# Optimize technical manuals for RAG & agents: n8n workflow

> Started by a clock, and works across Google Drive and S3. 21 steps, 1 branch, 3 loops or waits: large, and worth reading before you trust it with anything live.

Source: https://millionrounds.com/workflow/optimize-technical-manuals-for-rag-and-agents (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Integrations](https://millionrounds.com/workflows?category=Integrations#library)

# Optimize technical manuals for RAG & agents

Started by a clock, and works across Google Drive and S3. 21 steps, 1 branch, 3 loops or waits: large, and worth reading before you trust it with anything live.

Large

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Foptimize-technical-manuals-for-rag-and-agents)

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

**1** Branch: places the flow splits

**3** Loops or waits

**2** Services it connects to

## The flow

Starts it 1 Logic 11 Service 9

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

- 1 **Schedule Trigger2** Schedule trigger *Starts it*
- 2 **Search files and folders** Google Drive *Service*
- 3 **Loop over Documents to Blockify** Split In Batches *Logic*
- 4 **Download Document to Blockify** Google Drive *Service*
- 5 **Upload a Document to S3** Aws S3 *Service*
- 6 **Get AWS Signed URL** Code *Logic*
- 7 **Initiate PDF Extraction** Http Request *Service*
- 8 **PDF Status Polling** Http Request *Service*
- 9 **Wait** Wait *Logic*
- 10 **If Completed Poller** If *Logic*
- 11 **Download Final PDF Extracted Text Output** Http Request *Service*
- 12 **Extract Raw Markdown from PDF Text** Set *Logic*
- 13 **Technical Manual Split Chunks** Code *Logic*
- 14 **Technical Manual Prompt Payload Assembly** Code *Logic*
- 15 **Loop Over Chunks for Blockify** Split In Batches *Logic*
- 16 **Aggregate all Manual Sections** Aggregate *Logic*
- 17 **Blockify Technical Ingest API** Http Request *Service*
- 18 **Strip and Clean to Aggregate XML** Set *Logic*
- 19 **Extract IdeaBlocks from API Response** Set *Logic*
- 20 **Convert to File** Convert To File *Service*
- 21 **Upload Blockified Manual** Google Drive *Service*

## How it's built

- **Starts on:** A clock
- **Steps:** 21, with 1 branch, 3 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Google Drive, S3
- **Model:** None. This is plumbing, not judgement

## Questions

What does it need to run?

An n8n account, plus your own Google Drive and S3 accounts. You connect your own accounts after importing it; none are included.

What starts it?

It starts on a clock.

Does it use AI?

No. Every step is fixed logic or a call to a service, so it does the same thing every time.

How long does it take to set up?

Take your time. At 21 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 21 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%2Foptimize-technical-manuals-for-rag-and-agents)
- **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 Drive](https://millionrounds.com/workflows?service=Google+Drive#library)[S3](https://millionrounds.com/workflows?service=S3#library)

## Workflows like it

Also integrations, with the same services where possible, closest in size first.

- [**Back up workflows from multiple n8n instances to Google Drive** 21 steps · Google Drive](https://millionrounds.com/workflow/back-up-workflows-from-multiple-n8n-instances-to-google-driv)
- [**Back up Linux server directories to Google Drive with Borg** 20 steps · Google Drive, n8n data table](https://millionrounds.com/workflow/back-up-linux-server-directories-to-google-drive-with-borg)
- [**Back up self-hosted workflows to Google Drive daily** 18 steps · Google Drive, n8n data table](https://millionrounds.com/workflow/back-up-self-hosted-workflows-to-google-drive-daily)
- [**Employee Birthday & Work Anniversary Wishes Automation** 25 steps · Gmail, Google Drive](https://millionrounds.com/workflow/employee-birthday-and-work-anniversary-wishes-automation)
- [**Generate Tailwind landing pages from form input with Gemini** 16 steps · Google Drive](https://millionrounds.com/workflow/generate-tailwind-landing-pages-from-form-input-with-gemini)
- [**Search your travel memories with Gmail and Google Photos** 16 steps · Google Drive](https://millionrounds.com/workflow/search-your-travel-memories-with-gmail-and-google-photos)