January 22, 2026

Decodo + Google Sheets, Amazon product research ready

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

Copying Amazon product details into a sheet sounds simple until you do it for the fifth product in a row. Tabs everywhere. Specs in one spot, ads in another, and you still have to write a summary that actually makes sense.

This Amazon research automation hits e-commerce researchers first, but agency analysts and marketplace sellers feel it too. You get clean, structured rows in Google Sheets, plus AI-written summaries and competitive positioning notes without the manual grind.

Below, you’ll see how the workflow pulls an Amazon URL, scrapes the important parts with Decodo, asks OpenAI to turn it into analysis, then writes everything into a sheet you can compare and report from.

How This Automation Works

The full n8n workflow, from trigger to final output:

n8n Workflow Template: Decodo + Google Sheets, Amazon product research ready

Click to explore

flowchart LR

    subgraph sg0["When clicking ‘Execute workflow’ Flow"]
        direction LR
        n0@{ icon: "mdi:play-circle", form: "rounded", label: "When clicking ‘Execute workf..", pos: "b", h: 48 }
        n1@{ icon: "mdi:swap-vertical", form: "rounded", label: "Set the Input Fields", pos: "b", h: 48 }
        n2@{ icon: "mdi:cog", form: "rounded", label: "Decodo Web scrape for Amazon..", pos: "b", h: 48 }
        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/code.svg' width='40' height='40' /></div><br/>Extract Product Details"]
        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/>Extract Ads"]
        n5@{ icon: "mdi:brain", form: "rounded", label: "OpenAI Chat Model", pos: "b", h: 48 }
        n6@{ icon: "mdi:robot", form: "rounded", label: "Structured Output Parser", pos: "b", h: 48 }
        n7@{ icon: "mdi:brain", form: "rounded", label: "OpenAI Chat Model for Amazon..", pos: "b", h: 48 }
        n8@{ icon: "mdi:robot", form: "rounded", label: "Product Insights", pos: "b", h: 48 }
        n9@{ icon: "mdi:robot", form: "rounded", label: "Product Descriptive Summarizer", pos: "b", h: 48 }
        n10@{ icon: "mdi:robot", form: "rounded", label: "Competitive Analysis", pos: "b", h: 48 }
        n11@{ icon: "mdi:brain", form: "rounded", label: "OpenAI Chat Model for Compet..", pos: "b", h: 48 }
        n12@{ icon: "mdi:database", form: "rounded", label: "Append or update row in sheet", 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/merge.svg' width='40' height='40' /></div><br/>Merge"]
        n14@{ icon: "mdi:cog", form: "rounded", label: "Aggregate", pos: "b", h: 48 }
        n13 --> n14
        n14 --> n12
        n4 --> n8
        n8 --> n13
        n5 -.-> n9
        n10 --> n13
        n1 --> n2
        n3 --> n9
        n3 --> n10
        n6 -.-> n9
        n9 --> n13
        n0 --> n1
        n2 --> n3
        n2 --> n4
        n11 -.-> n10
        n7 -.-> n8
    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 n6,n8,n9,n10 ai
    class n5,n7,n11 aiModel
    class n12 database
    class n3,n4 code
    classDef customIcon fill:none,stroke:none
    class n3,n4,n13 customIcon

The Problem: Amazon product research doesn’t scale

If you only evaluate one product a month, manual research is annoying but survivable. The moment you’re comparing ten options for a category page, a pricing test, or a client pitch, it turns into a time sink. You have to grab titles, specs, key features, pricing, and sometimes ad placements, then squeeze it into a spreadsheet format that’s consistent enough to filter. And the worst part is the mental context switching: scrape, paste, re-check, rewrite, repeat. Mistakes happen quietly, so you notice them later, when your conclusions are already baked into a report.

The friction compounds. Here’s where it breaks down in real work.

You end up reformatting every row because Amazon pages don’t present data consistently.
Ads and placements get ignored because capturing them manually is a chore, which means your “analysis” misses competitive signals.
Two people can research the same product and still produce different notes, so comparisons become subjective.
After a few products, fatigue sets in and small copy-paste errors sneak into pricing, model numbers, or feature lists.

The Solution: Decodo scraping + OpenAI analysis into Google Sheets

This workflow turns an Amazon product URL into a structured research entry you can actually use. It starts by taking a product link you set in n8n (or pass in through a trigger), then Decodo scrapes the page for product details and ad listings. Next, the workflow parses that raw scrape into clean fields, then hands those fields to OpenAI to generate a narrative summary and competitive positioning insights. Finally, everything gets merged, grouped, and written into a Google Sheets row so your team has one consistent place to track products. You stop “collecting data” and start comparing it.

The workflow kicks off when you run it in n8n and provide a product URL. Decodo collects the page content, code nodes extract the parts you care about, and OpenAI turns it into readable analysis plus structured fields. Google Sheets becomes the system of record.

What You Get: Automation vs. Results

What This Workflow Automates

Results You’ll Get

Scrapes Amazon product pages with Decodo using the URL you provide.
Extracts product specs, feature bullets, and supplemental metadata into consistent fields.
Captures ad listing signals so you can see what’s promoted around the product.
Generates AI summaries and competitive positioning notes, then writes it all to Google Sheets.

Most teams get a clean research row in about 5 minutes, not 30+.
Your spreadsheet stays consistent, which makes filtering and comparison reliable.
Fewer “wait, where did that number come from?” moments during reporting.
Better product briefs because summaries aren’t written from scratch every time.
You can review more products per week without hiring extra help.

Example: What This Looks Like

Say you’re evaluating 20 Amazon products for a category comparison post. Manually, you might spend about 15 minutes per product grabbing specs, key features, and pricing, plus another 10 minutes writing a quick summary, so roughly 8 hours total. With this workflow, you paste each URL and let it run; even if you budget about 5 minutes per product to queue, review, and confirm the row, you’re down to around 2 hours. That’s most of a workday back, and the sheet is cleaner too.

What You’ll Need

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Decodo for scraping Amazon product pages.
Google Sheets to store and compare product rows.
OpenAI API key (get it from your OpenAI dashboard).

Skill level: Intermediate. You’ll connect credentials, install a community node for Decodo, and edit one input field (the product URL).

Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).

How It Works

You provide the product URL. The workflow starts from a manual run in n8n (common for research) and uses a “set input” node to store the Amazon link you want to analyze.

Decodo scrapes the page content. The Decodo community node pulls down product details and ad-related data from the page, which is the part that usually takes the most human time and attention.

The raw scrape gets cleaned up and analyzed. Two parsing steps separate item details from ad listings, then OpenAI generates a narrative summary and market positioning insights. Another AI step formats the output into structured fields so you’re not stuck with a blob of text.

Google Sheets becomes your research database. The workflow merges the analysis streams, groups them into one final payload, and updates a row in Google Sheets so you can sort, filter, and compare products quickly.

You can easily modify the insight schema to include things like sentiment, compliance notes, or pricing bands based on your needs. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Manual Trigger

Set up the manual trigger and the initial input so you can run and validate the workflow on demand.

Add the Manual Launch Start node as your trigger.
In Assign Input Parameters, create the field product_url with the value https://www.amazon.in/Sony-DualSense-Controller-Grey-PlayStation/dp/B0BQXZ11B8.
Connect Manual Launch Start → Assign Input Parameters.

⚠️ Common Pitfall: The Decodo Amazon Scrape node uses {{$json.product_url}}. If the field name changes, the scrape will fail.

Step 2: Connect Decodo Amazon Scrape

Configure the Amazon scraper to pull product data and ads for downstream analysis.

Add the Decodo Amazon Scrape node and connect it to Assign Input Parameters.
Set Operation to amazon.
Set URL to {{ $json.product_url }}.
Credential Required: Connect your decodoApi credentials.

Decodo Amazon Scrape outputs to both Parse Item Details and Parse Ad Listings in parallel.

Step 3: Set Up Processing and AI Analysis

Parse the scraped data and run AI models to extract insights, summaries, and competitive positioning.

In Parse Item Details, set JavaScript Code to return $input.first().json.results[0].content.results.product_details.
In Parse Ad Listings, set JavaScript Code to return $input.first().json.results[0].content.results.ads.
Configure Narrative Summary Generator with Text set to Provide me a descriptive summary of the following product details {{ $json.toJsonString() }} and Prompt Type set to define.
Configure Market Position Review with Text set to Analyze the following product details and provide a competitive positioning summary {{ $json.toJsonString() }} and Input Schema set to { "type": "object", "properties": { "competitive_analysis": { "type": "string" } } }.
Configure Product Insight Extractor with Schema Type set to manual and Input Schema set to { "$schema": "http://json-schema.org/draft-07/schema#", "title": "Amazon Product Data Mining Schema", "type": "object", "properties": { "summary": { "type": "object", "properties": { "total_items": { "type": "integer" }, "unique_asins": { "type": "integer" }, "duplicated_asins_with_counts": { "type": "object", "additionalProperties": { "type": "integer" } }, "average_price": { "type": "number" }, "min_price": { "type": "number" }, "max_price": { "type": "number" }, "average_reviews": { "type": "number" } }, "required": [ "total_items", "unique_asins", "duplicated_asins_with_counts", "average_price", "min_price", "max_price", "average_reviews" ] }, "product_insights": { "type": "object", "properties": { "best_value_item": { "type": "object", "properties": { "asin": { "type": "string" }, "price": { "type": "number" }, "reviews": { "type": "integer" } }, "required": ["asin", "price", "reviews"] }, "most_reviewed_item": { "type": "object", "properties": { "asin": { "type": "string" }, "price": { "type": "number" }, "reviews": { "type": "integer" } }, "required": ["asin", "price", "reviews"] }, "price_distribution": { "type": "object", "properties": { "low_price": { "type": "number" }, "high_price": { "type": "number" } }, "required": ["low_price", "high_price"] }, "prime_eligibility_percentage": { "type": "string" }, "rating_insights": { "type": "string" } }, "required": [ "best_value_item", "most_reviewed_item", "price_distribution", "prime_eligibility_percentage", "rating_insights" ] }, "metadata": { "type": "object", "properties": { "type_distribution": { "type": "object", "additionalProperties": { "type": "integer" } }, "location_distribution": { "type": "object", "additionalProperties": { "type": "integer" } }, "image_quality_notes": { "type": "string" } }, "required": [ "type_distribution", "location_distribution", "image_quality_notes" ] }, "recommendations": { "type": "object", "properties": { "remove_duplicates": { "type": "string" }, "pricing_strategy": { "type": "string" }, "listing_quality_improvements": { "type": "string" } }, "required": [ "remove_duplicates", "pricing_strategy", "listing_quality_improvements" ] } }, "required": ["summary", "product_insights", "metadata", "recommendations"] }.
Credential Required: Connect your openAiApi credentials to OpenAI Chat Engine, OpenAI Product Mining Model, and OpenAI Competition Model.

Parse Item Details outputs to both Narrative Summary Generator and Market Position Review in parallel.

Credential Reminder: Structured Result Parser is a sub-node connected to Narrative Summary Generator. Add credentials to OpenAI Chat Engine, not the parser.

Step 4: Configure Output Aggregation and Google Sheets Update

Merge all AI outputs, aggregate them, and write the final payload to your spreadsheet.

Set Combine Streams to Number Inputs 3 to accept the three AI outputs.
In Group Outputs, add Fields to Aggregate with Field to Aggregate set to output.
In Update Sheet Row, set Operation to appendOrUpdate.
In Update Sheet Row, map the column output to {{ $json.output.toJsonString() }}.
Set Document ID to [YOUR_ID] and Sheet Name to gid=0 (Sheet1).
Credential Required: Connect your googleSheetsOAuth2Api credentials.

Combine Streams merges Narrative Summary Generator, Product Insight Extractor, and Market Position Review before Group Outputs sends data to Update Sheet Row.

Step 5: Test and Activate Your Workflow

Validate the workflow end-to-end and then enable it for repeated use.

Click Execute Workflow from Manual Launch Start to run a test.
Confirm that Decodo Amazon Scrape returns data and that Combine Streams receives three inputs.
Verify that Update Sheet Row appends or updates the output column with a JSON string.
Toggle the workflow to Active once the test run succeeds.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Common Gotchas

Decodo credentials can expire or need specific permissions. If things break, check your Decodo dashboard credential status and API limits 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.
Google Sheets writes often fail because the target sheet/tab changed or the OAuth permission was revoked. Open the Google Sheets credential in n8n and re-auth if updates suddenly stop.

Frequently Asked Questions

How long does it take to set up this Amazon research automation automation?

About an hour if you already have your API keys and a Google Sheet ready.

Do I need coding skills to automate Amazon research automation?

No. You’ll mostly connect accounts and edit the product URL input. The parsing and AI steps are already built into the workflow.

Is n8n free to use for this Amazon research 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 API costs (often a few cents per product, depending on prompt size).

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.

Can I customize this Amazon research automation workflow for review and Q&A extraction?

Yes, but you’ll want to change the Decodo scraping request to pull review, FAQ, or Q&A sections (or scrape those pages separately), then extend the “Product Insight Extractor” and “Structured Result Parser” to include the new fields. Common tweaks include adding sentiment, pulling recurring complaints, and separating “spec facts” from “opinion signals.” If you’re publishing comparisons, adding a “best for” field in the narrative summary is also a good move.

Why is my Decodo connection failing in this workflow?

Usually it’s an invalid or expired API key in your Decodo credentials inside n8n. It can also be rate limits, or the Amazon page returning a bot-check that changes what gets scraped, which then causes the parsing nodes to fail because expected fields are missing. Check the Decodo node output first, then re-run the workflow after updating the credential.

How many products can this Amazon research automation automation handle?

A lot, as long as you respect scraping and AI rate limits.

Is this Amazon research automation automation better than using Zapier or Make?

For this use case, n8n is usually the better fit because you’re doing multi-step parsing, merging outputs, and running AI transforms in the same workflow without paying extra for each branch. Self-hosting is also a big deal here since this workflow uses a Decodo community node, and you may want higher volume without worrying about task pricing. Zapier and Make are great for simpler, polished app-to-app automations, but scraping plus structured AI analysis is where they can get awkward fast, frankly. If you want help choosing, Talk to an automation expert.

Once this is running, product research stops being a weekly slog and starts looking like a clean pipeline. You’ll spend your time making decisions, not rebuilding the same spreadsheet row again and again.

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": null,
"meta": {
"instanceId": "460ef260c551132275843d15231509291be14e70e25024de8834db974db98a13",
"templateId": null,
"templateCredsSetupCompleted": null
},
"name": "Automated Product Data Analysis Flow",
"tags": [],
"nodes": [
{
"id": "flowpast-topbar-11131",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
20
],
"parameters": {
"color": 7,
"width": 1800,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "9acc7180-abec-4d04-abd0-2505ec667a80",
"name": "Manual Launch Start",
"type": "n8n-nodes-base.manualTrigger",
"position": [
0,
210
],
"parameters": [],
"typeVersion": 1
},
{
"id": "11b5855c-64a2-48be-9ee7-f4245554c13a",
"name": "Assign Input Parameters",
"type": "n8n-nodes-base.set",
"position": [
230,
250
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "8b6c695f-14f7-4ff9-b40a-90f27414c802",
"name": "product_url",
"type": "string",
"value": "https://www.amazon.in/Sony-DualSense-Controller-Grey-PlayStation/dp/B0BQXZ11B8"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "657db23a-996b-43aa-b3cf-8148e1e6aaa5",
"name": "Decodo Amazon Scrape",
"type": "@decodo/n8n-nodes-decodo.decodo",
"position": [
470,
210
],
"parameters": {
"url": "={{ $json.product_url }}",
"operation": "amazon"
},
"credentials": {
"decodoApi": {
"id": "credential-id",
"name": ""
}
},
"retryOnFail": true,
"typeVersion": 1
},
{
"id": "33ee2b31-cb2e-45a5-8cee-b404ac83faca",
"name": "Parse Item Details",
"type": "n8n-nodes-base.code",
"position": [
710,
300
],
"parameters": {
"jsCode": "return $input.first().json.results[0].content.results.product_details"
},
"typeVersion": 2
},
{
"id": "19bb1c74-3200-437e-abd8-6cd2f76e06f6",
"name": "Parse Ad Listings",
"type": "n8n-nodes-base.code",
"position": [
700,
470
],
"parameters": {
"jsCode": "return $input.first().json.results[0].content.results.ads"
},
"typeVersion": 2
},
{
"id": "5578b6bc-9b76-43f6-a7c4-3f16648a29c1",
"name": "OpenAI Chat Engine",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
940,
120
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": []
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "ecd8d612-ba33-4098-ab15-d42b916606bb",
"name": "Structured Result Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1180,
150
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n\t\"type\": \"object\",\n\t\"properties\": {\n\t\t\"summary\": {\n\t\t\t\"type\": \"string\"\n\t\t}\n\t}\n}"
},
"typeVersion": 1.3
},
{
"id": "1170e95d-5995-4f7f-8abe-4a528b7780d9",
"name": "OpenAI Product Mining Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1010,
790
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": []
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "dddc5c80-7161-4b0e-bc4a-146d207550a7",
"name": "Product Insight Extractor",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
960,
640
],
"parameters": {
"text": "={\n  \"nodes\": [\n    {\n      \"parameters\": {\n        \"promptType\": \"define\",\n        \"text\": \"=Provide me a descriptive summary of the following product details\\n\\n{{ $json.toJsonString() }}\",\n        \"hasOutputParser\": true,\n        \"messages\": {\n          \"messageValues\": [\n            {\n              \"message\": \"You are an expert content analyzer and summary generator\"\n            }\n          ]\n        },\n        \"batching\": {}\n      },\n      \"type\": \"@n8n/n8n-nodes-langchain.chainLlm\",\n      \"typeVersion\": 1.7,\n      \"position\": [\n        400,\n        -192\n      ],\n      \"id\": \"c4c1aeb4-7976-4f02-acec-0a2696b67dd2\",\n      \"name\": \"Core LLM Chain\"\n    },\n    {\n      \"parameters\": {\n        \"model\": {\n          \"__rl\": true,\n          \"mode\": \"list\",\n          \"value\": \"gpt-4.1-mini\"\n        },\n        \"options\": {}\n      },\n      \"type\": \"@n8n/n8n-nodes-langchain.lmChatOpenAi\",\n      \"typeVersion\": 1.2,\n      \"position\": [\n        400,\n        0\n      ],\n      \"id\": \"3d8cece5-0cc7-4689-842b-ff07f936fad1\",\n      \"name\": \"OpenAI Chat Engine\",\n      \"credentials\": {\n        \"openAiApi\": {\n          \"id\": \"[YOUR_ID]\",\n          \"name\": \"\"\n        }\n      }\n    },\n    {\n      \"parameters\": {\n        \"schemaType\": \"manual\",\n        \"inputSchema\": \"{\\n\\t\\\"type\\\": \\\"object\\\",\\n\\t\\\"properties\\\": {\\n\\t\\t\\\"summary\\\": {\\n\\t\\t\\t\\\"type\\\": \\\"string\\\"\\n\\t\\t}\\n\\t}\\n}\"\n      },\n      \"type\": \"@n8n/n8n-nodes-langchain.outputParserStructured\",\n      \"typeVersion\": 1.3,\n      \"position\": [\n        576,\n        0\n      ],\n      \"id\": \"b6a8d561-db1d-47ff-bb86-d6aea419550d\",\n      \"name\": \"Structured Result Parser\"\n    }\n  ],\n  \"connections\": {\n    \"OpenAI Chat Engine\": {\n      \"ai_languageModel\": [\n        [\n          {\n            \"node\": \"Core LLM Chain\",\n            \"type\": \"ai_languageModel\",\n            \"index\": 0\n          }\n        ]\n      ]\n    },\n    \"Structured Result Parser\": {\n      \"ai_outputParser\": [\n        [\n          {\n            \"node\": \"Core LLM Chain\",\n            \"type\": \"ai_outputParser\",\n            \"index\": 0\n          }\n        ]\n      ]\n    }\n  },\n  \"pinData\": {},\n  \"meta\": {\n    \"templateCredsSetupCompleted\": null,\n    \"instanceId\": \"460ef260c551132275843d15231509291be14e70e25024de8834db974db98a13\"\n  }\n}",
"options": [],
"schemaType": "manual",
"inputSchema": "{\n  \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n  \"title\": \"Amazon Product Data Mining Schema\",\n  \"type\": \"object\",\n  \"properties\": {\n    \"summary\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"total_items\": { \"type\": \"integer\" },\n        \"unique_asins\": { \"type\": \"integer\" },\n        \"duplicated_asins_with_counts\": {\n          \"type\": \"object\",\n          \"additionalProperties\": { \"type\": \"integer\" }\n        },\n        \"average_price\": { \"type\": \"number\" },\n        \"min_price\": { \"type\": \"number\" },\n        \"max_price\": { \"type\": \"number\" },\n        \"average_reviews\": { \"type\": \"number\" }\n      },\n      \"required\": [\n        \"total_items\",\n        \"unique_asins\",\n        \"duplicated_asins_with_counts\",\n        \"average_price\",\n        \"min_price\",\n        \"max_price\",\n        \"average_reviews\"\n      ]\n    },\n\n    \"product_insights\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"best_value_item\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"asin\": { \"type\": \"string\" },\n            \"price\": { \"type\": \"number\" },\n            \"reviews\": { \"type\": \"integer\" }\n          },\n          \"required\": [\"asin\", \"price\", \"reviews\"]\n        },\n        \"most_reviewed_item\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"asin\": { \"type\": \"string\" },\n            \"price\": { \"type\": \"number\" },\n            \"reviews\": { \"type\": \"integer\" }\n          },\n          \"required\": [\"asin\", \"price\", \"reviews\"]\n        },\n        \"price_distribution\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"low_price\": { \"type\": \"number\" },\n            \"high_price\": { \"type\": \"number\" }\n          },\n          \"required\": [\"low_price\", \"high_price\"]\n        },\n        \"prime_eligibility_percentage\": { \"type\": \"string\" },\n        \"rating_insights\": { \"type\": \"string\" }\n      },\n      \"required\": [\n        \"best_value_item\",\n        \"most_reviewed_item\",\n        \"price_distribution\",\n        \"prime_eligibility_percentage\",\n        \"rating_insights\"\n      ]\n    },\n\n    \"metadata\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"type_distribution\": {\n          \"type\": \"object\",\n          \"additionalProperties\": { \"type\": \"integer\" }\n        },\n        \"location_distribution\": {\n          \"type\": \"object\",\n          \"additionalProperties\": { \"type\": \"integer\" }\n        },\n        \"image_quality_notes\": { \"type\": \"string\" }\n      },\n      \"required\": [\n        \"type_distribution\",\n        \"location_distribution\",\n        \"image_quality_notes\"\n      ]\n    },\n\n    \"recommendations\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"remove_duplicates\": { \"type\": \"string\" },\n        \"pricing_strategy\": { \"type\": \"string\" },\n        \"listing_quality_improvements\": { \"type\": \"string\" }\n      },\n      \"required\": [\n        \"remove_duplicates\",\n        \"pricing_strategy\",\n        \"listing_quality_improvements\"\n      ]\n    }\n  },\n  \"required\": [\"summary\", \"product_insights\", \"metadata\", \"recommendations\"]\n}\n"
},
"retryOnFail": true,
"typeVersion": 1.2
},
{
"id": "a09fa319-7cae-4c50-8082-896fb2112634",
"name": "Narrative Summary Generator",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
980,
340
],
"parameters": {
"text": "=Provide me a descriptive summary of the following product details\n\n{{ $json.toJsonString() }}",
"batching": [],
"messages": {
"messageValues": [
{
"message": "You are an expert content analyzer and summary generator"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.7
},
{
"id": "e8492c0a-3fce-4477-b1c6-e5138952026e",
"name": "Market Position Review",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
980,
590
],
"parameters": {
"text": "=Analyze the following product details and provide a competitive positioning summary\\n\\n{{ $json.toJsonString() }}",
"options": [],
"schemaType": "manual",
"inputSchema": "{\n\t\"type\": \"object\",\n\t\"properties\": {\n\t\t\"competitive_analysis\": {\n\t\t\t\"type\": \"string\"\n\t\t}\n\t}\n}"
},
"retryOnFail": true,
"typeVersion": 1.2
},
{
"id": "0ef2f0ba-04da-4553-a81e-1db94d32b09d",
"name": "OpenAI Competition Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
920,
820
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": []
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "2d285795-4baf-4052-8169-9e438e195c0a",
"name": "Update Sheet Row",
"type": "n8n-nodes-base.googleSheets",
"position": [
1700,
560
],
"parameters": {
"columns": {
"value": {
"output": "={{ $json.output.toJsonString() }}"
},
"schema": [
{
"id": "output",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "output",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"output"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "appendOrUpdate",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "Amazon Product Info with Decodo"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.7
},
{
"id": "08bc5f8e-29ec-4cdb-a722-28e3628380eb",
"name": "Combine Streams",
"type": "n8n-nodes-base.merge",
"position": [
1240,
480
],
"parameters": {
"numberInputs": 3
},
"typeVersion": 3.2
},
{
"id": "e53ba49c-aa57-46d3-9355-f9db4935e51f",
"name": "Group Outputs",
"type": "n8n-nodes-base.aggregate",
"position": [
1470,
520
],
"parameters": {
"options": [],
"fieldsToAggregate": {
"fieldToAggregate": [
{
"fieldToAggregate": "output"
}
]
}
},
"typeVersion": 1
}
],
"active": false,
"pinData": [],
"settings": {
"executionOrder": "v1"
},
"versionId": null,
"connections": {
"Combine Streams": {
"main": [
[
{
"node": "Group Outputs",
"type": "main",
"index": 0
}
]
]
},
"Group Outputs": {
"main": [
[
{
"node": "Update Sheet Row",
"type": "main",
"index": 0
}
]
]
},
"Parse Ad Listings": {
"main": [
[
{
"node": "Product Insight Extractor",
"type": "main",
"index": 0
}
]
]
},
"Product Insight Extractor": {
"main": [
[
{
"node": "Combine Streams",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Engine": {
"ai_languageModel": [
[
{
"node": "Narrative Summary Generator",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Market Position Review": {
"main": [
[
{
"node": "Combine Streams",
"type": "main",
"index": 2
}
]
]
},
"Assign Input Parameters": {
"main": [
[
{
"node": "Decodo Amazon Scrape",
"type": "main",
"index": 0
}
]
]
},
"Parse Item Details": {
"main": [
[
{
"node": "Narrative Summary Generator",
"type": "main",
"index": 0
},
{
"node": "Market Position Review",
"type": "main",
"index": 0
}
]
]
},
"Structured Result Parser": {
"ai_outputParser": [
[
{
"node": "Narrative Summary Generator",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Update Sheet Row": {
"main": [
[]
]
},
"Narrative Summary Generator": {
"main": [
[
{
"node": "Combine Streams",
"type": "main",
"index": 1
}
]
]
},
"Manual Launch Start": {
"main": [
[
{
"node": "Assign Input Parameters",
"type": "main",
"index": 0
}
]
]
},
"Decodo Amazon Scrape": {
"main": [
[
{
"node": "Parse Item Details",
"type": "main",
"index": 0
},
{
"node": "Parse Ad Listings",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Competition Model": {
"ai_languageModel": [
[
{
"node": "Market Position Review",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Product Mining Model": {
"ai_languageModel": [
[
{
"node": "Product Insight Extractor",
"type": "ai_languageModel",
"index": 0
}
]
]
}
}
}