> For the complete documentation index, see [llms.txt](https://docs.jetadmin.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.jetadmin.io/user-guide/integrations/devin.md).

# Devin

Devin is an AI software engineering platform that helps teams automate development tasks, manage coding sessions, generate documentation, and work with project knowledge. By connecting Devin to JetAdmin, you can interact with Devin directly from AI Agents and workflows to streamline engineering operations and access development resources.

## Connecting Devin

To connect your Devin account:

1. Open the **Data** tab from the left sidebar.
2. Click **Add Resource**.
3. Select **Devin** from the list of available resources.
4. Authenticate your Devin account.

{% @arcade/embed flowId="8QQ8Ynuc5QZgxFbhdhqp" url="<https://app.arcade.software/share/8QQ8Ynuc5QZgxFbhdhqp>" %}

{% hint style="info" %}
Once connected, the Devin resource becomes available anywhere JetAdmin supports Data resources.
{% endhint %}

## What can it do?

The Devin integration gives JetAdmin access to your Devin workspace and engineering tools.

From JetAdmin, you can:

* Ask questions about your projects and codebase
* Create and manage Devin coding sessions
* Manage automations, schedules, and playbooks
* Access project knowledge and generated documentation
* Generate and read project wikis
* Browse connected repositories and integrations
* Use Devin capabilities inside AI Agents and workflows

## Where to use it?

Devin is most useful whenever your application needs **software engineering automation**, **project knowledge**, or **developer assistance**.

You can use it in:

| JetAdmin feature   | Common use cases                                                                                     |
| ------------------ | ---------------------------------------------------------------------------------------------------- |
| **AI Agents**      | Answer engineering questions, explore codebases, summarize repositories, assist developers           |
| **Workflows**      | Automate development tasks, manage Devin sessions, generate documentation, schedule engineering jobs |
| **Internal tools** | Build engineering dashboards, project assistants, documentation portals, or developer support tools  |

Typical business use cases include:

* Engineering support
* Codebase exploration
* Developer onboarding
* Documentation generation
* Repository management
* Software project automation
* Internal developer assistants

## Available tools (Actions)

| Action                          | Description                                                                      |
| ------------------------------- | -------------------------------------------------------------------------------- |
| **Ask Question**                | Ask Devin questions about your projects, repositories, or engineering knowledge. |
| **Devin Automation**            | Create and manage automation workflows in Devin.                                 |
| **Devin Code Scan**             | Manage code scanning and analysis tasks.                                         |
| **Devin Knowledge**             | Access and manage Devin's project knowledge.                                     |
| **Devin Playbook**              | Manage reusable engineering playbooks.                                           |
| **Devin Schedule**              | Create and manage scheduled Devin tasks.                                         |
| **Devin Sessions**              | Create, search, interact with, and retrieve events from Devin coding sessions.   |
| **Find Setting**                | Retrieve configuration settings from your Devin workspace.                       |
| **Generate Wiki**               | Generate project documentation and wiki content automatically.                   |
| **List Available Repositories** | Retrieve repositories connected to your Devin workspace.                         |
| **List Integrations**           | List connected integrations available in Devin.                                  |
| **Read Wiki Contents**          | Retrieve the contents of a generated project wiki.                               |
| **Read Wiki Structure**         | Retrieve the structure and organization of a project wiki.                       |

## Example prompts for AI Agents

#### Ask about a project

```
Ask Devin to explain how authentication is implemented in our backend project.
```

#### Start a development session

```
Create a new Devin session to investigate a performance issue in the API service.
```

#### Generate project documentation

```
Generate a wiki for the selected repository and summarize the project architecture.
```

#### Explore a repository

```
List all repositories connected to Devin and summarize the purpose of each one.
```

#### Review project knowledge

```
Search Devin Knowledge for deployment documentation related to Kubernetes.
```

#### Check engineering automations

```
List all configured Devin automations and explain what each one does.
```

## Example

This example demonstrates how an AI Agent can generate developer documentation from a codebase using Devin.

{% @arcade/embed flowId="H53kqOjbjVxzs4PdLsuB" url="<https://app.arcade.software/share/H53kqOjbjVxzs4PdLsuB>" %}


---

# 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://docs.jetadmin.io/user-guide/integrations/devin.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.