Apify + Google Sheets for competitor visual insights
You know the feeling: you think a competitor changed their look, but proving it means hours of scrolling, screenshotting, and messy notes that never get reused. By the time you share findings, they’re already old.
This is the kind of busywork that hits social media managers first. But marketing leads and agency strategists feel it too, especially when “Apify Sheets insights” would save them from doing the same competitor audit every Monday.
This workflow pulls posts from Instagram and TikTok with Apify, runs visual analysis with GPT-4o Vision, then logs a clean summary to Google Sheets so you can track trends week to week and act faster.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Apify + Google Sheets for competitor visual insights
flowchart LR
subgraph sg0["Form Flow"]
direction LR
n0@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Scrape Instagram Posts", pos: "b", h: 48 }
n1@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Scrape TikTok Posts", pos: "b", h: 48 }
n2["<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/>Analyze Images with GPT-4o V.."]
n3@{ icon: "mdi:cog", form: "rounded", label: "Aggregate All Results", pos: "b", h: 48 }
n4["<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/>Generate Competitive Analysi.."]
n5@{ icon: "mdi:database", form: "rounded", label: "Log Results to Google Sheets", pos: "b", h: 48 }
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/form.svg' width='40' height='40' /></div><br/>Form Trigger1"]
n7@{ icon: "mdi:swap-vertical", form: "rounded", label: "Workflow Configuration1", pos: "b", h: 48 }
n8@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Platform Router1", pos: "b", h: 48 }
n9@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Filter Images Only1", pos: "b", h: 48 }
n6 --> n7
n8 --> n0
n8 --> n1
n9 --> n2
n1 --> n9
n3 --> n4
n0 --> n9
n7 --> n8
n2 --> n3
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 n0,n1,n8,n9 decision
class n5 database
class n2,n4 code
classDef customIcon fill:none,stroke:none
class n2,n4,n6 customIcon
The Problem: Competitor visual research takes forever
Competitive research sounds simple until you actually do it. You open Instagram, then TikTok, then you start saving posts, grabbing screenshots, and trying to describe “the vibe” in words that your team will understand next week. Meanwhile, your real job (planning content that wins) is sitting there untouched. The worst part is the inconsistency: one person notes “bright colors,” another says “pastel,” and nobody can tell if the trend is real or just a one-off post that caught their eye.
It adds up fast. And the friction compounds when you’re tracking more than one competitor.
- Manually reviewing two platforms for four accounts can easily eat about 2 hours per week, and that’s before you write a summary.
- Screenshots don’t turn into insights on their own, so you end up with a folder full of “evidence” and no decision.
- Without a structured log, you can’t compare week to week, which means you keep re-learning the same lesson.
- Teams lose confidence in the findings because the method changes every time someone new does the audit.
The Solution: Apify scrapes + AI vision analysis + Sheets logging
This workflow turns competitor visual research into a repeatable system. It starts with a simple submission form where you enter your own handle and up to three competitors, then choose which platforms you want (Instagram, TikTok, or both). n8n routes that request to the right Apify scraper, collects recent posts, and filters down to records that actually contain image content worth analyzing. From there, GPT-4o Vision reviews each image and extracts consistent attributes like color palette, composition style, mood or emotion, and text treatment (overlays, typography, density). Finally, the workflow compiles everything into a single competitive summary with recommendations and writes the results into Google Sheets so you have a searchable history.
The workflow kicks off from the form trigger, then uses Apify to pull content for each selected platform. After image-only filtering, AI vision analysis runs across the set and an aggregated report is generated. Google Sheets becomes your living “trend log,” not a one-time document.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you track your brand plus three competitors across Instagram and TikTok, and you review about 10 recent posts per account. Manually, even a quick scan and note-taking can take maybe 5 minutes per post, which is roughly 3–4 hours total. With this workflow, you spend about 5 minutes filling the form, then you wait while Apify pulls content and GPT-4o Vision analyzes it (often under an hour, depending on volume). The output shows up in Google Sheets as a structured log and a weekly-style summary, ready to share.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Apify for Instagram and TikTok scraping.
- Google Sheets to store history and summaries.
- OpenAI API key (get it from the OpenAI dashboard API keys page).
Skill level: Intermediate. You’ll copy credentials into n8n, paste a Sheet ID, and adjust a couple of variables if you want more or fewer posts.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
A submission form triggers the run. You enter your account, up to three competitors, and choose Instagram, TikTok, or both. That input is cleaned up so the workflow can reuse it consistently.
Platforms are routed automatically. A routing step sends Instagram requests to the Instagram Apify scraper and TikTok requests to the TikTok Apify scraper, so you don’t maintain separate workflows for each network.
Images are filtered and analyzed. The workflow keeps the records that contain usable image content, then GPT-4o Vision extracts the visual attributes you care about (palette, composition, mood, text styling) in a standardized format.
A competitive summary is generated and logged. Results are compiled into a readable report with recommendations, then written into Google Sheets with a timestamp and metadata so you can compare over time.
You can easily modify how many posts you analyze per account and what attributes the AI extracts based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Submission Form Trigger
Set up the user input form that launches the workflow and captures account details and analysis preferences.
- Add the Submission Form Trigger node as your trigger.
- Set Form Title to
Cross-Platform Competitive Visual Intelligence. - Set Form Description to
Analyze visual content from your brand and competitors across Instagram, Pinterest, and TikTok. - Ensure the form fields include Your Account/Hashtag, Competitor 1 Account, Competitor 2 Account, Competitor 3 Account, Select Platforms (checkbox), and Number of Posts to Analyze (number).
- Save the node to generate the form URL for submissions.
Step 2: Connect Apify for Platform Data Collection
Configure platform routing and connect Apify to pull Instagram and TikTok content.
- In Input Mapping Setup, keep Include Other Fields enabled and confirm the assignments map form inputs to variables like ownAccount, competitors, platforms, and postsCount.
- Set the openaiApiKey value to your key, replacing
[CONFIGURE_YOUR_API_KEY]. - In Route Platforms, confirm the two rules check
{{ $json['Select Platforms']}}forInstagramandTikTokrespectively. - In Fetch Instagram Posts, keep Operation as
Run actor and get datasetand set Custom Body to={{ { "directUrls": [ "https://www.instagram.com/" + $('Input Mapping Setup').item.json["ownAccount"] + "/", "https://www.instagram.com/" + JSON.parse($('Input Mapping Setup').item.json.competitors)[0] + "/", "https://www.instagram.com/" + JSON.parse($('Input Mapping Setup').item.json.competitors)[1] + "/" ].filter(url => !url.includes("undefined") && !url.includes("null")), "resultsType": "posts", "resultsLimit": $('Input Mapping Setup').item.json.postsCount || 10 } }}. - In Retrieve TikTok Clips, keep Operation as
Run actor and get datasetand set Custom Body to={{ { "profiles": [ $('Input Mapping Setup').item.json.ownAccount, JSON.parse($('Input Mapping Setup').item.json.competitors)[0], JSON.parse($('Input Mapping Setup').item.json.competitors)[1] ].filter(p => p), "resultsPerPage": $('Input Mapping Setup').item.json.postsCount || 10, "shouldDownloadVideos": false } }}.
Step 3: Set Up Image Filtering and AI Vision Processing
Filter content to image records and run visual analysis via OpenAI in code.
- In Filter Image Records, configure conditions to match type equals
Imageand displayUrl or imageUrl is not empty using{{ $json.type }}and{{ $json.displayUrl || $json.imageUrl }}. - In AI Vision Analysis, keep Mode set to
runOnceForEachItemand use the provided code to call OpenAI withmodel: 'gpt-4o'. - Ensure the code reads the key from
$('Input Mapping Setup').item.json.openaiApiKeyand useshttps://api.openai.com/v1/chat/completions.
[CONFIGURE_YOUR_API_KEY], the workflow will fail when AI Vision Analysis tries to call the OpenAI API.Step 4: Aggregate Results and Generate the Competitive Report
Aggregate AI outputs and generate the structured summary with a second OpenAI call.
- In Compile Analysis Results, set Aggregate to
aggregateAllItemDataand Destination Field Name toanalysisResults. - In Create Competitive Summary, keep the OpenAI call using
model: 'gpt-4'and ensure it references the API key from$('Input Mapping Setup').item.json.openaiApiKey. - Confirm the code returns the sections object, including fullReport, competitiveMatrix, and recommendedActions.
Step 5: Configure the Google Sheets Output
Write the summary and metadata into your Google Sheet for tracking and reporting.
- In Write Summary to Sheets, keep Operation set to
appendOrUpdate. - Set the Document ID to your spreadsheet ID in Document ID and select the target sheet in Sheet Name.
- Map columns to these expressions: summary →
{{ $json.fullReport.substring(0, 500) }}, platforms →{{ $('Input Mapping Setup').item.json.platforms }}, timestamp →{{ $now.toISO() }}, competitors →{{ $('Input Mapping Setup').item.json.competitors }}, own_account →{{ $('Input Mapping Setup').item.json.ownAccount }}, posts_analyzed →{{ $('Compile Analysis Results').item.json.analysisResults.length }}.
Credential Required: Connect your googleSheetsOAuth2Api credentials in Write Summary to Sheets.
Final خطوة: Test and Activate Your Workflow
Validate the full run and activate the workflow for ongoing use.
- Click Execute Workflow and submit the form from Submission Form Trigger with real accounts and platforms selected.
- Confirm that Fetch Instagram Posts and Retrieve TikTok Clips return data based on the selected platforms.
- Verify AI Vision Analysis outputs per image and Compile Analysis Results aggregates them into
analysisResults. - Check that Create Competitive Summary returns a structured report and Write Summary to Sheets appends a new row.
- Turn on the workflow using the Active toggle to enable production use.
Common Gotchas
- Apify credentials can expire or need specific permissions. If things break, check your Apify token in n8n Credentials and confirm the actor you’re calling is accessible.
- 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.
Frequently Asked Questions
About 30–60 minutes if your Apify, OpenAI, and Google access are ready.
No. You’ll mainly connect accounts and paste a Sheet ID and API keys. Light edits (like changing the number of posts to analyze) are simple and guided.
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 (usually a few cents to a couple dollars per run, depending on how many images you analyze) and your Apify usage.
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 it’s a common tweak. You can swap the Submission Form Trigger for a schedule trigger (or even a Gmail Trigger if you want “run when I email a keyword”), then keep the same platform routing and analysis steps. Most people also customize the AI prompts to match their brand categories, like “UGC-style,” “studio,” “text-heavy,” or “product-first.” If you want a tighter output, adjust the prompt in the AI Vision Analysis step and the report prompt in Create Competitive Summary.
Usually it’s an expired or incorrect Apify API token in n8n Credentials. It can also be that the Apify actor you’re calling isn’t available on your plan, or the run hits rate limits when you request too many posts at once. If the scraper returns empty data, check the input handles and confirm the platform selection is correct in the form submission.
A lot, but your limits come from your n8n plan, Apify usage, and how much vision analysis you run per batch.
For this use case, n8n is usually the better fit because you’re doing multi-branch routing (Instagram vs. TikTok), filtering, aggregation, and an AI analysis loop, which gets clunky fast in simpler builders. n8n also gives you a self-host option, which matters when you want to run bigger audits without paying per tiny step. Zapier or Make can still work if you keep it small, like one platform and a short summary. Frankly, the moment you want “up to three competitors” plus a real report, most teams are happier in n8n. Talk to an automation expert if you want a quick recommendation based on your volume.
Once this is running, competitor visual research becomes a quick input and a reliable output. You’ll spend your time making decisions, not collecting receipts.
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.
