> For the complete documentation index, see [llms.txt](https://help.newtone.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.newtone.ai/documentation/getting-started/how-a-project-runs.md).

# How a project runs

The phases of a Newtone engagement, who is responsible for what, and what we need from your team.

A Newtone engagement is configuration-led. The platform is set up for your brand before your team operates it, which is why the first weeks look different from a typical software rollout.

## The phases

**1. Scoping.** We agree which content types, markets and languages are in scope, and where your product data lives. The output is a definition of what "done" looks like for the first production run.

**2. Configuration.** The Newtone team encodes your brand: voice, terminology, do-not-translate lists, mandatory and forbidden wording, output formats, and any market-specific rules. We work from your existing brand guidelines, your published content and a working session with your team. You review the result rather than build it.

**3. Validation.** We run a representative sample through the configured system and your team reviews it. Corrections at this stage feed back into the configuration, not just into the individual items. This loop repeats until the output is signed off as publishable.

**4. Production.** Your team runs generation and translation at volume, through the app, a scheduled workflow or the API. Review is exception handling at this point.

**5. Expansion.** Additional languages, markets or content types reuse the same configuration. Adding a content type is usually a smaller step than the first one.

> The exact timeline depends on the concrete scope, but typically our clients are up and running within 2-4 weeks. 

## Who does what

| Activity                                       | Your team | Newtone team | Platform           |
| ---------------------------------------------- | --------- | ------------ | ------------------ |
| Define scope, markets, languages               | Owns      | Advises      | —                  |
| Provide brand guidelines and reference content | Owns      | —            | —                  |
| Connect the data source                        | Shared    | Shared       | —                  |
| Encode voice, terminology and rules            | Reviews   | Owns         | Stores and applies |
| Validate sample output                         | Owns      | Advises      | —                  |
| Run generation and translation                 | Owns      | —            | Executes           |
| Review and approve content                     | Owns      | —            | Tracks states      |
| Publish back to source system                  | Approves  | —            | Executes           |
| Adjust configuration over time                 | Requests  | Owns         | Applies            |

## What we need from you

* Access to the system holding your product data, or an export in an agreed format
* Your brand and tone-of-voice guidelines, in whatever form they exist
* Examples of published content you consider good, and examples you consider wrong
* A named person per market or language who can approve output
* A decision on where approved content is written back to

The last two matter more than they look. Projects slow down most often because approval sits with nobody in particular, or because it is unclear which system is authoritative.

## Changing the configuration later

Configuration is not frozen after go-live. Terminology changes, brands reposition, and new markets bring new rules. Raise changes through your Newtone contact; recurring corrections your reviewers make are a signal that the configuration needs updating rather than that the content needs fixing.


---

# 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://help.newtone.ai/documentation/getting-started/how-a-project-runs.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.