Skip to content

docs: add tutorials for using early access AI agent features #17186

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 14 commits into from
Apr 2, 2025
Prev Previous commit
Next Next commit
fmt
  • Loading branch information
bpmct committed Apr 1, 2025
commit d3300d6a96eab0f7d56cb99ce4f0c54350626d44
2 changes: 1 addition & 1 deletion docs/tutorials/ai-agents/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
> staging environment.
>
> Join our [Discord channel](https://discord.gg/coder) or
> [contact us](https://coder.com/contact) to get help or leave feedback.
> [contact us](https://coder.com/contact) to get help or share feedback.

AI Coding Agents such as [Claude Code](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview), [Goose](https://block.github.io/goose/), and [Aider](https://github.com/paul-gauthier/aider) are becoming increasingly popular for:

Expand All @@ -33,4 +33,4 @@

## Table of Contents

<children></chilren>

Check warning on line 36 in docs/tutorials/ai-agents/README.md

View workflow job for this annotation

GitHub Actions / lint

"chilren" should be "children".
2 changes: 1 addition & 1 deletion docs/tutorials/ai-agents/best-practices.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
> staging environment.
>
> Join our [Discord channel](https://discord.gg/coder) or
> [contact us](https://coder.com/contact) to get help or leave feedback.
> [contact us](https://coder.com/contact) to get help or share feedback.

## Overview

Expand Down Expand Up @@ -64,5 +64,5 @@

- [Supervise Agents in the UI](./coder-dashboard.md)
- [Supervise Agents in the IDE](./ide-integration.md)
- [Supervise Agents Programatically](./headless.md)

Check warning on line 67 in docs/tutorials/ai-agents/best-practices.md

View workflow job for this annotation

GitHub Actions / lint

"Programatically" should be "Programmatically".
- [Securing Agents](./securing.md)
2 changes: 1 addition & 1 deletion docs/tutorials/ai-agents/coder-dashboard.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
> staging environment.
>
> Join our [Discord channel](https://discord.gg/coder) or
> [contact us](https://coder.com/contact) to get help or leave feedback.
> [contact us](https://coder.com/contact) to get help or share feedback.

## Prerequisites

Expand All @@ -23,5 +23,5 @@
## Next Steps

- [Supervise Agents in the IDE](./ide-integration.md)
- [Supervise Agents Programatically](./headless.md)

Check warning on line 26 in docs/tutorials/ai-agents/coder-dashboard.md

View workflow job for this annotation

GitHub Actions / lint

"Programatically" should be "Programmatically".
- [Securing Agents](./securing.md)
2 changes: 1 addition & 1 deletion docs/tutorials/ai-agents/create-template.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
> staging environment.
>
> Join our [Discord channel](https://discord.gg/coder) or
> [contact us](https://coder.com/contact) to get help or leave feedback.
> [contact us](https://coder.com/contact) to get help or share feedback.

## Overview

Expand All @@ -22,7 +22,7 @@

## 1. Duplicate an existing template

It is best to create a seperate template for AI agents based on an existing

Check warning on line 25 in docs/tutorials/ai-agents/create-template.md

View workflow job for this annotation

GitHub Actions / lint

"seperate" should be "separate".
template that has all of the tools and dependencies installed.

This can be done in the Coder UI:
Expand Down
2 changes: 1 addition & 1 deletion docs/tutorials/ai-agents/headless.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
> staging environment.
>
> Join our [Discord channel](https://discord.gg/coder) or
> [contact us](https://coder.com/contact) to get help or leave feedback.
> [contact us](https://coder.com/contact) to get help or share feedback.

## Prerequisites

Expand All @@ -15,7 +15,7 @@
## Overview

Once you have an agent running and reporting activity to Coder, you can manage
it programatically via the MCP server, Coder CLI, and/or REST API.

Check warning on line 18 in docs/tutorials/ai-agents/headless.md

View workflow job for this annotation

GitHub Actions / lint

"programatically" should be "programmatically".

## MCP Server

Expand Down
2 changes: 1 addition & 1 deletion docs/tutorials/ai-agents/ide-integration.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
> staging environment.
>
> Join our [Discord channel](https://discord.gg/coder) or
> [contact us](https://coder.com/contact) to get help or leave feedback.
> [contact us](https://coder.com/contact) to get help or share feedback.

## Prerequisites

Expand All @@ -24,5 +24,5 @@

## Next Steps

- [Programatically manage agents](./headless.md)

Check warning on line 27 in docs/tutorials/ai-agents/ide-integration.md

View workflow job for this annotation

GitHub Actions / lint

"Programatically" should be "Programmatically".
- [Securing Agents with Boundaries](./securing.md)
2 changes: 1 addition & 1 deletion docs/tutorials/ai-agents/issue-tracker.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
> staging environment.
>
> Join our [Discord channel](https://discord.gg/coder) or
> [contact us](https://coder.com/contact) to get help or leave feedback.
> [contact us](https://coder.com/contact) to get help or share feedback.

## Overview

Expand Down Expand Up @@ -55,5 +55,5 @@
- [Best practices & adding tools via MCP](./best-practices.md)
- [Supervise Agents in the UI](./coder-dashboard.md)
- [Supervise Agents in the IDE](./ide-integration.md)
- [Supervise Agents Programatically](./headless.md)

Check warning on line 58 in docs/tutorials/ai-agents/issue-tracker.md

View workflow job for this annotation

GitHub Actions / lint

"Programatically" should be "Programmatically".
- [Securing Agents with Boundaries](./securing.md)
2 changes: 1 addition & 1 deletion docs/tutorials/ai-agents/securing.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
> staging environment.
>
> Join our [Discord channel](https://discord.gg/coder) or
> [contact us](https://coder.com/contact) to get help or leave feedback.
> [contact us](https://coder.com/contact) to get help or share feedback.

As the AI landscape is evolving, we are working to ensure Coder remains a secure
platform for running AI agents just as it is for other cloud development
Expand All @@ -24,7 +24,7 @@
threats or bad actors. These same protections can be used to ensure AI agents do
not access or upload sensitive information.

## Seperate API keys and scopes for agents

Check warning on line 27 in docs/tutorials/ai-agents/securing.md

View workflow job for this annotation

GitHub Actions / lint

"Seperate" should be "Separate".

Many agents require API keys to access external services. It is recommended to
create a separate API key for your agent with the minimum permissions required.
Expand All @@ -38,7 +38,7 @@

Agent Boundaries add an additional layer and isolation of security between the
agent and the rest of the environment inside of your Coder workspace, allowing
humans to have more priviledges and access compared to agents inside the same

Check warning on line 41 in docs/tutorials/ai-agents/securing.md

View workflow job for this annotation

GitHub Actions / lint

"priviledges" should be "privileges".
workspace.

Trial agent boundaries in your workspaces by following the instructions in the
Expand Down
Loading