# AI-powered product research & comparison with SerpAPI: n8n workflow

> Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/ai-powered-product-research-and-comparison-with-serpapi (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Research and reporting](https://millionrounds.com/workflows?category=Research+and+reporting#library)

# AI-powered product research & comparison with SerpAPI

Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 25 steps: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fai-powered-product-research-and-comparison-with-serpapi)

**25 steps** Large: read it before trusting it with anything live

**0** Branches: places the flow splits

**0** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 1 Model 22 Logic 2

The steps in the order they run, from what starts it.

- 1 **When chat message received** Chat trigger *Starts it*
- 2 **OpenAI Chat Model1** Lm Chat Open Ai *Model*
- 3 **Window Buffer Memory1** Memory Buffer Window *Model*
- 4 **SerpAPI1** Tool Serp Api *Model*
- 5 **Structured Output Parser** Output Parser Structured *Model*
- 6 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 7 **SerpAPI** Tool Serp Api *Model*
- 8 **SerpAPI3** Tool Serp Api *Model*
- 9 **SerpAPI4** Tool Serp Api *Model*
- 10 **SerpAPI5** Tool Serp Api *Model*
- 11 **OpenAI Chat Model2** Lm Chat Open Ai *Model*
- 12 **SerpAPI2** Tool Serp Api *Model*
- 13 **OpenAI Chat Model3** Lm Chat Open Ai *Model*
- 14 **OpenAI Chat Model4** Lm Chat Open Ai *Model*
- 15 **OpenAI Chat Model5** Lm Chat Open Ai *Model*
- 16 **OpenAI Chat Model6** Lm Chat Open Ai *Model*
- 17 **Item Finder** Agent *Model*
- 18 **Compiler** Agent *Model*
- 19 **Reviewer 1** Agent *Model*
- 20 **Reviewer 3** Agent *Model*
- 21 **Reviewer 4** Agent *Model*
- 22 **Reviewer 5** Agent *Model*
- 23 **Reviewer 2** Agent *Model*
- 24 **Merge1** Merge *Logic*
- 25 **Aggregate1** Aggregate *Logic*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 25
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 25 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 25 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fai-powered-product-research-and-comparison-with-serpapi)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Workflows like it

Also research and reporting, with the same services where possible, closest in size first.

- [**Audit website security and send AI reports with Gmail** 25 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/audit-website-security-and-send-ai-reports-with-gmail)
- [**Automate multi-website Google Analytics reports with OpenAI** 25 steps · calls a model · Email, Gmail](https://millionrounds.com/workflow/automate-multi-website-google-analytics-reports-with-openai)
- [**Collect news from RSS feeds, summarize it and send it out** 25 steps · calls a model · Email, RSS](https://millionrounds.com/workflow/collect-news-from-rss-feeds-summarize-it-and-send-it-out)
- [**Compare multi-period financial data from Google Sheets** 25 steps · calls a model · Google Sheets](https://millionrounds.com/workflow/compare-multi-period-financial-data-from-google-sheets)
- [**Generate multi-period financial reports from Google Sheets** 25 steps · calls a model · Google Sheets](https://millionrounds.com/workflow/generate-multi-period-financial-reports-from-google-sheets)
- [**Log and report construction punch list items with OpenAI** 25 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/log-and-report-construction-punch-list-items-with-openai)