Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions content/en/agentic_onboarding/setup.md
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ To install the Datadog Onboarding Model Context Protocol (MCP) server, follow th

2. Select the MCP server installed in Step 1. You should see a `disconnected - Enter to login` message. Press <kbd>Enter</kbd>.
3. When you see the option to authenticate, press <kbd>Enter</kbd>. This brings you to the OAuth screen.
4. After authentication, choose **Open** to continue and grant access to your Datadog account.
4. After authentication, choose {{< ui >}}Open{{< /ui >}} to continue and grant access to your Datadog account.
5. Confirm that MCP tools appear under the **datadog-onboarding-{{< region-param key=dd_datacenter_lowercase >}}** server.
{{< /site-region >}}

Expand All @@ -59,8 +59,8 @@ To install the Datadog Onboarding Model Context Protocol (MCP) server, follow th
<code>{{< region-param key=cursor_mcp_install_deeplink >}}</code>
</pre>

2. In Cursor, click **Install** for the **datadog-onboarding-{{< region-param key=dd_datacenter_lowercase >}}** server.
3. If the MCP server shows a **Needs login** or **Connect** link, select it and complete the OAuth flow. When prompted, choose **Open** to continue and grant access to your Datadog account.
2. In Cursor, click {{< ui >}}Install{{< /ui >}} for the **datadog-onboarding-{{< region-param key=dd_datacenter_lowercase >}}** server.
3. If the MCP server shows a {{< ui >}}Needs login{{< /ui >}} or {{< ui >}}Connect{{< /ui >}} link, select it and complete the OAuth flow. When prompted, choose {{< ui >}}Open{{< /ui >}} to continue and grant access to your Datadog account.
4. After authentication, return to Cursor and confirm that MCP tools appear under the **datadog-onboarding-{{< region-param key=dd_datacenter_lowercase >}}** server.
{{< /site-region >}}

Expand Down
8 changes: 4 additions & 4 deletions content/en/ai_agents_console/_index.md
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ AI Agents Console supports the following integrations:

To monitor Claude Code with AI Agents Console, set up the [Anthropic Usage and Costs][4] integration.

After setup, navigate to the [AI Agents Console][1] and click the **Claude Code** tile to view metrics.
After setup, navigate to the [AI Agents Console][1] and click the {{< ui >}}Claude Code{{< /ui >}} tile to view metrics.

#### Option 2: OpenTelemetry (OTLP)

Expand Down Expand Up @@ -65,7 +65,7 @@ The following procedure configures Claude Code to send telemetry directly to Dat
<div class="alert alert-info">To set up AI Agents Console for Claude Code across your organization, your IT team can use a Mobile Device Management (MDM) system or <a href="https://code.claude.com/docs/en/server-managed-settings">server-managed settings</a> to distribute the Claude Code settings file across all managed devices.</div>
4. Restart Claude Code.

After you restart Claude Code, navigate to the [AI Agents Console][1] in Datadog and click on the **Claude Code** tile. Metrics (usage, cost, latency, errors) should appear within a few minutes.
After you restart Claude Code, navigate to the [AI Agents Console][1] in Datadog and click on the {{< ui >}}Claude Code{{< /ui >}} tile. Metrics (usage, cost, latency, errors) should appear within a few minutes.

#### Option 3: Forward data through the Datadog Agent

Expand Down Expand Up @@ -100,13 +100,13 @@ After you restart Claude Code, navigate to the [AI Agents Console][1] in Datadog
<div class="alert alert-info">To set up AI Agents Console for Claude Code across your organization, your IT team can use a Mobile Device Management (MDM) system or <a href="https://code.claude.com/docs/en/server-managed-settings">server-managed settings</a> to distribute the Claude Code settings file across all managed devices.</div>
5. Restart Claude Code.

After you restart Claude Code, navigate to the [AI Agents Console][1] in Datadog and click on the **Claude Code** tile. Metrics (usage, cost, latency, errors) should appear within a few minutes.
After you restart Claude Code, navigate to the [AI Agents Console][1] in Datadog and click on the {{< ui >}}Claude Code{{< /ui >}} tile. Metrics (usage, cost, latency, errors) should appear within a few minutes.

### Cursor

To monitor Cursor with AI Agents Console, set up the [Cursor][5] integration using the Datadog Extension for Cursor.

After setup, navigate to the [AI Agents Console][1] and click the **Cursor** tile to view metrics.
After setup, navigate to the [AI Agents Console][1] and click the {{< ui >}}Cursor{{< /ui >}} tile to view metrics.

## Further reading

Expand Down
4 changes: 2 additions & 2 deletions content/en/bits_ai/bits_ai_dev_agent/_index.md
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ Bits AI Dev Agent integrates with GitHub to create pull requests, respond to com

**Note**: Comment `@Datadog` to prompt Bits for updates to the PR. Bits Dev never auto-merges PRs.

Go to **Bits AI** > **Dev Agent** > **[Code sessions][7]** to see all Dev Agent code sessions and generated PRs. You can search sessions and filter by service, product source, and status.
Go to {{< ui >}}Bits AI{{< /ui >}} > {{< ui >}}Dev Agent{{< /ui >}} > [{{< ui >}}Code sessions{{< /ui >}}][7] to see all Dev Agent code sessions and generated PRs. You can search sessions and filter by service, product source, and status.

### Auto-push

Expand All @@ -74,7 +74,7 @@ In [Error Tracking][1], Bits AI Dev Agent diagnoses and remediates code issues w
- Determines whether an error can be fixed through code and generates a fix with unit tests.
- Provides links within the chat to relevant files and methods for streamlined navigation.
- Analyzes errors asynchronously as they arrive.
- Marks errors with a **Fix available** status and enables filtering to surface those issues.
- Marks errors with a {{< ui >}}Fix available{{< /ui >}} status and enables filtering to surface those issues.

[Auto-push](#auto-push) is available for this feature.

Expand Down
24 changes: 12 additions & 12 deletions content/en/bits_ai/bits_ai_dev_agent/setup.md
Original file line number Diff line number Diff line change
Expand Up @@ -17,22 +17,22 @@ If your organization uses custom roles, an admin must add this permission manual

1. Install the [GitHub integration][2]. For full installation and configuration steps, see the [GitHub integration guide][3].

1. In your GitHub account, navigate to **Settings** > **Apps** > **Datadog** to configure GitHub permissions.
1. In your GitHub account, navigate to {{< ui >}}Settings{{< /ui >}} > {{< ui >}}Apps{{< /ui >}} > {{< ui >}}Datadog{{< /ui >}} to configure GitHub permissions.

1. To enable basic Dev Agent functionality, set the following permissions:

- **Repository permissions**
- {{< ui >}}Repository permissions{{< /ui >}}
- Repository contents: Read & write
- Pull requests: Read & write
- **Subscribe to events**
- {{< ui >}}Subscribe to events{{< /ui >}}
- Push

1. (Optional) To allow the Dev Agent to use CI logs when iterating on pull requests, you must send CI logs to Datadog and enable the [auto-push](#enable-auto-push) feature. This requires additional permissions:

- **Repository permissions**
- {{< ui >}}Repository permissions{{< /ui >}}
- Checks: Read
- Commit statuses: Read only
- **Subscribe to events**
- {{< ui >}}Subscribe to events{{< /ui >}}
- Check run
- Check suite
- Issue comment
Expand All @@ -48,10 +48,10 @@ Bits AI Dev Agent uses the `service` and `version` telemetry tags to match detec

To configure telemetry tagging, see [Tag your APM telemetry with Git information][4].

You can also configure service-to-repository mapping manually in the Bits AI Dev Agent settings under [**Repositories**][5] > **Service Repository Mapping**.
You can also configure service-to-repository mapping manually in the Bits AI Dev Agent settings under [{{< ui >}}Repositories{{< /ui >}}][5] > {{< ui >}}Service Repository Mapping{{< /ui >}}.

### Enable auto-push
To enable auto-push, so the Dev Agent can push commits directly to a branch, navigate to [**Bits AI Dev** > **Settings** > **General**][12] , and set the toggle to **Enable**.
To enable auto-push, so the Dev Agent can push commits directly to a branch, navigate to [{{< ui >}}Bits AI Dev{{< /ui >}} > {{< ui >}}Settings{{< /ui >}} > {{< ui >}}General{{< /ui >}}][12] , and set the toggle to {{< ui >}}Enable{{< /ui >}}.

**Note**: If auto-push is disabled, you must review and approve code in Datadog before the Dev Agent can push it.

Expand All @@ -67,15 +67,15 @@ The Dev Agent ingests custom instruction files from your repository, including:
- `agent.md`


You can also define global custom instructions, which apply to all Dev Agent sessions, in **Bits AI Dev** > [**Settings**][12] > **General**, in the **Global Agent Instructions** section.
You can also define global custom instructions, which apply to all Dev Agent sessions, in {{< ui >}}Bits AI Dev{{< /ui >}} > [{{< ui >}}Settings{{< /ui >}}][12] > {{< ui >}}General{{< /ui >}}, in the {{< ui >}}Global Agent Instructions{{< /ui >}} section.

## Environment setup

Configure the Dev Agent's runtime environment, including network access policies and repository-specific tooling.

### Configure internet access

By default, the Dev Agent has **no internet access** during agent execution. To configure which external domains agents can reach, navigate to **Bits AI Dev** > [**Settings**][12] > **General**, and find the **Internet Access** section. Choose from the following access policies: **No Internet Access**, **Default Allowlist**, **Custom + Default Allowlist**, or **Custom Allowlist**.
By default, the Dev Agent has no internet access during agent execution. To configure which external domains agents can reach, navigate to {{< ui >}}Bits AI Dev{{< /ui >}} > [{{< ui >}}Settings{{< /ui >}}][12] > {{< ui >}}General{{< /ui >}}, and find the {{< ui >}}Internet Access{{< /ui >}} section. Choose from the following access policies: {{< ui >}}No Internet Access{{< /ui >}}, {{< ui >}}Default Allowlist{{< /ui >}}, {{< ui >}}Custom + Default Allowlist{{< /ui >}}, or {{< ui >}}Custom Allowlist{{< /ui >}}.

The default allowlist includes the following domains:

Expand All @@ -96,10 +96,10 @@ Configure a custom environment for the Dev Agent to install dependencies, format

To configure a repository environment:

1. Go to **Bits AI Dev** > **Settings** > [**Repositories**][5], and find the **Environments** section.
1. Click **Add Environment** to create a repository configuration:
1. Go to {{< ui >}}Bits AI Dev{{< /ui >}} > {{< ui >}}Settings{{< /ui >}} > [{{< ui >}}Repositories{{< /ui >}}][5], and find the {{< ui >}}Environments{{< /ui >}} section.
1. Click {{< ui >}}Add Environment{{< /ui >}} to create a repository configuration:
1. Select a repository from the dropdown.
1. (Optional) Under **Pre-installed Languages**, click **Select Versions** to specify the language versions the sandbox should use.
1. (Optional) Under {{< ui >}}Pre-installed Languages{{< /ui >}}, click {{< ui >}}Select Versions{{< /ui >}} to specify the language versions the sandbox should use.
1. (Optional) Define environment variables and secrets. Environment variables are available during both environment setup and Dev Agent execution. Secrets are available as environment variables only during environment setup.
1. (Optional) Add a shell script with setup commands to execute (for example: `pip install -r requirements.txt`).
1. Run the setup command to ensure it runs successfully.
Expand Down
26 changes: 13 additions & 13 deletions content/en/bits_ai/bits_ai_security_analyst.md
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ Bits AI Security Analyst is an autonomous AI agent that investigates Cloud SIEM

Bits AI Security Analyst investigations are autonomous. If a detection rule is enabled, Bits AI autonomously investigates signals associated with it.

In the [Cloud SIEM Signals Explorer][5], you can click the **Bits AI Security Analyst** tab to only show signals that Bits AI investigated. In the Severity column, a Bits AI status displays as Investigating, until marking the signal as either Benign or Suspicious.
In the [Cloud SIEM Signals Explorer][5], you can click the {{< ui >}}Bits AI Security Analyst{{< /ui >}} tab to only show signals that Bits AI investigated. In the Severity column, a Bits AI status displays as Investigating, until marking the signal as either Benign or Suspicious.

{{< img src="bits_ai/bits_ai_security_analyst_signals_explorer.png" alt="The Cloud SIEM signals explorer, on the Bits AI Security Analyst tab" style="width:100%;" >}}

Expand Down Expand Up @@ -72,32 +72,32 @@ When you enable Bits AI Security Analyst, Datadog analyzes your rules, including

Rule eligibility depends on whether Datadog has built the investigation capability for the log source, and whether the Agent is able to investigate the specific rule. If you have new custom rules to evaluate, or want to ask about a rule that wasn't made eligible, contact [Datadog support][1].

1. In Datadog, go to **Security** > **Settings** > **[Bits AI Security Analyst][3]**.
1. In Datadog, go to {{< ui >}}Security{{< /ui >}} > {{< ui >}}Settings{{< /ui >}} > [{{< ui >}}Bits AI Security Analyst{{< /ui >}}][3].
1. Turn on the toggle to enable Bits AI Security Analyst. Additional settings appear.
1. (Optional) Configure which rules and which severities you want Bits AI Security Analyst to automatically investigate signals for. There are two ways to do so:
- Click **Rule Settings** to configure investigations for individual rules. You can change the minimum severity for signals to be investigated, and enable or disable individual rules for investigation.
- Click **Query Filter** to write a signal query filter, so Bits AI Security Analyst only investigates signals that match your filter.
1. Some log sources require credentials to run or enhance investigations by accessing logs, telemetry, or other data that isn't in Datadog. To add credentials, click **Edit credentials**. In the **Select or Add Connection** window that opens, follow the prompts to select an [existing connection][4] from Actions Catalog, or add a connection. Datadog securely stores and restricts all credentials using Actions Catalog.
- Click {{< ui >}}Rule Settings{{< /ui >}} to configure investigations for individual rules. You can change the minimum severity for signals to be investigated, and enable or disable individual rules for investigation.
- Click {{< ui >}}Query Filter{{< /ui >}} to write a signal query filter, so Bits AI Security Analyst only investigates signals that match your filter.
1. Some log sources require credentials to run or enhance investigations by accessing logs, telemetry, or other data that isn't in Datadog. To add credentials, click {{< ui >}}Edit credentials{{< /ui >}}. In the {{< ui >}}Select or Add Connection{{< /ui >}} window that opens, follow the prompts to select an [existing connection][4] from Actions Catalog, or add a connection. Datadog securely stores and restricts all credentials using Actions Catalog.
- Some log sources require additional setup so you can create HTTP connections. Here's an example:
{{< collapse-content title="Configure SentinelOne" level="h4" expanded=false id="sentinelone" >}}
<ol>
<li>In SentinelOne, ensure you have permission to create an API token. Create an S1 API service user, then assign the <strong>Viewer</strong> role to that user.</li>
<li>In Datadog, in the <strong>Select or Add Connection</strong> window, in the dropdown, select <strong>New Connection</strong>, then click the <strong>HTTP</strong> tile.</li>
<li>In SentinelOne, ensure you have permission to create an API token. Create an S1 API service user, then assign the {{< ui >}}Viewer{{< /ui >}} role to that user.</li>
<li>In Datadog, in the {{< ui >}}Select or Add Connection{{< /ui >}} window, in the dropdown, select {{< ui >}}New Connection{{< /ui >}}, then click the {{< ui >}}HTTP{{< /ui >}} tile.</li>
<li>Add the following information:
<ul>
<li>In the <strong>Description</strong> field, Datadog recommends adding your token expiry date, to make it easily accessible.</li>
<li>In the <strong>Base URL</strong> field, enter your SentinelOne Management Console URL.</li>
<li>Under <strong>Token Auth</strong>, enter a name for your token in the <strong>Token Name</strong> field, and your API token in the <strong>Token Value</strong> field.</li>
<li>In the {{< ui >}}Description{{< /ui >}} field, Datadog recommends adding your token expiry date, to make it easily accessible.</li>
<li>In the {{< ui >}}Base URL{{< /ui >}} field, enter your SentinelOne Management Console URL.</li>
<li>Under {{< ui >}}Token Auth{{< /ui >}}, enter a name for your token in the {{< ui >}}Token Name{{< /ui >}} field, and your API token in the {{< ui >}}Token Value{{< /ui >}} field.</li>
</ul>
</li>
<li>Click <strong>Next, Confirm Access</strong> to verify your connection.</li>
<li>Click {{< ui >}}Next, Confirm Access{{< /ui >}} to verify your connection.</li>
</ol>
{{< /collapse-content >}}

## Disable Bits AI Security Analyst

1. In Datadog, go to **Security** > **Settings** > **[Bits AI Security Analyst][3]**.
1. Scroll to the bottom of the page. Under **Disable Bits AI Security Analyst**, turn off the **Enabled** toggle.
1. In Datadog, go to {{< ui >}}Security{{< /ui >}} > {{< ui >}}Settings{{< /ui >}} > [{{< ui >}}Bits AI Security Analyst{{< /ui >}}][3].
1. Scroll to the bottom of the page. Under {{< ui >}}Disable Bits AI Security Analyst{{< /ui >}}, turn off the {{< ui >}}Enabled{{< /ui >}} toggle.
<div class="alert alert-warning">Disabling Bits AI Security Analyst permanently resets all configuration settings.</div>

## Further reading
Expand Down
Loading
Loading