> For the complete documentation index, see [llms.txt](https://docs.chord.co/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.chord.co/get-started/how-chord-works.md).

# How Chord works

Chord collects transactional and behavioral data from your store and other systems, brings it into a single source of truth, and models it so your team can analyze it and act on it.

![A diagram of Chord's data infrastructure: Source, Ingest, Centralize, Organize, Analyze, with testing and monitoring across every stage](https://2938842758-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F5Oy2IAsu7IvAGAlWgC36%2Fuploads%2Fgit-blob-f05c49d3cfa02180dcce4617e3a82da095c27d2e%2Fdata-infrastructure.png?alt=media)

## The stages

| Stage      | What happens                                                                      | Where to read more                                                                                           |
| ---------- | --------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
| Source     | Data comes from Chord OMS, third-party integrations and your site's front end.    | [Collect data overview](/collect-data/overview.md), [Connect sources overview](/connect-sources/overview.md) |
| Ingest     | Chord CDP receives events and data from every source.                             | [Collect data overview](/collect-data/overview.md)                                                           |
| Centralize | Everything lands in a data warehouse.                                             |                                                                                                              |
| Organize   | Data models turn raw data into consistent, trusted tables.                        | [Commerce data models](/model-your-data/commerce-data-models.md)                                             |
| Analyze    | Your team works with the data in Chord Analytics, in reporting tools or with SQL. | [Analytics](/analyze-with-dashboards/analytics.md)                                                           |

Testing and monitoring run across every stage.

## Actionable data

Transactional data and behavioral event data sit side by side in one place, which gives you a complete view of each customer. Curated dashboards and customizable explores make it easier to work with data across channels.

## Data integrations

Chord's integration platform sends your OMS and customer data to the third-party tools you use, when you need it there. The same events also feed Chord's analytics. See [Event streaming destinations](/activate/event-streaming/destinations.md) and [Data activations](/activate/data-activations.md).


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.chord.co/get-started/how-chord-works.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.