From 39ae9812ace79e36114b3fb5b6bf84d6eefb9bef Mon Sep 17 00:00:00 2001 From: David Karlsson <35727626+dvdksn@users.noreply.github.com> Date: Thu, 22 Oct 2026 06:07:36 +0200 Subject: [PATCH 1/6] docs: start DAP getting started with a shell --- .../manuals/agentic-platform/get-started.md | 111 +++++++++--------- 1 file changed, 56 insertions(+), 55 deletions(-) diff --git a/content/manuals/agentic-platform/get-started.md b/content/manuals/agentic-platform/get-started.md index 45ee64d51c51..b067056d1a25 100644 --- a/content/manuals/agentic-platform/get-started.md +++ b/content/manuals/agentic-platform/get-started.md @@ -1,78 +1,79 @@ --- title: Get started with Docker Agentic Platform linkTitle: Get started -description: Run your first cloud sandbox, ask an agent to review a sample project, save the result, and pause or delete the sandbox when you're finished. -keywords: docker agentic platform, get started, cloud sandboxes, agents, ssh, vscode, cursor +description: Start a shell in your first cloud sandbox, explore a sample project, save a file, and pause or delete the sandbox when you're finished. +keywords: docker agentic platform, get started, cloud sandboxes, shell, agents, ssh, vscode, cursor weight: 10 aliases: - /agentic-platform/concepts/platform-model/ --- -Use a cloud sandbox to have an agent review a project without setting up the -project on your computer. In this walkthrough, you'll launch Claude Code, -clone a public sample application, and save a project review. Then you'll -pause the sandbox to return later or delete it when you're finished. +Use a cloud sandbox to work on a project without setting it up on your +computer. In this walkthrough, you'll start a shell, clone a public sample +application, and save a record of its latest commit. Then you'll pause the +sandbox to return later or delete it when you're finished. You can complete the walkthrough in the browser. An optional step shows how to open the same project in VS Code or Cursor over SSH. ## Before you begin -You need: +You need a personal Docker account with an active +[Docker Agentic Platform subscription](signup.md#activate-cloud-access). -- A personal Docker account with an active - [Docker Agentic Platform subscription](signup.md#activate-cloud-access). -- An Anthropic API key for the Claude Code kit. Add it under **Secrets** or - enter it when you launch the sandbox. Your model provider bills inference - separately from Docker's sandbox compute charges. - -This example uses a public repository, so you don't need a GitHub token. -For other agents and their credentials, see [Kits](kits.md) and -[Secrets](secrets.md). +The Shell kit doesn't require a model provider API key. This example uses a +public repository, so you don't need a GitHub token either. For agents and +their credentials, see [Kits](kits.md) and [Secrets](secrets.md). ## Start a sandbox 1. Open [Docker Agentic Platform](https://agentic-platform.docker.com/) and - select **New**. -2. Choose the Claude Code kit. -3. Add your Anthropic API key if it isn't already saved. Don't enter it in - the agent's prompt or in a file inside the sandbox. -4. Keep the defaults and select **Run**. + select **+ New sandbox**. +2. Open the kit picker and choose **shell**. +3. If saved secrets or a GitHub token are selected, deselect them for this + walkthrough. You don't need MCP tools either. +4. In the network policy picker, select **Balanced** to permit access to + GitHub. Keep the compute and timer defaults and select **Run**. -On your first launch, the default **Open** network policy permits outbound -access to any host. If you're using a custom policy, make sure it permits -GitHub and your model provider. See [Network policies](policies.md). +If you use a custom network policy, make sure it permits GitHub. See +[Network policies](policies.md). -When the sandbox is ready, its terminal opens with Claude Code. After launch, +When the sandbox is ready, its terminal opens with a Bash shell. After launch, you can't change the selected credentials, tools, network policies, or compute size. See [Sandbox options](#sandbox-options) for other launch settings. -## Give the agent a task - -Your local files aren't mounted in a cloud sandbox. Ask Claude Code to clone -and review a public sample project: - -```text -Clone https://github.com/docker/welcome-to-docker.git into -/home/agent/workspace/project, then review the application. -Read the source, package.json, and Dockerfile. Don't modify the application -or install dependencies. -Write /home/agent/workspace/review.md with: -- A short explanation of what the application does. -- The commands defined in package.json for running and building it. -- An explanation of how the Dockerfile builds and serves the application. -- One small improvement you'd recommend, with the relevant file path. -Base the review on the files you read. Don't claim to have run the application. -Summarize your findings in your response. +## Explore a project + +Your local files aren't mounted in a cloud sandbox. In the browser terminal, +clone a public sample project: + +```console +$ cd /home/agent/workspace +$ git clone https://github.com/docker/welcome-to-docker.git project +$ cd project +$ ls +``` + +Read the project's package scripts and Dockerfile: + +```console +$ cat package.json +$ cat Dockerfile +``` + +Save a record of the latest commit to a file in the workspace: + +```console +$ git log -1 --oneline > /home/agent/workspace/latest-commit.txt +$ cat /home/agent/workspace/latest-commit.txt ``` -Claude Code summarizes the project in the conversation and saves the review -at `/home/agent/workspace/review.md`. You can ask follow-up questions or give -it another task in the same session. +The output shows the commit's short ID and message. The file stays in the +sandbox so you can open it later or copy it to your computer. ## Keep your work -The cloned project and review are stored in the sandbox. Files don't sync +The cloned project and commit record are stored in the sandbox. Files don't sync automatically with your computer or a remote repository. They remain available when you pause and resume the sandbox, but are lost when you delete it. @@ -84,7 +85,7 @@ needs to push changes. ## Open the project in your editor (optional) -Open the project and review in VS Code or Cursor over SSH. Your editor +Open the project and commit record in VS Code or Cursor over SSH. Your editor runs on your computer, while the files and terminal commands stay in the cloud sandbox. @@ -114,32 +115,32 @@ cloud sandbox. 5. Open your editor's Command Palette and run **Remote-SSH: Connect to Host**. Enter `@sbx_cloud`, using the same ID as in the SSH command. 6. Open `/home/agent/workspace` in the remote window. You'll find the cloned - application in `project` and the agent's output in `review.md`. + application in `project` and the commit record in `latest-commit.txt`. The first connection installs the editor's server inside the sandbox. -To download the review, run this command in a terminal on your computer: +To download the commit record, run this command in a terminal on your computer: ```console -$ sbx --cloud cp :/home/agent/workspace/review.md ./review.md +$ sbx --cloud cp :/home/agent/workspace/latest-commit.txt ./latest-commit.txt ``` ## Pause, keep running, or delete the sandbox Closing the browser or disconnecting your editor leaves the sandbox running. -An agent can continue working until you pause or delete the sandbox, or its -timer expires. Compute is billed while the sandbox runs, even when the agent -has finished its task. +Commands and background processes can continue until you pause or delete the +sandbox, or its timer expires. Compute is billed while the sandbox runs, even +when no commands are running. Return to **Sandboxes** in the Console and choose what to do next: - Pause the sandbox to stop compute charges and keep its files. Confirm that it is paused in the list. To continue later, reopen the sandbox and resume it. Resuming starts a fresh timer with the original duration. -- Leave it running if the agent still has work to do. Check the expiration +- Leave it running if a command or background process still has work to do. Check the expiration time: the default **Stop** action stops the sandbox after one hour, including background processes, and keeps its files. -- Delete it when you no longer need it. Save the review or push any changes +- Delete it when you no longer need it. Save the commit record or push any changes you want to keep first. Deletion removes files stored only in the sandbox. For more detail, see [Lifecycle actions](sandboxes.md#manage-the-lifecycle). From 4213e2aeae4c68ddd5bb1361fc29a931f082f89f Mon Sep 17 00:00:00 2001 From: David Karlsson <35727626+dvdksn@users.noreply.github.com> Date: Thu, 22 Oct 2026 08:35:30 +0200 Subject: [PATCH 2/6] docs: demonstrate building and previewing an app in DAP --- .../manuals/agentic-platform/get-started.md | 69 ++++++++++--------- 1 file changed, 37 insertions(+), 32 deletions(-) diff --git a/content/manuals/agentic-platform/get-started.md b/content/manuals/agentic-platform/get-started.md index b067056d1a25..e59f1c6db388 100644 --- a/content/manuals/agentic-platform/get-started.md +++ b/content/manuals/agentic-platform/get-started.md @@ -1,17 +1,18 @@ --- title: Get started with Docker Agentic Platform linkTitle: Get started -description: Start a shell in your first cloud sandbox, explore a sample project, save a file, and pause or delete the sandbox when you're finished. +description: Build and run a sample web app in a cloud sandbox, preview it in your browser, and connect your editor without setting up a local development environment. keywords: docker agentic platform, get started, cloud sandboxes, shell, agents, ssh, vscode, cursor weight: 10 aliases: - /agentic-platform/concepts/platform-model/ --- -Use a cloud sandbox to work on a project without setting it up on your -computer. In this walkthrough, you'll start a shell, clone a public sample -application, and save a record of its latest commit. Then you'll pause the -sandbox to return later or delete it when you're finished. +Build and run a web application in a cloud sandbox without installing its +dependencies on your computer. In this walkthrough, you'll start a shell, +clone a sample application, build its container image, and open the running +app in your browser. Then you'll pause the sandbox to return later or delete +it when you're finished. You can complete the walkthrough in the browser. An optional step shows how to open the same project in VS Code or Cursor over SSH. @@ -33,16 +34,17 @@ their credentials, see [Kits](kits.md) and [Secrets](secrets.md). 3. If saved secrets or a GitHub token are selected, deselect them for this walkthrough. You don't need MCP tools either. 4. In the network policy picker, select **Balanced** to permit access to - GitHub. Keep the compute and timer defaults and select **Run**. + GitHub, Docker Hub, and npm. Keep the compute and timer defaults and select + **Run**. -If you use a custom network policy, make sure it permits GitHub. See -[Network policies](policies.md). +If you use a custom network policy, make sure it permits GitHub, Docker Hub, +and npm. See [Network policies](policies.md). When the sandbox is ready, its terminal opens with a Bash shell. After launch, you can't change the selected credentials, tools, network policies, or compute size. See [Sandbox options](#sandbox-options) for other launch settings. -## Explore a project +## Build and run an application Your local files aren't mounted in a cloud sandbox. In the browser terminal, clone a public sample project: @@ -51,29 +53,37 @@ clone a public sample project: $ cd /home/agent/workspace $ git clone https://github.com/docker/welcome-to-docker.git project $ cd project -$ ls ``` -Read the project's package scripts and Dockerfile: +The Shell kit includes Docker Engine. Build the application's container image: ```console -$ cat package.json -$ cat Dockerfile +$ docker build -t welcome-to-docker . ``` -Save a record of the latest commit to a file in the workspace: +The build installs the application's dependencies and compiles it inside the +sandbox. When it finishes, start a container and publish its port: ```console -$ git log -1 --oneline > /home/agent/workspace/latest-commit.txt -$ cat /home/agent/workspace/latest-commit.txt +$ docker run -d --name welcome-to-docker -p 3000:3000 welcome-to-docker ``` -The output shows the commit's short ID and message. The file stays in the -sandbox so you can open it later or copy it to your computer. +## Preview the application + +1. Select **Connect** on the sandbox's detail page. +2. Under **Connect via a Port**, enter `3000` and select **Open Port**. +3. Open the generated URL in your browser. + +You should see the Welcome to Docker application. The application runs in the +cloud sandbox, so you can try it without installing Docker or Node.js on your +computer. + +The generated URL is public. Close the port in **Connect** when you've finished +previewing the application. ## Keep your work -The cloned project and commit record are stored in the sandbox. Files don't sync +The source code and container image are stored in the sandbox. Files don't sync automatically with your computer or a remote repository. They remain available when you pause and resume the sandbox, but are lost when you delete it. @@ -85,9 +95,9 @@ needs to push changes. ## Open the project in your editor (optional) -Open the project and commit record in VS Code or Cursor over SSH. Your editor -runs on your computer, while the files and terminal commands stay in the -cloud sandbox. +Open the project in VS Code or Cursor over SSH to edit the application. Your +editor runs on your computer, while the files and terminal commands stay in +the cloud sandbox. 1. Install the [Docker Sandboxes CLI](/manuals/ai/sandboxes/install.md), version 0.45.0 or later. @@ -114,17 +124,12 @@ cloud sandbox. In Cursor, install its Remote - SSH support. 5. Open your editor's Command Palette and run **Remote-SSH: Connect to Host**. Enter `@sbx_cloud`, using the same ID as in the SSH command. -6. Open `/home/agent/workspace` in the remote window. You'll find the cloned - application in `project` and the commit record in `latest-commit.txt`. +6. Open `/home/agent/workspace/project` in the remote window. Edit the source + files, then rebuild the image and recreate the container to preview your + changes. The first connection installs the editor's server inside the sandbox. -To download the commit record, run this command in a terminal on your computer: - -```console -$ sbx --cloud cp :/home/agent/workspace/latest-commit.txt ./latest-commit.txt -``` - ## Pause, keep running, or delete the sandbox Closing the browser or disconnecting your editor leaves the sandbox running. @@ -137,10 +142,10 @@ Return to **Sandboxes** in the Console and choose what to do next: - Pause the sandbox to stop compute charges and keep its files. Confirm that it is paused in the list. To continue later, reopen the sandbox and resume it. Resuming starts a fresh timer with the original duration. -- Leave it running if a command or background process still has work to do. Check the expiration +- Leave it running to keep the application available. Check the expiration time: the default **Stop** action stops the sandbox after one hour, including background processes, and keeps its files. -- Delete it when you no longer need it. Save the commit record or push any changes +- Delete it when you no longer need it. Push any source changes you want to keep first. Deletion removes files stored only in the sandbox. For more detail, see [Lifecycle actions](sandboxes.md#manage-the-lifecycle). From c03b1b1dc88f31883495db208ce051e9e414efa2 Mon Sep 17 00:00:00 2001 From: David Karlsson <35727626+dvdksn@users.noreply.github.com> Date: Thu, 22 Oct 2026 08:38:41 +0200 Subject: [PATCH 3/6] docs: remove redundant sandbox workspace command --- content/manuals/agentic-platform/get-started.md | 1 - 1 file changed, 1 deletion(-) diff --git a/content/manuals/agentic-platform/get-started.md b/content/manuals/agentic-platform/get-started.md index e59f1c6db388..9b94e4770db9 100644 --- a/content/manuals/agentic-platform/get-started.md +++ b/content/manuals/agentic-platform/get-started.md @@ -50,7 +50,6 @@ Your local files aren't mounted in a cloud sandbox. In the browser terminal, clone a public sample project: ```console -$ cd /home/agent/workspace $ git clone https://github.com/docker/welcome-to-docker.git project $ cd project ``` From a022723d506e9e2bf58b52095cea538ea23f0ae0 Mon Sep 17 00:00:00 2001 From: David Karlsson <35727626+dvdksn@users.noreply.github.com> Date: Thu, 22 Oct 2026 09:00:12 +0200 Subject: [PATCH 4/6] docs: introduce sandbox kits before selecting Shell --- content/manuals/agentic-platform/get-started.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/content/manuals/agentic-platform/get-started.md b/content/manuals/agentic-platform/get-started.md index 9b94e4770db9..c7615805e5af 100644 --- a/content/manuals/agentic-platform/get-started.md +++ b/content/manuals/agentic-platform/get-started.md @@ -22,12 +22,14 @@ to open the same project in VS Code or Cursor over SSH. You need a personal Docker account with an active [Docker Agentic Platform subscription](signup.md#activate-cloud-access). -The Shell kit doesn't require a model provider API key. This example uses a -public repository, so you don't need a GitHub token either. For agents and -their credentials, see [Kits](kits.md) and [Secrets](secrets.md). +You don't need a model provider API key for this walkthrough. The sample +project is public, so you don't need a GitHub token either. ## Start a sandbox +A [kit](kits.md) defines a sandbox's base image and installed tools. This +walkthrough uses the Shell kit, which starts a Bash shell without an agent. + 1. Open [Docker Agentic Platform](https://agentic-platform.docker.com/) and select **+ New sandbox**. 2. Open the kit picker and choose **shell**. From 0a064fabedb6df29885e89e142a45cd934d373c4 Mon Sep 17 00:00:00 2001 From: David Karlsson <35727626+dvdksn@users.noreply.github.com> Date: Thu, 22 Oct 2026 12:24:53 +0000 Subject: [PATCH 5/6] docs: offer coding agent and shell getting-started workflows The shell walkthrough replaced the existing Claude Code guide. Restore the coding agent workflow alongside the shell workflow, add links to choose a path, and share editor and sandbox lifecycle instructions. --- .../manuals/agentic-platform/get-started.md | 110 ++++++++++++++---- 1 file changed, 87 insertions(+), 23 deletions(-) diff --git a/content/manuals/agentic-platform/get-started.md b/content/manuals/agentic-platform/get-started.md index c7615805e5af..65b76c61e645 100644 --- a/content/manuals/agentic-platform/get-started.md +++ b/content/manuals/agentic-platform/get-started.md @@ -1,20 +1,17 @@ --- title: Get started with Docker Agentic Platform linkTitle: Get started -description: Build and run a sample web app in a cloud sandbox, preview it in your browser, and connect your editor without setting up a local development environment. +description: Review a sample project with a coding agent or build and preview it from a shell in a cloud sandbox, without setting up a local development environment. keywords: docker agentic platform, get started, cloud sandboxes, shell, agents, ssh, vscode, cursor weight: 10 aliases: - /agentic-platform/concepts/platform-model/ --- -Build and run a web application in a cloud sandbox without installing its -dependencies on your computer. In this walkthrough, you'll start a shell, -clone a sample application, build its container image, and open the running -app in your browser. Then you'll pause the sandbox to return later or delete -it when you're finished. +Use a cloud sandbox to review a project with a coding agent or build and run +an application from a shell, without setting up the project on your computer. -You can complete the walkthrough in the browser. An optional step shows how +You can complete either workflow in the browser. An optional step shows how to open the same project in VS Code or Cursor over SSH. ## Before you begin @@ -22,13 +19,73 @@ to open the same project in VS Code or Cursor over SSH. You need a personal Docker account with an active [Docker Agentic Platform subscription](signup.md#activate-cloud-access). -You don't need a model provider API key for this walkthrough. The sample -project is public, so you don't need a GitHub token either. +Both workflows use a public sample project, so you don't need a GitHub token. -## Start a sandbox +## Choose a workflow -A [kit](kits.md) defines a sandbox's base image and installed tools. This -walkthrough uses the Shell kit, which starts a Bash shell without an agent. +- [Use a coding agent](#use-a-coding-agent) to have Claude Code review a sample + project and save its findings. You need an Anthropic API key. +- [Use a shell](#use-a-shell) to build and run the sample application and preview + it in your browser. You don't need a model provider API key. + +A [kit](kits.md) defines a sandbox's base image and installed tools. Choose the +kit for the workflow you want to follow. After launch, you can't change the +selected credentials, tools, network policies, or compute size. See +[Sandbox options](#sandbox-options) for other launch settings. + +## Use a coding agent + +Add an Anthropic API key under **Secrets** or enter it when you launch the +sandbox. Your model provider bills inference separately from Docker's sandbox +compute charges. For other agents and their credentials, see [Kits](kits.md) +and [Secrets](secrets.md). + +### Launch Claude Code + +1. Open [Docker Agentic Platform](https://agentic-platform.docker.com/) and + select **+ New sandbox**. +2. Choose the Claude Code kit. +3. Add your Anthropic API key if it isn't already saved. Don't enter it in + the agent's prompt or in a file inside the sandbox. +4. Keep the defaults and select **Run**. + +On your first launch, the default **Open** network policy permits outbound +access to any host. If you're using a custom policy, make sure it permits +GitHub and your model provider. See [Network policies](policies.md). + +When the sandbox is ready, its terminal opens with Claude Code. + +### Give the agent a task + +Your local files aren't mounted in a cloud sandbox. Ask Claude Code to clone +and review a public sample project: + +```text +Clone https://github.com/docker/welcome-to-docker.git into +/home/agent/workspace/project, then review the application. +Read the source, package.json, and Dockerfile. Don't modify the application +or install dependencies. +Write /home/agent/workspace/review.md with: +- A short explanation of what the application does. +- The commands defined in package.json for running and building it. +- An explanation of how the Dockerfile builds and serves the application. +- One small improvement you'd recommend, with the relevant file path. +Base the review on the files you read. Don't claim to have run the application. +Summarize your findings in your response. +``` + +Claude Code summarizes the project in the conversation and saves the review +at `/home/agent/workspace/review.md`. You can ask follow-up questions or give +it another task in the same session. + +Continue to [keep your work](#keep-your-work), or +[open the project in your editor](#open-the-project-in-your-editor-optional). + +## Use a shell + +### Launch a shell + +The Shell kit starts a Bash shell without an agent. 1. Open [Docker Agentic Platform](https://agentic-platform.docker.com/) and select **+ New sandbox**. @@ -42,11 +99,9 @@ walkthrough uses the Shell kit, which starts a Bash shell without an agent. If you use a custom network policy, make sure it permits GitHub, Docker Hub, and npm. See [Network policies](policies.md). -When the sandbox is ready, its terminal opens with a Bash shell. After launch, -you can't change the selected credentials, tools, network policies, or compute -size. See [Sandbox options](#sandbox-options) for other launch settings. +When the sandbox is ready, its terminal opens with a Bash shell. -## Build and run an application +### Build and run an application Your local files aren't mounted in a cloud sandbox. In the browser terminal, clone a public sample project: @@ -69,7 +124,7 @@ sandbox. When it finishes, start a container and publish its port: $ docker run -d --name welcome-to-docker -p 3000:3000 welcome-to-docker ``` -## Preview the application +### Preview the application 1. Select **Connect** on the sandbox's detail page. 2. Under **Connect via a Port**, enter `3000` and select **Open Port**. @@ -82,10 +137,13 @@ computer. The generated URL is public. Close the port in **Connect** when you've finished previewing the application. +Continue to [keep your work](#keep-your-work), or +[open the project in your editor](#open-the-project-in-your-editor-optional). + ## Keep your work -The source code and container image are stored in the sandbox. Files don't sync -automatically with your computer or a remote repository. They remain available +The cloned project and any files you create are stored in the sandbox. Files +don't sync automatically with your computer or a remote repository. They remain available when you pause and resume the sandbox, but are lost when you delete it. To keep files outside the sandbox, use the CLI to @@ -125,12 +183,18 @@ the cloud sandbox. In Cursor, install its Remote - SSH support. 5. Open your editor's Command Palette and run **Remote-SSH: Connect to Host**. Enter `@sbx_cloud`, using the same ID as in the SSH command. -6. Open `/home/agent/workspace/project` in the remote window. Edit the source - files, then rebuild the image and recreate the container to preview your - changes. +6. Open `/home/agent/workspace` in the remote window. Both workflows clone + the application into `project`. The coding agent also saves `review.md` + in the workspace. The first connection installs the editor's server inside the sandbox. +If you followed the coding agent workflow, download the review run this command in a terminal on your computer: + +```console +$ sbx --cloud cp :/home/agent/workspace/review.md ./review.md +``` + ## Pause, keep running, or delete the sandbox Closing the browser or disconnecting your editor leaves the sandbox running. @@ -143,7 +207,7 @@ Return to **Sandboxes** in the Console and choose what to do next: - Pause the sandbox to stop compute charges and keep its files. Confirm that it is paused in the list. To continue later, reopen the sandbox and resume it. Resuming starts a fresh timer with the original duration. -- Leave it running to keep the application available. Check the expiration +- Leave it running if the agent still has work to do or to keep the application available. Check the expiration time: the default **Stop** action stops the sandbox after one hour, including background processes, and keeps its files. - Delete it when you no longer need it. Push any source changes From bf62c8bf7a4f1e5910717fa3b396e2c8c5273d7b Mon Sep 17 00:00:00 2001 From: David Karlsson <35727626+dvdksn@users.noreply.github.com> Date: Thu, 22 Oct 2026 12:37:04 +0000 Subject: [PATCH 6/6] docs: keep workflow selection focused on the reader's task The kit definition and launch restrictions interrupted the choice between workflows. Remove that paragraph and move the launch restrictions to Sandbox options. --- content/manuals/agentic-platform/get-started.md | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/content/manuals/agentic-platform/get-started.md b/content/manuals/agentic-platform/get-started.md index 65b76c61e645..6b5c76925d5e 100644 --- a/content/manuals/agentic-platform/get-started.md +++ b/content/manuals/agentic-platform/get-started.md @@ -28,11 +28,6 @@ Both workflows use a public sample project, so you don't need a GitHub token. - [Use a shell](#use-a-shell) to build and run the sample application and preview it in your browser. You don't need a model provider API key. -A [kit](kits.md) defines a sandbox's base image and installed tools. Choose the -kit for the workflow you want to follow. After launch, you can't change the -selected credentials, tools, network policies, or compute size. See -[Sandbox options](#sandbox-options) for other launch settings. - ## Use a coding agent Add an Anthropic API key under **Secrets** or enter it when you launch the @@ -221,7 +216,8 @@ For programmatic workflows, see the ## Sandbox options -Configure these options before selecting **Run**: +After launch, you can't change the selected credentials, tools, network policies, +or compute size. Configure these options before selecting **Run**: | Option | What to choose | | --- | --- |