January 21, 2026

Perplexity AI to Google Sheets, post-ready ideas

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

You open your notes app to “post something about AI,” then lose 45 minutes chasing links, skimming threads, and trying to turn half-baked headlines into a coherent take. By the time you have a hook, you’ve burned the good part of your morning. Again.

Founders feel this when content is “important” but never urgent. A marketing lead gets squeezed between campaigns. And an agency strategist ends up doing research three times for three clients. This Perplexity Sheets automation gives you a daily stack of scripts, captions, and text overlays, ready to review.

It runs on a schedule, pulls fresh AI news, generates post-ready packages with OpenAI, and drops everything into Google Sheets so you can approve and publish without starting from zero.

How This Automation Works

See how this solves the problem:

n8n Workflow Template: Perplexity AI to Google Sheets, post-ready ideas

Click to explore

flowchart LR

    subgraph sg0["Scheduled Start Flow"]
        direction LR
        n0@{ icon: "mdi:play-circle", form: "rounded", label: "Scheduled Start Trigger", pos: "b", h: 48 }
        n1["<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/merge.svg' width='40' height='40' /></div><br/>Merge Streams"]
        n2@{ icon: "mdi:swap-vertical", form: "rounded", label: "Iterate Records", pos: "b", h: 48 }
        n3@{ icon: "mdi:swap-vertical", form: "rounded", label: "Profile Details", pos: "b", h: 48 }
        n4@{ icon: "mdi:robot", form: "rounded", label: "Generate Content Packages", 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/>Fetch AI News Topic"]
        n6["<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/>Retrieve Market Trend Topic"]
        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/>Gather Automation Topic"]
        n8["<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/>Parse Topic Content A"]
        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/>Parse Topic Content B"]
        n10["<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/>Parse Topic Content C"]
        n11["<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/>Combine Topic Outputs"]
        n12["<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/>Parse Generated Packages"]
        n13@{ icon: "mdi:database", form: "rounded", label: "Append to Sheets", pos: "b", h: 48 }
        n14@{ icon: "mdi:message-outline", form: "rounded", label: "Send Email Alert", pos: "b", h: 48 }
        n1 --> n11
        n3 --> n4
        n13 --> n2
        n12 --> n2
        n11 --> n3
        n2 --> n14
        n2 --> n13
        n8 --> n6
        n8 --> n1
        n0 --> n5
        n9 --> n7
        n9 --> n1
        n10 --> n1
        n4 --> n12
        n5 --> n8
        n6 --> n9
        n7 --> n10
    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 n4 ai
    class n13 database
    class n5,n6,n7 api
    class n8,n9,n10,n11,n12 code
    classDef customIcon fill:none,stroke:none
    class n1,n5,n6,n7,n8,n9,n10,n11,n12 customIcon

The Challenge: Daily content can’t depend on “inspiration”

Short-form content looks simple until you try to produce it consistently. The real time drain is not recording. It’s the daily research loop: find something timely, verify it, pull a quote, create an angle, and then write three different pieces of copy (script, caption, overlays) that still sound like you. Miss a day or two and you’re back to scrambling, which usually leads to safe, generic posts that don’t move the needle. Honestly, it’s exhausting because it’s mentally expensive work done under a deadline you set for yourself.

It adds up fast. Here’s where it breaks down in real life.

Research happens in five tabs, but your drafts live somewhere else, so context keeps getting lost.
Scripts and captions don’t match your voice, which means you rewrite instead of refine.
When you rely on “what I saw on X today,” you repeat topics and miss bigger trends your audience would actually care about.
There’s no simple approval pipeline, so “I’ll post later” turns into “maybe next week.”

The Fix: Daily AI news packages delivered into Google Sheets

This workflow runs every morning (by default, 6 AM IST) and does the boring parts for you. It calls Perplexity AI three times to fetch fresh, relevant stories across AI news, market trends, and business automation. Then it cleans and combines those topic results into one structured input, along with your “About me” profile (name, niche, business, services, and context). OpenAI uses that combined input to create complete content packages: a short video script with a hook and mini narrative, a caption with a clear call to action and hashtags, plus punchy text overlay ideas for the video’s opening screen. Finally, it appends each package as a new row in Google Sheets and emails you to say the ideas are ready.

The workflow starts with a scheduled trigger and three Perplexity HTTP requests. From there, parsing and merging turns messy news into clean prompts for OpenAI. Google Sheets becomes your review queue, and Gmail is the nudge that keeps your publishing cadence alive.

What Changes: Before vs. After

What This Eliminates

Impact You’ll See

Manually hunting for “today’s AI story” across multiple sources.
Copy-pasting headlines and citations into drafts and losing track of sources.
Writing separate script, caption, and overlays from scratch for every idea.
Forgetting to review drafts because there’s no daily prompt to check.

Most teams get about an hour back per posting day, sometimes more when the topic is complex.
You start the day with a filled content sheet instead of a blank page.
More consistent brand voice, because your “About me” context is baked in.
A simple approval workflow appears naturally (Sheet columns like Approval and Published).
You can batch-record faster because the scripts are already shaped and short.

Real-World Impact

Say you want 3 short-form posts per week. Manually, you might spend about 30 minutes researching, 20 minutes writing a script, and another 20 minutes on caption plus overlay ideas, so roughly 1 hour per post. That’s about 3 hours a week just to get to “draft.” With this workflow, the daily run happens automatically, then you spend maybe 10 minutes reviewing and tweaking a package in Google Sheets. You get your week’s drafts without the research spiral.

Requirements

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Perplexity AI API for daily AI news research.
OpenAI to generate scripts, captions, overlays.
Google Sheets to store and review content rows.
Gmail to send the “ideas ready” email.
Perplexity API Key (get it from your Perplexity dashboard).
OpenAI API Key (get it from the OpenAI platform dashboard).

Skill level: Beginner. You’ll connect accounts, paste API keys, and update one Google Sheet ID.

Need help implementing this? Talk to an automation expert (free 15-minute consultation).

The Workflow Flow

A daily schedule triggers the run. At the chosen time, n8n kicks off three separate requests to Perplexity AI so you’re not betting everything on one query.

News is cleaned up and combined. The workflow parses each topic response, keeps the useful parts (including citations), and merges them into one “ready for writing” input.

Your profile context is added. A configurable “About me” section supplies the personal brand details that keep the output from sounding like generic AI content.

OpenAI generates the content packages. Scripts stay concise (under 700 characters), captions include a CTA and hashtags, and overlays are short enough to fit a thumbnail or opening frame.

Everything lands in Google Sheets and you get notified. Each package becomes a new row in a “Content Idea” sheet, then Gmail sends a quick confirmation so you know it’s ready.

You can easily modify the three Perplexity topics to match your niche, so the sheet fills with ideas your audience actually wants. 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 to collect AI-related topics.

Add and open Scheduled Start Trigger.
Set the schedule rule to run at 06:00 using Trigger At Hour in the interval configuration.
Ensure Scheduled Start Trigger connects to Fetch AI News Topic.

Step 2: Connect Perplexity Topic Fetching

These HTTP requests pull three topic streams for AI news, market trends, and automation.

Open Fetch AI News Topic and set URL to https://api.perplexity.ai/chat/completions with Method POST.
Set JSON Body to the provided expression starting with ={ "model": "sonar-pro", ... }.
In Fetch AI News Topic headers, set Authorization to Bearer [CONFIGURE_YOUR_TOKEN] and Content-Type to application/json.
Repeat the same header and JSON body pattern for Retrieve Market Trend Topic and Gather Automation Topic, keeping their unique prompt text intact.
Confirm the parallel flow: Parse Topic Content A outputs to both Retrieve Market Trend Topic and Merge Streams in parallel, and Parse Topic Content B outputs to both Gather Automation Topic and Merge Streams in parallel.

⚠️ Common Pitfall: Leaving the Authorization token placeholder will cause all three topic requests to fail.

Step 3: Configure Topic Parsing and Merge Logic

Code nodes parse API responses and merge the three topic streams into a combined dataset.

Keep the JavaScript in Parse Topic Content A, Parse Topic Content B, and Parse Topic Content C as provided to extract content and citations.
Open Merge Streams and confirm Number of Inputs is 3.
In Combine Topic Outputs, ensure the JS combines content with items.map(item => item.json.content).join('\n\n') and dedupes citations.

Tip: If you modify any upstream prompts, keep Combine Topic Outputs intact so the content aggregation still works.

Step 4: Set Up Profile and AI Generation

Profile data is injected into the prompt and used to generate content packages.

Open Profile Details and replace placeholders: set Name to [YOUR_NAME], Niche to [YOUR_NICHE], Business Name to [YOUR_BUSINESS], and Busines Type to [YOUR_BUSINESS_TYPE].
Open Generate Content Packages and confirm the Model is gpt-4.1-mini.
Verify the message content includes expressions like {{ $json.Name }} and {{ $('Combine Topic Outputs').item.json.combinedContent }}.
Credential Required: Connect your openAiApi credentials in Generate Content Packages.

⚠️ Common Pitfall: The prompt enforces strict output formatting. Changing the “Text Overlay / Video Script / Caption Text” labels may break Parse Generated Packages.

Step 5: Parse, Batch, and Store Output

Generated packages are parsed, split into records, appended to Google Sheets, and followed by an email alert.

Keep the JavaScript in Parse Generated Packages to extract text_overlay_output, video_script_output, and caption_text_output.
Ensure Iterate Records remains connected from Parse Generated Packages and outputs to both Append to Sheets and Send Email Alert.
Open Append to Sheets and set Document to [YOUR_ID] and Sheet Name to [YOUR_ID] (as shown in the node parameters).
Map columns in Append to Sheets as follows: Caption → {{ $json.caption_text_output }}, Text Overlay → {{ $json.text_overlay_output }}, Video Script → {{ $json.video_script_output }}.
Credential Required: Connect your googleSheetsOAuth2Api credentials in Append to Sheets.
Open Send Email Alert and set Send To to [YOUR_EMAIL], Subject to Content Generated, and Message to 10 new articles are added in the google sheets..
Credential Required: Connect your gmailOAuth2 credentials in Send Email Alert.

Tip: If your Sheet headers differ from “Text Overlay,” “Video Script,” and “Caption,” update the column mapping to match your sheet exactly.

Step 6: Test and Activate Your Workflow

Run a full test to verify topic retrieval, AI generation, parsing, and storage.

Click Execute Workflow and watch the run from Scheduled Start Trigger through Send Email Alert.
Confirm Merge Streams receives three inputs and Combine Topic Outputs outputs combinedContent and combinedCitations.
Verify Parse Generated Packages outputs multiple items with text_overlay_output, video_script_output, and caption_text_output.
Check your Google Sheet for new rows and ensure you receive the email from Send Email Alert.
Switch the workflow to Active to run automatically on schedule.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Watch Out For

Google Sheets OAuth permissions can be picky. If appends fail, check the connected Google account in n8n credentials and confirm it has edit access to the target sheet.
If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
Perplexity and OpenAI API keys can get rotated or rate-limited. When results suddenly look empty, check your Perplexity HTTP request headers and your OpenAI usage limits first.

Common Questions

How quickly can I implement this Perplexity Sheets automation automation?

About 30 minutes if your accounts and keys are ready.

Can non-technical teams implement this Perplexity Sheets automation?

Yes. You won’t write code, but you will paste API keys and pick the correct Google Sheet.

Is n8n free to use for this Perplexity Sheets automation workflow?

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 and Perplexity API usage costs.

Where can I host n8n to run this automation?

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.

How do I adapt this Perplexity Sheets automation solution to my specific challenges?

Start by editing the “About me” node so the scripts sound like your brand, not a template. Then adjust the three Perplexity topic requests (AI news, market trends, automation) to match your niche, like “AI for real estate” or “AI for DTC growth.” If you want different output formats, change the prompt inside the OpenAI “Generate Content Packages” node and keep the “under 700 characters” constraint if you’re targeting Reels/TikTok pacing. You can also add extra columns in Google Sheets (like Platform, Owner, or Due Date) without changing the core logic.

Why is my Google Sheets connection failing in this workflow?

Usually it’s the wrong Google account connected in n8n, or that account doesn’t have edit access to the destination sheet. Double-check the Google Sheets credential selected in the “Append to Sheets” node, then confirm the sheet ID (documentId) matches your copied template. If it worked yesterday and failed today, re-authenticate Google OAuth in n8n because tokens do expire sometimes. Also confirm you didn’t rename the worksheet tab that the node targets.

What’s the capacity of this Perplexity Sheets automation solution?

If you self-host, there’s no execution limit (it mostly depends on your server and API rate limits). On n8n Cloud, your limit depends on plan, and this workflow counts one execution per daily run plus any batching as it appends rows. Practically, most small teams run this daily and generate a handful of ideas without issues; if you scale to many brands or topics, you’ll want to watch API quotas and execution volume.

Is this Perplexity Sheets automation automation better than using Zapier or Make?

Often, yes. This workflow uses multiple HTTP requests, parsing, merging streams, and batching into Google Sheets, and n8n handles that kind of branching and transformation cleanly. You also get a self-hosting option, which can matter once you’re running daily automations across clients. Zapier or Make can still be fine if you want the simplest possible version and don’t care about deeper control. If you’re unsure, Talk to an automation expert and describe your volume and channels.

Once this is running, your “I should post today” moment turns into a quick review in Google Sheets. The workflow does the repetitive work so you can spend your energy on the insight and delivery.

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.

Lisa Granqvist

Workflow Automation Expert

Expert in workflow automation and no-code tools.

{
"id": "",
"meta": {
"instanceId": "067a71a555660ed041fc1c6e7df28d7060bd64329148740da724f1c3a5631808"
},
"nodes": [
{
"id": "flowpast-topbar-5995",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
20
],
"parameters": {
"color": 7,
"width": 830,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "ba46fd37-7223-4bf4-9ee2-48d25c415f09",
"name": "Scheduled Start Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
680,
125
],
"parameters": {
"rule": {
"interval": [
{
"triggerAtHour": 6
}
]
}
},
"typeVersion": 1.2
},
{
"id": "18aac787-d988-4505-876d-72dc2c5e8056",
"name": "Merge Streams",
"type": "n8n-nodes-base.merge",
"position": [
730,
355
],
"parameters": {
"numberInputs": 3
},
"typeVersion": 3.1
},
{
"id": "233798de-74b0-42bb-83ef-2151fbce1f8b",
"name": "Iterate Records",
"type": "n8n-nodes-base.splitInBatches",
"position": [
75,
745
],
"parameters": {
"options": []
},
"typeVersion": 3
},
{
"id": "91253544-dba4-4055-ac8c-b5c0a0ac8077",
"name": "Profile Details",
"type": "n8n-nodes-base.set",
"position": [
425,
525
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "e1fa7dff-0850-4743-a503-85c234802478",
"name": "Name",
"type": "string",
"value": "[YOUR_NAME]"
},
{
"id": "a2452ec6-4130-4057-bd6f-26512fbc3dd9",
"name": "Niche",
"type": "string",
"value": "[YOUR_NICHE]"
},
{
"id": "89ec4977-fd00-432f-b71c-73ee2d2d89a0",
"name": "Business Name",
"type": "string",
"value": "[YOUR_BUSINESS]"
},
{
"id": "2ff18a0a-45a8-45c2-9a99-0f051d294e61",
"name": "Busines Type",
"type": "string",
"value": "[YOUR_BUSINESS_TYPE]"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "c152e25f-4f81-4277-a58f-c60933f2ffdd",
"name": "Generate Content Packages",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
225,
550
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini",
"cachedResultName": "GPT-4.1-MINI"
},
"options": [],
"messages": {
"values": [
{
"content": "=Your Role:\nYou are \"CreatorAI,\" an expert short-form video content strategist and scriptwriter specializing in AI.\n\nUser & Objectives:\nYour user is {{ $json.Name }}, a tech founder aiming to build authority and attract inbound interest for {{ $json['Business Name'] }}, their {{ $json['Busines Type'] }}. Content should educate, entertain, and establish {{ $json.Name }} as a thought leader, leading to client acquisition naturally.\n\n{{ $json.Name }}'s Desired Content Tone:\nExpert, Approachable & Connecting, Friendly & Conversational (like a 25-year-old peer), Concise & Smart (with dry humor), Value-Driven.\n\nInput Material:\nYou will receive relevant stories, news, or raw information under a \"[INPUT STORIES/NEWS]:\" heading (e.g., {{ $('Combine Topic Outputs').item.json.combinedContent }} and citations: {{ $('Combine Topic Outputs').item.json.combinedCitations }}). Use this for content generation.\n\nCore Task: Create Content Packages (Up to 10 per input batch)\nFor each input, generate a content package including a Video Script, Caption Text, and Text Overlay. All content must focus on tangible business benefits and solutions.\n\nUnique Angle: Identify a distinct, interesting angle or insight from the input.\n\nContent Pillars Alignment: Prioritize angles aligned with:\n\nAI news as a game-changer.\n\nAI automation solving business pain points (time, cost, efficiency).\n\nSpecific AI automation use cases/applications.\n\nAI agents/custom workflows transforming operations.\n\nFuture of work with AI.\n\nSales process automation benefits.\n\nQuick AI tool tips/productivity hacks.\n\nDebunking AI myths.\n\nBroader implications of AI for founders/professionals.\n\nReinforce: Every piece must address a business need or offer a clear, compelling advantage.\n\nOutput Requirements (Per Content Package):\n\nA. Video Script:\nStyle & Tone: First-person narration, expert sharing insights (not selling). Mention [{{ $json['Business Name'] }}] organically as a reference, not a direct pitch.\n\nEngagement: Powerful hook (first 3 seconds).\n\nMini-Narrative: Problem/event \u2192 generic AI solution/strategy \u2192 potential impact. DO NOT mention [{{ $json['Business Name'] }}] here.\n\nClarity: Single, clear takeaway. Simple language, no jargon unless clarified.\n\nShow, Don't Tell: Vivid language, concrete examples, micro-stories (struggle \u2192 AI turning point \u2192 positive outcome).\n\nHuman-Centric: Focus on impact on employees/founders.\n\nPacing & Conciseness: UNDER 700 CHARACTERS. Short, impactful sentences, natural line breaks.\n\nFormatting: NEVER use triple quotes (\"\"\").\n\nB. Caption Text:\nTone: Friendly, expert, funny, approachable.\n\nStructure: Engaging hook/question, more context/value than script.\n\nCall to Action (CTA): Clear, direct engagement. Ask for a specific keyword comment (e.g., \"Comment 'Workflow' for more\"). Add \"Follow for more.\"\n\nHashtags: 3-5 relevant, space-separated (e.g., #AIautomation #BusinessGrowth).\n\nC. Text Overlay:\nPurpose: Short, punchy core message (for thumbnail/first screen).\n\nFormat: Extremely concise (3-7 words), ALL CAPS or Title Case.\n\nContent: Intriguing hook, benefit, or core idea from video's angle.\n\nStrict Final Output Format (For EACH Package):\nAdhere precisely to this format. Do not add any extra formatting, explanations, or markdown around these lines:\n\nText Overlay: [YOUR GENERATED TEXT OVERLAY HERE]\nVideo Script: [YOUR GENERATED VIDEO SCRIPT HERE]\nCaption Text: [YOUR GENERATED CAPTION TEXT HERE]"
}
]
}
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.8
},
{
"id": "15a10fc1-c346-4baf-aeb8-361ec819aa6d",
"name": "Fetch AI News Topic",
"type": "n8n-nodes-base.httpRequest",
"position": [
475,
150
],
"parameters": {
"url": "https://api.perplexity.ai/chat/completions",
"method": "POST",
"options": [],
"jsonBody": "={\n  \"model\": \"sonar-pro\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"Be precise and concise.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Find me 5 new, interesting, and relevant stories and news related to artificial intelligence from today or yesterday. Label them 1 through 5\"\n    }\n  ]\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "Bearer [CONFIGURE_YOUR_TOKEN]"
},
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"typeVersion": 4.1
},
{
"id": "0f2cc14b-72d2-44ed-92e7-1c203caf6bc5",
"name": "Retrieve Market Trend Topic",
"type": "n8n-nodes-base.httpRequest",
"position": [
30,
155
],
"parameters": {
"url": "https://api.perplexity.ai/chat/completions",
"method": "POST",
"options": [],
"jsonBody": "={\n  \"model\": \"sonar-pro\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"Be precise and concise.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Find me 5 new, interesting, and relevant stories and news related to market and industry trends in artificial intelligence from today or yesterday. Label them 1 through 5\"\n    }\n  ]\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "Bearer [CONFIGURE_YOUR_TOKEN]"
},
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"typeVersion": 4.1
},
{
"id": "232d6065-7132-4e10-9b09-cee1a8238b8d",
"name": "Gather Automation Topic",
"type": "n8n-nodes-base.httpRequest",
"position": [
295,
360
],
"parameters": {
"url": "https://api.perplexity.ai/chat/completions",
"method": "POST",
"options": [],
"jsonBody": "={\n  \"model\": \"sonar-pro\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"Be precise and concise.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Find me 5 new, interesting, and relevant stories related to automation of business using artificial intelligence from today or yesterday. Label them 1 through 5\"\n    }\n  ]\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "Bearer [CONFIGURE_YOUR_TOKEN]"
},
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"typeVersion": 4.1
},
{
"id": "8b31dda9-a7a6-43c4-a00f-4322a17ac110",
"name": "Parse Topic Content A",
"type": "n8n-nodes-base.code",
"position": [
255,
120
],
"parameters": {
"jsCode": "return items.map(item => {\n  const choice = item.json.choices?.[0];\n  const message = \n    choice?.message?.content || \"No message content found\";\n  const citations = \n    item.json?.citations || [];\n\n  return {\n    json: {\n      index: choice?.index ?? null,\n      role: choice?.message?.role ?? null,\n      finish_reason: \n        choice?.finish_reason ?? null,\n      content: message,\n      citations: citations,\n    },\n  };\n});"
},
"typeVersion": 2
},
{
"id": "efcb202e-4fcc-40c0-93a9-5ae6ca3ccf12",
"name": "Parse Topic Content B",
"type": "n8n-nodes-base.code",
"position": [
55,
340
],
"parameters": {
"jsCode": "return items.map(item => {\n  const choice = item.json.choices?.[0];\n  const message = \n    choice?.message?.content || \"No message content found\";\n  const citations = \n    item.json?.citations || [];\n\n  return {\n    json: {\n      index: choice?.index ?? null,\n      role: choice?.message?.role ?? null,\n      finish_reason: \n        choice?.finish_reason ?? null,\n      content: message,\n      citations: citations,\n    },\n  };\n});"
},
"typeVersion": 2
},
{
"id": "13edb6e8-878a-4fbd-893b-747f5f020b6a",
"name": "Parse Topic Content C",
"type": "n8n-nodes-base.code",
"position": [
510,
325
],
"parameters": {
"jsCode": "return items.map(item => {\n  const choice = item.json.choices?.[0];\n  const message = \n    choice?.message?.content || \"No message content found\";\n  const citations = \n    item.json?.citations || [];\n\n  return {\n    json: {\n      index: choice?.index ?? null,\n      role: choice?.message?.role ?? null,\n      finish_reason: \n        choice?.finish_reason ?? null,\n      content: message,\n      citations: citations,\n    },\n  };\n});"
},
"typeVersion": 2
},
{
"id": "6bbdb827-729b-437c-a1b2-751fc391999b",
"name": "Combine Topic Outputs",
"type": "n8n-nodes-base.code",
"position": [
650,
555
],
"parameters": {
"jsCode": "const combinedContent =\n  items.map(item =>\n    item.json.content).join('\\n\\n');\n\n// Flatten and dedupe citations\nconst combinedCitations = [\n  ...new Set(\n    items\n      .flatMap(item =>\n        item.json.citations || [])\n      .filter(url => typeof url ===\n        'string' && url.startsWith('http'))\n  )\n];\n\nreturn [{\n  json: {\n    combinedContent,\n    combinedCitations\n  }\n}];"
},
"typeVersion": 2
},
{
"id": "4417ab22-ab3b-4a68-93e5-9eab2ea7509a",
"name": "Parse Generated Packages",
"type": "n8n-nodes-base.code",
"position": [
0,
535
],
"parameters": {
"jsCode": "const results = [];\n\nfor (const item of items) {\n  // Ensure the input item has the expected structure and content\n  if (!item.json || !item.json.message || typeof item.json.message.content !== 'string') {\n    console.warn(\"Skipping item: Invalid structure or missing AI content.\", item);\n    continue;\n  }\n\n  const aiResponse = item.json.message.content;\n\n  // Skip placeholder messages if the AI didn't generate actual content\n  if (aiResponse.includes(\"Please provide the collection of relevant stories\")) {\n    console.log(\"Skipping instruction/placeholder message from AI.\");\n    continue;\n  }\n\n  const lines = aiResponse.split('\\n');\n\n  let currentPackage = {\n    text_overlay_output: \"\",\n    video_script_output: \"\",\n    caption_text_output: \"\"\n  };\n  let currentSection = \"\"; // 'overlay', 'script', 'caption'\n\n  for (const line of lines) {\n    const trimmedLine = line.trim();\n\n    // Skip empty lines unless they are part of a multi-line content (unlikely for this format)\n    if (!trimmedLine && currentSection !== \"\") {\n      // Allow empty lines within content if needed, but for strict format, they usually indicate a break\n      // For this specific format, an empty line usually means end of a section if not followed by data\n      continue;\n    }\n\n    if (trimmedLine.startsWith(\"Text Overlay:\")) {\n      // If we've already collected data for a package, push it before starting a new one\n      if (currentPackage.text_overlay_output || currentPackage.video_script_output || currentPackage.caption_text_output) {\n        results.push({ json: { ...currentPackage } }); // Push a copy of the current package\n        currentPackage = { // Reset for the new package\n          text_overlay_output: \"\",\n          video_script_output: \"\",\n          caption_text_output: \"\"\n        };\n      }\n      currentPackage.text_overlay_output = trimmedLine.substring(\"Text Overlay:\".length).trim();\n      currentSection = \"overlay\";\n    } else if (trimmedLine.startsWith(\"Video Script:\")) {\n      currentPackage.video_script_output = trimmedLine.substring(\"Video Script:\".length).trim();\n      currentSection = \"script\";\n    } else if (trimmedLine.startsWith(\"Caption Text:\")) {\n      currentPackage.caption_text_output = trimmedLine.substring(\"Caption Text:\".length).trim();\n      currentSection = \"caption\";\n    } else {\n      // Append content to the current section if it's a continuation\n      // Add a space or newline depending on desired handling of multi-line content.\n      // Given the prompt's strict output, these are usually single lines.\n      // Let's assume continuation means adding a space or newline.\n      // For short-form content, it's safer to append with a space if it's not a new key.\n      if (currentSection === \"video_script_output\") {\n        currentPackage.video_script_output += (currentPackage.video_script_output ? \" \" : \"\") + trimmedLine;\n      } else if (currentSection === \"caption_text_output\") {\n        currentPackage.caption_text_output += (currentPackage.caption_text_output ? \"\\\\n\" : \"\") + trimmedLine; // Captions might have line breaks for hashtags etc.\n      }\n      // No need to append to text_overlay_output as it's typically a single, short line.\n    }\n  }\n\n  // After the loop, push the last collected package\n  if (currentPackage.text_overlay_output || currentPackage.video_script_output || currentPackage.caption_text_output) {\n    // Final check for triple quotes in the last script\n    if (currentPackage.video_script_output) {\n      currentPackage.video_script_output = currentPackage.video_script_output.replace(/\\\"\\\"\\\"/g, \"'''\");\n    }\n    results.push({ json: { ...currentPackage } });\n  }\n}\n\nreturn results;"
},
"typeVersion": 2
},
{
"id": "508e2c05-b2db-4b01-a131-98b10cfff657",
"name": "Append to Sheets",
"type": "n8n-nodes-base.googleSheets",
"position": [
285,
765
],
"parameters": {
"columns": {
"value": {
"Caption": "={{ $json.caption_text_output }}",
"Text Overlay": "={{ $json.text_overlay_output }}",
"Video Script": "={{ $json.video_script_output }}"
},
"schema": [
{
"id": "Text Overlay",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Text Overlay",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Video Script",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Video Script",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Caption",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Caption",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Approval",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Approval",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Published",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Published",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "Content Idea"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "Content "
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.6
},
{
"id": "a19169e7-ded8-4053-9a25-3b10220ad1cf",
"name": "Send Email Alert",
"type": "n8n-nodes-base.gmail",
"position": [
505,
735
],
"webhookId": "b095003a-0562-42b5-8fe0-ac2e1b5e38e0",
"parameters": {
"sendTo": "[YOUR_EMAIL]",
"message": "10 new articles are added in the google sheets.",
"options": [],
"subject": "Content Generated"
},
"credentials": {
"gmailOAuth2": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2.1
}
],
"pinData": [],
"connections": {
"Merge Streams": {
"main": [
[
{
"node": "Combine Topic Outputs",
"type": "main",
"index": 0
}
]
]
},
"Profile Details": {
"main": [
[
{
"node": "Generate Content Packages",
"type": "main",
"index": 0
}
]
]
},
"Append to Sheets": {
"main": [
[
{
"node": "Iterate Records",
"type": "main",
"index": 0
}
]
]
},
"Parse Generated Packages": {
"main": [
[
{
"node": "Iterate Records",
"type": "main",
"index": 0
}
]
]
},
"Combine Topic Outputs": {
"main": [
[
{
"node": "Profile Details",
"type": "main",
"index": 0
}
]
]
},
"Iterate Records": {
"main": [
[
{
"node": "Send Email Alert",
"type": "main",
"index": 0
}
],
[
{
"node": "Append to Sheets",
"type": "main",
"index": 0
}
]
]
},
"Parse Topic Content A": {
"main": [
[
{
"node": "Retrieve Market Trend Topic",
"type": "main",
"index": 0
},
{
"node": "Merge Streams",
"type": "main",
"index": 0
}
]
]
},
"Scheduled Start Trigger": {
"main": [
[
{
"node": "Fetch AI News Topic",
"type": "main",
"index": 0
}
]
]
},
"Parse Topic Content B": {
"main": [
[
{
"node": "Gather Automation Topic",
"type": "main",
"index": 0
},
{
"node": "Merge Streams",
"type": "main",
"index": 1
}
]
]
},
"Parse Topic Content C": {
"main": [
[
{
"node": "Merge Streams",
"type": "main",
"index": 2
}
]
]
},
"Generate Content Packages": {
"main": [
[
{
"node": "Parse Generated Packages",
"type": "main",
"index": 0
}
]
]
},
"Fetch AI News Topic": {
"main": [
[
{
"node": "Parse Topic Content A",
"type": "main",
"index": 0
}
]
]
},
"Retrieve Market Trend Topic": {
"main": [
[
{
"node": "Parse Topic Content B",
"type": "main",
"index": 0
}
]
]
},
"Gather Automation Topic": {
"main": [
[
{
"node": "Parse Topic Content C",
"type": "main",
"index": 0
}
]
]
}
},
"name": "Automated Content Package Builder",
"versionId": ""
}