> For the complete documentation index, see [llms.txt](https://handbook.n8n.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://handbook.n8n.io/start-here/how-we-work.md).

# How we work

![](https://1295977995-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FikYvt5xWzvK7NtuHBUPD%2Fuploads%2Fgit-blob-a77352a2672425017b78a7d49d20392247053697%2Fhow-we-work-editorial.png?alt=media)

These principles guide how we make decisions, work with other teams, and deliver automations.

## Our beliefs

Our work is guided by five core tenets:

1. **Understand before you automate.** Map the process, challenge assumptions, and define what done looks like before building.
2. **Choose the right tool for the problem.** Make deliberate tradeoffs between deterministic workflows, AI, existing products, and custom solutions.
3. **Build like it has to last.** Treat every workflow as a product with ownership, documentation, error handling, monitoring, and a handover plan.
4. **Responsible automation is the only kind worth building.** Design for compliance, data integrity, auditability, appropriate access, and sustainable cost from the start.
5. **The future of work is built by everyone.** Help teams learn to build and maintain their own automations. Provide reusable patterns and support local champions instead of relying only on central delivery.

## What we do and don't do

Clear boundaries help the Automation team focus on work where it can contribute the most value.

### What we do

We:

* Help teams understand and improve a process before automating it.
* Evaluate opportunities based on business impact, strategic alignment, process readiness, durability, and likely adoption.
* Design and build cross-functional or technically demanding automations.
* Establish standards for quality, documentation, ownership, monitoring, and responsible AI use.
* Build reusable patterns and shared infrastructure when they reduce repeated effort.
* Work with system owners when an automation affects their data, tools, or policies.
* Help teams learn by building with them.
* Design and deliver enablement programs and workshops built around what a specific function actually needs.
* Work with functional leaders to identify where AI and automation can improve their team's work, not only the problem directly in front of us.
* Document lessons, including approaches that did not work.

### What we do not do

We do not:

* Accept work solely because it arrived first or has a vocal requester.
* Automate a process that nobody can explain or own.
* Treat a requested implementation as the only possible solution.
* Implement a new solution when existing tool solves the problem better.
* Take permanent ownership of another team's business process by default.
* Treat documentation, monitoring, handover, or maintenance as optional cleanup work.
* Commit to large, unplanned rebuilds because the original owner is no longer available.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://handbook.n8n.io/start-here/how-we-work.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.