Apify + Airtable: Reels winners tracked with insights
Keeping up with Instagram Reels research sounds simple until you’re juggling creators, copying view counts, saving links, and trying to write “why this worked” notes that don’t feel made up. By the time you’re done, the trend has moved on.
This Apify Airtable automation hits social media analysts first, honestly. But marketing leads building content calendars and creators running their own swipe files feel it too. You get a repeatable way to capture winners, rank them, and store insights without turning your week into spreadsheet cleanup.
Below you’ll see how the workflow runs, what it produces inside Airtable, and how to think about customizing it so it matches your niche and your research cadence.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Apify + Airtable: Reels winners tracked with insights
flowchart LR
subgraph sg0["When Executed by Another Workflow Flow"]
direction LR
n0@{ icon: "mdi:cog", form: "rounded", label: "Wait", pos: "b", h: 48 }
n1@{ icon: "mdi:swap-vertical", form: "rounded", label: "Set Prompt", 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/httprequest.dark.svg' width='40' height='40' /></div><br/>Gemini - Generate Upload URL"]
n3["<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/>Gemini - Upload File"]
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/httprequest.dark.svg' width='40' height='40' /></div><br/>Gemini - Ask Questions"]
n5@{ icon: "mdi:swap-vertical", form: "rounded", label: "Save Values", pos: "b", h: 48 }
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/httprequest.dark.svg' width='40' height='40' /></div><br/>Download File"]
n14["<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/airtable.svg' width='40' height='40' /></div><br/>Get Video"]
n15["<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/airtable.svg' width='40' height='40' /></div><br/>Set Guideline"]
n18@{ icon: "mdi:play-circle", form: "rounded", label: "When Executed by Another Wor..", pos: "b", h: 48 }
n0 --> n1
n14 --> n2
n1 --> n4
n5 --> n0
n12 --> n3
n3 --> n5
n4 --> n15
n2 --> n12
n18 --> n14
end
subgraph sg1["Schedule Flow"]
direction LR
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/>Apify - Fetch Reels"]
n7@{ icon: "mdi:cog", form: "rounded", label: "Sort", pos: "b", h: 48 }
n8@{ icon: "mdi:cog", form: "rounded", label: "Limit", pos: "b", h: 48 }
n9@{ icon: "mdi:swap-vertical", form: "rounded", label: "Save Fields", pos: "b", h: 48 }
n10@{ icon: "mdi:swap-vertical", form: "rounded", label: "Loop Over Items", pos: "b", h: 48 }
n11@{ icon: "mdi:cog", form: "rounded", label: "Execute Workflow1", pos: "b", h: 48 }
n13["<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/airtable.svg' width='40' height='40' /></div><br/>Create Video"]
n16["<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/airtable.svg' width='40' height='40' /></div><br/>Search Creators"]
n17@{ icon: "mdi:play-circle", form: "rounded", label: "Schedule Trigger", pos: "b", h: 48 }
n7 --> n8
n8 --> n13
n9 --> n7
n13 --> n11
n10 --> n6
n16 --> n10
n17 --> n16
n11 --> n10
n6 --> n9
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 n18,n17 trigger
class n14,n15,n13,n16 database
class n2,n3,n4,n12,n6 api
classDef customIcon fill:none,stroke:none
class n2,n3,n4,n12,n14,n15,n6,n13,n16 customIcon
The Problem: Reels Research Turns Into Busywork
Reels research usually starts with good intentions. You open Instagram “for five minutes,” spot a few strong videos, then realize you need the link, the creator handle, the view count, the hook style, the caption structure, the audio, and some notes on what you’d reuse. Now multiply that by 10 creators, every week. The manual process is slow, it’s easy to miss context, and you end up with half-finished notes that don’t help when it’s time to create.
The friction compounds. After a while, the swipe file stops getting updated, and your team falls back to guessing.
- You waste about 2 hours a week just collecting links, screenshots, and metrics across creators.
- View counts and “top videos” change quickly, so yesterday’s notes can become misleading.
- Insights get stored in random places (DMs, spreadsheets, Notion), which makes patterns hard to spot.
- Manual ranking and filtering invites mistakes, especially when you’re moving fast.
The Solution: Apify Pulls Winners, Airtable Stores the Story
This workflow turns Reels research into a system. It starts by pulling a list of creators from Airtable, then uses Apify to retrieve recent Reels for each creator. Next, it maps the Reel details into clean fields, sorts by views, and limits the results so you only keep the highest-performing videos worth studying. For deeper “why it worked” notes, the workflow can fetch the actual video file, upload it to an external AI analysis service (the workflow uses Gemini endpoints via HTTP), and generate structured takeaways using an analysis prompt. Finally, everything is saved back into Airtable as a neat record you can filter, tag, and reuse.
The workflow begins either on a schedule or via a manual run. It collects creators, pulls Reels, ranks them, then writes the top entries into Airtable. If you enable the analysis portion, it waits briefly for the upload to finish, sends a prompt, and updates the Airtable record with clear guidelines and observations.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you track 15 creators and you want the top 3 Reels from each, once a week. Manually, you might spend about 5 minutes per creator finding recent posts, copying links, and writing a quick note, which is roughly 75 minutes (and that’s before deeper analysis). With this workflow, you trigger it once, let Apify pull the Reels, and Airtable fills itself. You’ll spend maybe 10 minutes skimming the ranked results and tagging the ones you want to recreate.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Airtable for creator list and swipe-file database
- Apify to retrieve Reels data per creator
- Gemini API key (get it from Google AI Studio)
Skill level: Intermediate. You’ll connect accounts, confirm Airtable fields, and paste a couple of API credentials into n8n nodes.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
A manual run or a schedule kicks it off. You can start this workflow on demand while testing, then switch to the scheduled trigger to refresh your research weekly (or daily, if you’re aggressive).
Airtable provides the “source of truth” list. The workflow pulls creator records from Airtable, then iterates through them in batches so it can handle larger lists without falling over.
Apify fetches Reels and n8n ranks them. Reels are retrieved via HTTP request, mapped into consistent fields, sorted by views, and limited to the top set you actually care about reviewing.
AI analysis writes the takeaway, then Airtable stores it. For each selected video, the workflow can fetch the file, upload it for analysis, wait briefly, generate insights from a defined prompt, and update the Airtable record so your swipe file includes the “why,” not just the link.
You can easily modify the number of Reels kept per creator to match your review time and content volume. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Trigger
Set up the two workflow entry points that start the automation: a scheduled run and an inbound execution trigger.
- Open Scheduled Automation Trigger and define your schedule rule (the workflow uses a monthly interval by default).
- Open Workflow Execution Trigger and confirm Input Source is set to
passthroughfor child workflow calls. - Verify the execution flow from Scheduled Automation Trigger → Find Creator Records and Workflow Execution Trigger → Fetch Video Entry.
Tip: Use the scheduled trigger for batch collection, and the workflow execution trigger for targeted processing of a single video record.
Step 2: Connect Airtable Records for Creators and Videos
Connect Airtable to pull creator records, fetch video metadata, and store final analysis updates.
- Open Find Creator Records and select the correct Base and Table (the workflow expects a “Creators” table). Credential Required: Connect your
airtableTokenApicredentials. - Open Fetch Video Entry and set ID to
={{ $json.id }}to load a specific video record. Credential Required: Connect yourairtableTokenApicredentials. - Open Create Video Record and verify the field mappings: Video to
={{ [ {"url":$json.url} ] }}, Views to={{ $json.views }}, Caption to={{ $json.caption }}, and Creator to={{ [$json.creator] }}. Credential Required: Connect yourairtableTokenApicredentials. - Open Update Video Guideline and confirm the update mapping uses
={{ $('Fetch Video Entry').first().json.id }}and={{ $json.candidates[0].content.parts[0].text }}. Credential Required: Connect yourairtableTokenApicredentials.
⚠️ Common Pitfall: Ensure the Airtable field names exactly match the workflow mappings (e.g., Video, Views, Caption, Creator, Guideline), or updates will fail.
Step 3: Retrieve and Rank Reels by Views
Use Apify to fetch Instagram reels, map the data, and rank it before creating Airtable records.
- Open Iterate Creator List to batch creators from Airtable; it feeds the reels retrieval loop.
- Open Apify Retrieve Reels and set JSON Body to the provided payload, including
{{ $json['Instagram Username'] }}and{{ new Date().toISOString().slice(0, 10).replace(/-\\d+$/, '-01') }}. - Set the Query Parameter token in Apify Retrieve Reels to your Apify API token (replace
[CONFIGURE_YOUR_TOKEN]). - Open Map Reel Fields and confirm JSON Output is set to
={"url": {{ JSON.stringify($json.videoUrl) }}, "views": {{ $json.videoViewCount }}, "caption": {{ JSON.stringify($json.caption) }}, "creator": "{{ $('Iterate Creator List').item.json.Name }}"}. - Open Order by Views and ensure sorting is descending on views.
- Open Restrict Results to limit the number of top reels that become Airtable records.
Tip: If Apify returns no data, validate the Instagram usernames in Airtable and confirm the resultsType value in Apify Retrieve Reels.
Step 4: Configure Gemini Upload and Analysis Pipeline
Upload the reel file to Gemini, wait for processing, and analyze it using the structured prompt.
- Open Gemini Create Upload Link and confirm the URL is
https://generativelanguage.googleapis.com/upload/v1beta/fileswith JSON Body set to{"file": {"display_name": "{{ $json.Video[0].filename }}"}}. - Set the Query Parameter key in Gemini Create Upload Link to your Google Generative Language API key (replace
[CONFIGURE_YOUR_TOKEN]). - Open Fetch Video File and set URL to
={{ $('Fetch Video Entry').item.json.Video[0].url }}to download the video file. - Open Gemini Send File and set URL to
={{ $('Gemini Create Upload Link').item.json.headers['x-goog-upload-url'] }}and ensure Content Type isbinaryData. - Set the Query Parameter key in Gemini Send File to your API key (replace
[CONFIGURE_YOUR_TOKEN]). - Open Store Upload Details and confirm assignments for gemini_file_url
={{ $json.file.uri }}, mimeType={{ $json.file.mimeType }}, and airtable_rec_id={{ $('Fetch Video Entry').item.json.id }}. - Open Pause Interval and set Amount to
60seconds to allow the file to be processed. - Open Define Analysis Prompt and verify the prompt value includes your analysis instructions (the workflow uses the long multi-point prompt in the node).
- Open Gemini Analyze Clip and confirm the JSON Body references
{{ $json.prompt }},{{ $('Store Upload Details').item.json.mimeType }}, and{{ $('Store Upload Details').item.json.gemini_file_url }}. - Set the Query Parameter key in Gemini Analyze Clip to your API key (replace
[CONFIGURE_YOUR_TOKEN]).
⚠️ Common Pitfall: If Gemini returns empty results, verify the upload response contains file.uri and the wait time in Pause Interval is long enough for processing.
Step 5: Configure Sub-Workflow Handoff
After record creation, the workflow calls another workflow and loops back through creators.
- Open Run Sub-Workflow (Configure Required) and set Workflow ID to the child workflow you want to execute.
- Confirm the execution flow from Create Video Record → Run Sub-Workflow (Configure Required) → Iterate Creator List to continue processing creators.
⚠️ Common Pitfall: Leaving Workflow ID blank in Run Sub-Workflow (Configure Required) will cause the automation to stop after creating video records.
Step 6: Test and Activate Your Workflow
Validate each branch of the workflow and then enable it for production runs.
- Click Execute Workflow and test the scheduled branch by manually running Scheduled Automation Trigger to ensure creators are fetched and reels are stored in Airtable.
- Test the execution branch by running Workflow Execution Trigger with a sample record id so Fetch Video Entry and the Gemini upload/analyze chain complete.
- Confirm success when Airtable records are created by Create Video Record and guidelines are written by Update Video Guideline.
- Once tests succeed, toggle the workflow to Active so the schedule and child workflow calls run in production.
Common Gotchas
- Airtable credentials can expire or need specific permissions. If things break, check the n8n Airtable node credentials screen and confirm the base/table access first.
- If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Apify results can look “wrong” if your actor input is too broad. Double-check the Apify actor settings and the creator handle field being passed from Airtable.
Frequently Asked Questions
About 45 minutes if your Airtable base and Apify access are ready.
No. You’ll mostly connect accounts and match Airtable fields to what the workflow expects.
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 Gemini and Apify usage costs, which depend on how many videos you analyze.
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 one of the easiest tweaks. Change the “Restrict Results” (limit) node to keep more videos per creator, and adjust the “Define Analysis Prompt” (set) node to focus on your niche (fitness, SaaS, local services, whatever). You can also add extra Airtable fields in “Map Reel Fields” so you store things like hook type, CTA style, or editing pattern. If you want the analysis to run only on certain creators, use the If node to filter before the upload and analysis steps.
Usually it’s an expired token or the wrong base being selected in the Airtable node. Reconnect Airtable inside n8n, then verify the table and fields still exist (renamed columns are a sneaky one). If it fails only on “Create Video Record,” check that required fields aren’t set to “must have a value” in Airtable.
If you self-host, the practical limit is your server and your Apify/Gemini quotas. On n8n Cloud, it depends on your execution allowance, but most small teams can comfortably process a weekly batch of a few hundred Reels if you’re only analyzing the top subset. The heavy part is video analysis, so many people fetch broadly and analyze narrowly.
Often, yes, because this workflow has batching, sorting, limiting, and a multi-step analysis chain that’s awkward (and pricey) in simpler automation tools. n8n also makes it easier to keep logic in one place, especially when you want to loop through creators and apply the same rules each time. Zapier or Make can still work if you only want to push raw data from Apify into Airtable and skip analysis. But once you add “fetch file → upload → wait → analyze → update record,” the cracks show. Talk to an automation expert if you want help choosing the cleanest setup.
Once this is running, your swipe file updates itself and your “what should we make next?” meeting gets a lot easier. The workflow handles the repetitive stuff, so you can focus on the creative calls that actually move results.
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.
