Perplexity to Gmail, a clean daily AI news digest
Your “quick AI news check” turns into 12 open tabs, three half-read threads, and a vague feeling you missed the one update that actually mattered. Then you do it again tomorrow. Same mess.
This AI news digest automation hits marketing leads and agency owners first, honestly. But founders and ops folks feel it too, because staying current is now part of everyone’s job. You get a clean, readable summary in Gmail every morning at 9 AM, without the tab hopping.
Below you’ll see how the workflow pulls headlines from Perplexity, formats them with OpenAI, and sends a simple daily email you can scan in under two minutes.
How This Automation Works
See how this solves the problem:
n8n Workflow Template: Perplexity to Gmail, a clean daily AI news digest
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:message-outline", form: "rounded", label: "Send a message", pos: "b", h: 48 }
n2@{ icon: "mdi:robot", form: "rounded", label: "Formatter AI Agent", pos: "b", h: 48 }
n3@{ icon: "mdi:brain", form: "rounded", label: "OpenAI Chat Model", pos: "b", h: 48 }
n4@{ icon: "mdi:memory", form: "rounded", label: "Simple Memory", 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/perplexity.dark.svg' width='40' height='40' /></div><br/>Research Agent"]
n4 -.-> n2
n5 --> n2
n0 --> n5
n3 -.-> n2
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 n2 ai
class n3 aiModel
class n4 ai
classDef customIcon fill:none,stroke:none
class n5 customIcon
The Challenge: Staying on top of AI news without losing your morning
Keeping up with AI news is important, but the way most teams do it is rough. You search, skim, open links, and try to remember what you saw yesterday so you can spot what’s new today. Some days you go deep and burn an hour. Other days you miss everything because you’re busy, and now you’re behind. And when you do find good updates, you still have to paste them into Slack, drop them into a doc, or forward them to someone who asked, “Anything new in AI this week?”
It adds up fast. Here’s where it breaks down in real life.
- You spend about 30 minutes bouncing between sources, and the “headline value” is usually 5 minutes of that.
- Good links get lost in browser chaos, so you can’t easily reference them later when you need sources.
- Summaries end up inconsistent because each person paraphrases differently (and nobody has time to polish).
- Sharing becomes another chore, so updates die in DMs instead of becoming a repeatable market research habit.
The Fix: A daily Perplexity-to-Gmail digest formatted by OpenAI
This workflow runs once per day and delivers a clean email digest of AI headlines from the last 24 hours. At 9 AM, n8n triggers a Perplexity AI Agent that searches for recent AI-related news and returns a structured set of items: headline, one-sentence summary, source, and the full URL. That raw feed is useful, but it still reads like research output. So the workflow passes it into a formatting agent powered by an OpenAI chat model (GPT-4.1-mini), which rewrites the bundle into something you’d actually want to read in an inbox. Finally, Gmail sends the finished digest to you or your team, so the update is waiting where you already work.
The workflow starts on a daily schedule. Perplexity gathers “what’s new” across the last day, then OpenAI turns it into a crisp email layout. Gmail delivers it automatically, which means no one has to remember to do the check.
What Changes: Before vs. After
| What This Eliminates | Impact You’ll See |
|---|---|
|
|
Real-World Impact
Let’s say you do a daily AI check and share highlights with two teammates. Before: about 30 minutes to search, open links, and pick the top stories, then another 10 minutes to rewrite and forward it. Call it roughly 40 minutes per day. With this workflow: you spend maybe 2 minutes scanning the email, and 2 more minutes forwarding or pasting a standout link if you want. That’s about 30 minutes back each day, without relying on willpower.
Requirements
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Perplexity AI API to fetch AI headlines from the last 24 hours
- OpenAI API to format the digest for readability
- Gmail account (OAuth2 credentials from Google Cloud Console)
Skill level: Intermediate. You’ll connect APIs, authorize Gmail, and tweak a prompt, but you won’t be writing “real code.”
Need help implementing this? Talk to an automation expert (free 15-minute consultation).
The Workflow Flow
A daily 9 AM schedule kicks it off. The workflow runs automatically every 24 hours, so the digest arrives at a predictable time and becomes part of your morning routine.
Perplexity gathers the raw “what happened” list. The AI News Researcher agent searches for AI-related headlines published in the last 24 hours and returns each item with a headline, short summary, source, and URL.
OpenAI turns research into a clean digest. The News Formatting Agent uses a GPT model to rewrite and structure the results like an email you would actually read. If you enable the optional memory buffer, you can keep the style consistent over time (for example: always include “why it matters” for product updates).
Gmail sends the final email. The Dispatch Email Digest node delivers it to your inbox or a shared address, so the update is centralized and easy to forward.
You can easily modify the topic from “AI news” to something narrower (like “AI ads”, “LLM security”, or “MarTech AI”) based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Scheduled Trigger
Set the schedule that starts the daily AI news research cycle.
- Add the Scheduled Run Trigger node.
- Set the schedule rule to run daily at
9for triggerAtHour.
Step 2: Connect Perplexity for AI News Research
Pull the latest AI headlines from Perplexity with a focused prompt.
- Add the AI News Researcher node and connect it to Scheduled Run Trigger.
- Credential Required: Connect your perplexityApi credentials.
- Set Model to
sonar-pro. - Ensure the system message includes the request for full headlines, summaries, URLs, dates, and sources, and the user prompt asks for the latest AI development headlines from the past 24 hours.
Step 3: Set Up the AI Formatting Pipeline
Format the research output into a clean, readable email digest.
- Add the News Formatting Agent node and connect it after AI News Researcher.
- Set Text to
={{ $json.choices[0].message.content }}. - Set the system message to instruct formatting for an email-friendly layout.
- Add OpenAI Chat Engine as the language model for News Formatting Agent. Credential Required: Connect your openAiApi credentials.
- Add Conversation Memory Buffer as the memory for News Formatting Agent and set Session Key to
={{ $('AI News Researcher').item.json.id }}with Session ID Type set tocustomKey.
Step 4: Configure the Email Delivery
Send the formatted digest via Gmail.
- Add the Dispatch Email Digest node and connect it to News Formatting Agent.
- Credential Required: Connect your gmailOAuth2 credentials.
- Set Message to
={{ $json.output }}. - Set Subject to
AI News Update in the last 24 hours. - Set Email Type to
text. - Fill in Send To with the recipient email address.
Step 5: Test and Activate Your Workflow
Validate the flow from research to email delivery, then enable the schedule.
- Click Execute Workflow to run the flow manually from Scheduled Run Trigger.
- Verify that AI News Researcher returns recent headlines and News Formatting Agent outputs a readable digest.
- Confirm Dispatch Email Digest sends the email with the formatted content.
- Toggle the workflow to Active so the schedule runs daily.
Watch Out For
- Gmail OAuth credentials can expire or get blocked by workspace policies. If emails stop sending, check the credential status in n8n first, then confirm the Google Cloud OAuth consent screen is still valid.
- If you add Wait nodes or expand this to post into Slack and Google Docs, 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.
Common Questions
About 30 minutes if your API keys and Gmail login are ready.
Yes. No coding required, but someone will need to connect Perplexity, OpenAI, and Gmail credentials in n8n.
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 Perplexity API usage and OpenAI API usage (often a few dollars a month for a daily digest, depending on output size).
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.
Change the query inside the Perplexity “AI News Researcher” agent, then adjust the prompt in the “News Formatting Agent” to match your format. Common tweaks include narrowing the topic (for example, “AI policy” only), adding a short “why it matters” line per headline, or sending the same digest to Slack instead of Gmail. If you want continuity, keep the Conversation Memory Buffer enabled so the agent can maintain a consistent voice across days.
Usually it’s expired or revoked OAuth access. Reconnect the Gmail credential in n8n, then confirm the Google account still has permission to send mail via the configured OAuth app. If you’re on Google Workspace, an admin policy can also block third-party OAuth apps, so it’s worth checking the admin console if reconnecting doesn’t stick.
For a once-daily run, capacity is basically a non-issue.
Often, yes, if you care about formatting quality and control. This workflow relies on an AI agent plus a chat model, and n8n handles that kind of multi-step logic cleanly without turning into a fragile chain of mini-zaps. Self-hosting is another practical win because you’re not paying per tiny step when you expand it. That said, Zapier or Make can be quicker for a basic “send myself an email” setup if you’re not using Perplexity or custom prompts. Talk to an automation expert if you’re not sure which fits.
Once this is running, you stop spending your best morning minutes hunting for updates. The workflow sends the digest, you skim it, and you 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.
