> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/build-and-improve/overview/guided-project-setup.md).

# Guided Project setup

Create a Project from a guided process template and complete the setup tasks with the Agent.

Guided setup creates a Project from a process template and gives the Agent a defined setup plan.

## Select a domain and process

The create-Project screen currently groups process templates into six domains:

| Domain                | Scope                                                            |
| --------------------- | ---------------------------------------------------------------- |
| **Quote & Sell**      | Requests, quotations, customer orders and sales-order processing |
| **Procure & Receive** | Purchasing, supplier work and incoming goods                     |
| **Plan & Produce**    | Planning, production preparation and production execution        |
| **Store & Ship**      | Storage, movement, shipping and delivery                         |
| **Pay & Collect**     | Supplier payments and customer collections                       |
| **Support & Enable**  | Support, checks, reporting and operational administration        |

Select the process template that matches the work you want the Project to perform.

**Blank** creates a Project without a guided setup plan. Use it when no current template fits and configure the Project manually.

## Complete the setup tasks

A guided template creates a persistent setup checklist. The Agent works through the tasks and records progress in the Project.

The exact tasks depend on the selected process. A setup can include:

* collecting process-specific rules and constraints;
* adding or creating working data;
* connecting required systems;
* creating and testing Skills;
* creating background Workflows;
* creating review or exception views;
* configuring the Project Overview;
* preparing the Project for live use.

The setup state is stored with the Project, so task progress is retained when you leave and return.

## Use mock data where supported

Some guided templates can be configured on mock data before production systems are connected. This is useful for reviewing the process, Project structure and operator experience before granting production authority.

For example, the Order intake template can build representative customers, article mappings and order rules before a live ERP is connected.

Do not treat mock-data results as production acceptance. Re-test the process after connecting the real systems.

## Review generated components

The Agent can create several Project components during setup. Review the resulting Project state rather than relying on the conversation alone.

Check the relevant items in the Project:

* Skills and their test results;
* Connections and their authority;
* Tables, Files and Knowledge;
* Workflows and publish state;
* operator or review views;
* Overview content;
* Monitoring;
* remaining approval or human-decision boundaries.

## Publish and go live

Publishing a Skill or Workflow changes the maintained Project configuration. Review the generated component and its tests before approving publication.

Before live use, run representative cases with the production Connections and verify the result in the system that owns it.

If a setup template does not match the process boundary, stop using the template as the specification. Configure the Project manually or change the process scope first.


---

# 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.lleverage.ai/build-and-improve/overview/guided-project-setup.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.