Airtable + Amazon Suggest: keywords ready to use
You know the drill: you type a seed keyword into Amazon, skim the dropdown, copy a handful of phrases, paste them somewhere, then do it again. And again. It’s slow, messy, and it’s way too easy to lose the best ideas in a sea of tabs.
This Amazon keyword automation hits hardest for PPC managers cleaning up campaign lists, but product marketers and Amazon sellers feel it too. The outcome is simple. You get Amazon Suggest keyword ideas pulled into Airtable automatically, deduped and ready to review.
Below, you’ll see how the workflow works, what it eliminates, and how to adapt it so your keyword research stops being a weekly chore.
How This Automation Works
See how this solves the problem:
n8n Workflow Template: Airtable + Amazon Suggest: keywords ready to use
flowchart LR
subgraph sg0["Flow 1"]
direction LR
n0@{ icon: "mdi:swap-vertical", form: "rounded", label: "Clean Keywords", 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/airtable.svg' width='40' height='40' /></div><br/>Get airtable data"]
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/>Get Amazon keywords"]
n3@{ icon: "mdi:swap-vertical", form: "rounded", label: "Format output", pos: "b", h: 48 }
n4@{ icon: "mdi:cog", form: "rounded", label: "Aggregate keywords", 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/>Combine into string"]
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/airtable.svg' width='40' height='40' /></div><br/>Save keywords"]
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/webhook.dark.svg' width='40' height='40' /></div><br/>Receive Keyword"]
n3 --> n0
n0 --> n4
n7 --> n1
n1 --> n2
n4 --> n5
n5 --> n6
n2 --> n3
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 n1,n6 database
class n2,n7 api
class n5 code
classDef customIcon fill:none,stroke:none
class n1,n2,n5,n6,n7 customIcon
The Challenge: Amazon Suggest Keywords Without the Mess
Amazon Suggest is one of the fastest ways to uncover real buyer language, but collecting it manually is a grind. You start with one seed term, then you spiral into variations, misspellings, and “just one more” checks because you don’t trust you captured everything. Then comes the cleanup: duplicates, near-duplicates, random spacing, and keyword lists that don’t match your product or ad structure. Worst part, you can’t reuse the work easily next month, so you end up doing the same research twice.
It adds up fast. Here’s where it breaks down.
- Copy-pasting suggestions for even 10 seed keywords can burn about 1–2 hours, and that’s before any cleanup.
- Duplicates sneak in constantly, which means bloated PPC builds and messy negative keyword work later.
- Lists live in scattered notes and sheets, so nobody knows what’s “approved” versus experimental.
- Manual collection makes consistency almost impossible (same seed, different person, different results).
The Fix: Airtable → Amazon Suggest → Airtable (Clean, Stored, Reusable)
This workflow automates the whole “grab suggestions and organize them” loop using Airtable and Amazon’s completion API. A new keyword request comes in, the workflow fetches the matching Airtable record, then sends the seed keyword to Amazon Suggest via an HTTP request. Amazon returns a list of suggested searches, which the workflow splits into individual items, normalizes them (so spacing and formatting don’t create fake duplicates), then aggregates the final set. Finally, it builds a clean keyword string and updates the original Airtable row, so your suggestions sit right next to the seed keyword that generated them. One place. Reviewable. Easy to reuse next time you build campaigns.
The workflow starts with a keyword “hook” coming in, then it pulls your seed from Airtable. Next, it hits Amazon Suggest, cleans the response into tidy keyword items, and writes the results back to the same Airtable record. No browser dropdown scraping. No copy-paste marathons.
What Changes: Before vs. After
| What This Eliminates | Impact You’ll See |
|---|---|
|
|
Real-World Impact
Say you research 20 seed keywords for a new product launch. Manually, you might spend about 5 minutes per seed collecting and pasting suggestions, plus another 30 minutes cleaning duplicates, so call it roughly 2 hours. With this workflow, you drop the 20 seeds into Airtable and trigger runs, then you just review the filled-in results. Even if you spend 20–30 minutes doing final human judgment (which you should), you still get about 1–2 hours back each time you run keyword discovery.
Requirements
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Airtable to store seed keywords and results.
- Amazon Suggest (completion API) to generate keyword ideas from Amazon.
- Airtable API key/token (get it from Airtable account settings).
Skill level: Beginner. You’ll connect Airtable, paste the right IDs/fields, and run a test keyword.
Need help implementing this? Talk to an automation expert (free 15-minute consultation).
The Workflow Flow
A keyword request comes in. The workflow is triggered by an incoming webhook, which acts like the “start” button when you want to fetch suggestions for a specific Airtable record.
Your seed keyword is pulled from Airtable. n8n retrieves the record so it knows exactly which product/seed term to process, and where the results should be written back.
Amazon Suggest is queried and cleaned up. n8n sends the keyword to Amazon’s completion API using an HTTP request, splits the returned suggestion list into individual keywords, then normalizes each item so you don’t get duplicates caused by formatting.
Results are aggregated and saved. The workflow merges the cleaned items, builds a tidy keyword string, then updates the same Airtable row so your suggestions are stored next to the original seed keyword.
You can easily modify the Amazon Suggest endpoint (or the formatting rules) to capture more data, change locales, or store each suggestion as its own row instead of a single field. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Webhook Trigger
Set up the entry point that receives the keyword request and starts the workflow.
- Add and open Incoming Keyword Hook.
- Set the Path to
e1df17af-e8b8-4261-ba45-aba7106c65bd. - Set Response Mode to
lastNodeso the final output is returned to the caller. - Save the node and copy the generated webhook URL for testing.
q (e.g., ?q=rec123) because Retrieve Airtable Record uses {{$json.query.q}}.Step 2: Connect Airtable and Fetch the Keyword Record
Retrieve the Airtable row that contains the seed keyword used for suggestions.
- Add and open Retrieve Airtable Record.
- Credential Required: Connect your
airtableTokenApicredentials. - Set Base to your Airtable base (replace
[YOUR_ID]). - Set Table to your Airtable table (replace
[YOUR_ID]). - Set Record ID to
={{ $json.query.q }}.
q, Retrieve Airtable Record won’t find a row and the rest of the workflow will return empty results.Step 3: Call Amazon Suggest and Normalize Results
Use the retrieved keyword to fetch suggestions from Amazon and prepare each suggestion for aggregation.
- Add and open Amazon Suggest API Call.
- Set URL to
=https://completion.amazon.com/api/2017/suggestions?mid=ATVPDKIKX0DER&alias=aps&prefix={{ $json.Keyword }}. - Add and open Split Suggestion List, then set Field to Split Out to
suggestions. - Add and open Normalize Keyword Items, then set Keywords (array) to
={{ $json.value }}.
Step 4: Aggregate and Format Keywords
Combine the normalized suggestions into a single, comma-separated string.
- Add and open Aggregate Keyword List and set Fields to Aggregate to include Keywords.
- Add and open Build Keyword String and set JavaScript Code to
return [{\n json: {\n keywords: items[0].json.Keywords.join(", ")\n }\n}];.
Step 5: Configure the Airtable Update Output
Write the final keyword string back to the original Airtable row.
- Add and open Update Airtable Row.
- Credential Required: Connect your
airtableTokenApicredentials. - Set Operation to
update. - Set Base and Table to match Retrieve Airtable Record (replace
[YOUR_ID]values). - In Columns, set id to
={{ $('Retrieve Airtable Record').item.json.id }}. - Set Keyword output to
={{ $json.keywords }}.
Keyword output to match the mapping used by Update Airtable Row.Step 6: Test and Activate Your Workflow
Validate the flow end-to-end and then enable it for production.
- Click Execute Workflow and trigger Incoming Keyword Hook with a test URL containing
?q=RECORD_ID. - Confirm that Amazon Suggest API Call returns a
suggestionsarray and that Build Keyword String outputs akeywordsstring. - Verify the Airtable row is updated in Update Airtable Row under the Keyword output field.
- Toggle the workflow to Active to start receiving live webhook requests.
Watch Out For
- Airtable credentials can expire or need specific permissions. If things break, check the Airtable token scopes and the base/table access first.
- If Amazon returns an empty or short suggestion list, downstream aggregation can look “broken” even though the API responded. Test a few seed keywords, including broader ones, before you assume the workflow failed.
- Normalization rules matter more than people expect. If your Set (Edit Fields) step trims too aggressively, you can accidentally collapse distinct keywords into one, so spot-check the first few runs.
Common Questions
About 30 minutes if your Airtable base is ready.
Yes, but you’ll want someone comfortable with API tokens and field mapping. No coding is required for the default setup.
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 Airtable costs if you’re on a paid plan.
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.
You can change what Amazon returns by editing the Amazon Completion API URL in the HTTP Request step (for example, switching marketplace/locale parameters). If you prefer one keyword per row, adjust the Split Suggestion List and Update Airtable Row logic so each suggestion is inserted into a linked table instead of being aggregated. Many teams also tweak Normalize Keyword Items to enforce lowercase, trim extra spaces, and remove odd characters that cause duplicates. If you want a “final approved list,” add a checkbox field and only aggregate items marked approved.
Usually it’s an expired token or the token doesn’t have access to the base you’re updating. Update the Airtable credential in n8n, then confirm the base/table IDs and that the record still exists. If it fails only sometimes, you may be hitting Airtable rate limits during big batches.
If you self-host n8n, there’s no fixed execution limit (it depends on your server and Airtable limits). On n8n Cloud, capacity depends on your plan, but this workflow is lightweight and typically handles keyword batches comfortably as long as you pace requests to Airtable and Amazon.
Often, yes, because this flow benefits from cleaning, splitting, and aggregating data in one run. n8n makes that kind of logic easier to maintain, and self-hosting means you won’t pay more just because you ran a big keyword batch. Zapier and Make can still do it, but you’ll usually stitch together more steps to normalize and dedupe properly. If your team only needs a simple “send keyword, get response, paste it somewhere,” those tools can be fine. If you want it done cleanly and repeatably, n8n is a better fit. Talk to an automation expert if you’re not sure which fits.
Once this is running, keyword collection becomes a background task instead of a calendar event. You keep the human judgment, and the workflow does the tedious part.
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.
