
You can easily modify the topics and language to match your market, then keep the same delivery mechanism. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Scheduled Trigger
Set the workflow to run on a daily schedule so it can prepare the news digest automatically.
- Add the Scheduled Run Initiator node as your trigger.
- Set the Rule to run every 24 hours by configuring Interval with Field set to
hoursand Hours Interval set to24. - Confirm the workflow Timezone is correct in settings (currently
America/New_York).
Step 2: Connect the News Query Builder
Generate the daily query that the AI agent will use to fetch and summarize the news.
- Connect Scheduled Run Initiator to Assemble News Query.
- In Assemble News Query, keep the Code value as provided to build the query and date string.
- Verify the output includes
queryanddatefields for downstream nodes.
Step 3: Set Up AI Briefing and Tools
Configure the AI agent, language model, tool, and output parser so it can fetch news, summarize it, and return structured JSON.
- Connect Assemble News Query to AI Briefing Agent.
- In AI Briefing Agent, set Text to
={{ $json.query }}and keep Prompt Type set todefine. - Ensure the system message defines the JSON schema and Japanese output requirements as shown in the node configuration.
- Connect OpenRouter LLM Gateway to AI Briefing Agent as the language model.
Credential Required: Connect youropenRouterApicredentials. - Connect Tavily News Fetcher to AI Briefing Agent as the tool and keep URL set to
https://api.tavily.com/searchwith MethodPOST. - In Tavily News Fetcher, replace the API key placeholder in JSON Body with your actual key:
"api_key": "[CONFIGURE_YOUR_API_KEY]". - Connect Structured Output Parser to AI Briefing Agent as the output parser and keep Schema Type set to
manualwith the provided JSON schema.
Step 4: Configure Email Formatting and Delivery
Transform the AI output into an HTML email and send it via Gmail.
- Connect AI Briefing Agent to Compose Email HTML.
- In Compose Email HTML, keep the HTML template code as provided to render
subjectandhtmlBodyoutputs. - Connect Compose Email HTML to Dispatch Gmail Email.
- In Dispatch Gmail Email, set Send To to your recipient address (replace
[YOUR_EMAIL]). - Set Message to
={{ $json.htmlBody }}and Subject to={{ $json.subject }}. - Credential Required: Connect your
gmailOAuth2credentials.
false if you want a clean HTML email without n8n attribution.Step 5: Test and Activate Your Workflow
Run a manual test to validate AI output, HTML formatting, and email delivery before enabling the schedule.
- Click Execute Workflow to run the trigger manually and follow the path Scheduled Run Initiator → Assemble News Query → AI Briefing Agent → Compose Email HTML → Dispatch Gmail Email.
- Confirm the AI Briefing Agent output contains structured JSON with
title,summary, andstories. - Verify the email arrives with formatted HTML and the correct subject line.
- Toggle the workflow to Active to enable daily automated runs.
Common Gotchas
- Gmail OAuth credentials can expire or be missing permissions. If sending fails, check the Gmail node’s connected account and Google OAuth consent settings first.
- If you’re using external search and an AI agent, response times vary day to day. If downstream nodes occasionally receive empty content, increase any wait/retry behavior and reduce how many stories you request at once.
- The AI News Agent prompt is set up for Japanese output in this template. If you want English (or a specific brand tone), change the system prompt early or you’ll be rewriting the digest every morning.
Frequently Asked Questions
About 30 minutes once your API keys are ready.
No coding required for the core flow. You’ll mostly paste credentials and tweak the agent prompt (the code nodes are already written).
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 Tavily and OpenRouter usage (both have free tiers, then small per-request costs).
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’ll do it in two places. Update the language and tone in the “AI Briefing Agent” system prompt, then adjust the categories/keywords in the “Assemble News Query” code node so the agent searches what you actually care about. Common tweaks include “competitor launches,” “AI policy and regulation,” and “funding and acquisitions.” You can also swap the final Gmail send for Slack or Telegram later without changing the core research and summarization.
Usually it’s OAuth. Reconnect the Gmail credential in n8n, confirm the Google account still has Gmail enabled, and double-check the Gmail node is using the right credential. If it fails only sometimes, you may also be hitting Google sending limits or trying to send to too many recipients at once.
Practically, most teams keep it to about 5–15 stories per email so it stays readable.
It depends on how “agentic” you want the briefing to be. Zapier and Make are fine for moving data between apps, but this workflow leans on an AI agent that searches, evaluates, and outputs structured JSON, which is where n8n tends to feel more flexible. You also get the self-hosting option, which matters if you run this daily across multiple brands or clients. If you only need a simple “RSS in, email out” digest, Zapier can be quicker. If you’re unsure, Talk to an automation expert and you’ll get a straight recommendation.
Once this is running, the briefing shows up even on your busiest weeks. One email. Forward it, archive it, move on.
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.
