# Generate cited web research reports with SerpAPI and Claude: n8n workflow

> Started by another system calling it, and works across Google Docs, Postgres and Slack. It hands the judgement calls to Claude.

Source: https://millionrounds.com/workflow/generate-cited-web-research-reports-with-serpapi-and-claude (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)

# Generate cited web research reports with SerpAPI and Claude

Started by another system calling it, and works across Google Docs, Postgres and Slack. It hands the judgement calls to Claude. 19 steps, 1 branch: a working afternoon to understand properly.

Medium Calls a model: Claude

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgenerate-cited-web-research-reports-with-serpapi-and-claude)

**19 steps** Medium: a working afternoon

**1** Branch: places the flow splits

**0** Loops or waits

**3** Services it connects to

## The flow

Starts it 1 Model 8 Logic 5 Service 5

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

- 1 **When Research Pipeline Webhook Received** Webhook *Starts it*
- 2 **Claude Model for Planning** Lm Chat Anthropic *Model*
- 3 **Parse Planner Output** Output Parser Structured *Model*
- 4 **Claude Model for Synthesis** Lm Chat Anthropic *Model*
- 5 **Claude Model for Confidence Scoring** Lm Chat Anthropic *Model*
- 6 **Parse Scorer Output** Output Parser Structured *Model*
- 7 **Set Research Workflow Parameters** Set *Logic*
- 8 **Planner AI Agent** Agent *Model*
- 9 **Synthesis AI Agent** Agent *Model*
- 10 **Confidence Scoring Agent** Agent *Model*
- 11 **Extract Sub-Questions for Research** Set *Logic*
- 12 **Check Confidence Threshold** If *Logic*
- 13 **Split Sub-Questions for Parallel Processing** Code *Logic*
- 14 **Create Research Report in Google Docs** Google Docs *Service*
- 15 **Fetch Search Results from SerpAPI** Http Request *Service*
- 16 **Notify Slack - High Confidence Research** Slack *Service*
- 17 **Notify Slack - Low Confidence Research** Slack *Service*
- 18 **Combine Search Results for Synthesis** Aggregate *Logic*
- 19 **Store Research Run in Database** Postgres *Service*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 19, with 1 branch
- **Size:** Medium: a working afternoon
- **Connects to:** Google Docs, Postgres, Slack
- **Model:** Claude

## Questions

What does it need to run?

An n8n account, plus your own Google Docs, Postgres and Slack accounts, and a key for Claude. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls Claude. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 19 steps is enough that you should read each one before running it.

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 19 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%2Fgenerate-cited-web-research-reports-with-serpapi-and-claude)
- **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.

## Connects to

Each opens the other workflows that use it.

[Google Docs](https://millionrounds.com/workflows?service=Google+Docs#library)[Postgres](https://millionrounds.com/workflows?service=Postgres#library)[Slack](https://millionrounds.com/workflows?service=Slack#library)

## Workflows like it

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

- [**Automate actuarial premium adjustments and claims reporting** 19 steps · calls a model · Gmail, Slack](https://millionrounds.com/workflow/automate-actuarial-premium-adjustments-and-claims-reporting)
- [**Gold market prediction system with Perplexity Sonar-Pro** 19 steps · calls a model · Email, Slack](https://millionrounds.com/workflow/gold-market-prediction-system-with-perplexity-sonar-pro)
- [**Track commodity news sentiment with Groq and Google Sheets** 19 steps · calls a model · Google Sheets, RSS](https://millionrounds.com/workflow/track-commodity-news-sentiment-with-groq-and-google-sheets)
- [**Generate Real Estate Research Reports with Exa AI and PandaDoc** 19 steps · Google Sheets, Slack](https://millionrounds.com/workflow/generate-real-estate-research-reports-with-exa-ai-and-pandad)
- [**AI research paper analysis & documentation with Decodo** 20 steps · calls a model · Google Docs, Google Sheets](https://millionrounds.com/workflow/ai-research-paper-analysis-and-documentation-with-decodo)
- [**Analyse GitHub PRs for vulnerabilities with OpenAI and Slack** 18 steps · calls a model · GitHub, Slack](https://millionrounds.com/workflow/analyse-github-prs-for-vulnerabilities-with-openai-and-slack)