DOCS-12323: Bits AI Kubernetes Remediation

config/_default/menus/main.en.yaml

@@ -3101,251 +3101,256 @@ menu:
       parent: containers
       identifier: containers_autoscaling
       weight: 2
+    - name: Remediation
+      url: containers/bits_ai_kubernetes_remediation
+      parent: containers
+      identifier: containers_autoscaling
+      weight: 3
     - name: Docker and other runtimes
       url: containers/docker/
       parent: containers
       identifier: containers_docker
-      weight: 3
+      weight: 4
     - name: APM
       url: containers/docker/apm/
       parent: containers_docker
       identifier: containers_docker_apm
-      weight: 301
+      weight: 401
     - name: Log collection
       url: containers/docker/log/
       parent: containers_docker
       identifier: containers_docker_log
-      weight: 302
+      weight: 402
     - name: Tag extraction
       url: containers/docker/tag/
       parent: containers_docker
       identifier: containers_docker_tag
-      weight: 303
+      weight: 403
     - name: Integrations
       url: containers/docker/integrations/
       parent: containers_docker
       identifier: containers_docker_integrations
-      weight: 304
+      weight: 404
     - name: Prometheus
       url: containers/docker/prometheus/
       parent: containers_docker
       identifier: containers_docker_prometheus
-      weight: 305
+      weight: 405
     - name: Data Collected
       url: containers/docker/data_collected/
       parent: containers_docker
       identifier: containers_docker_data_collected
-      weight: 306
+      weight: 406
     - name: Kubernetes
       url: containers/kubernetes/
       parent: containers
       identifier: containers_kubernetes
-      weight: 4
+      weight: 5
     - name: Installation
       url: containers/kubernetes/installation
       parent: containers_kubernetes
       identifier: containers_kubernetes_installation
-      weight: 401
+      weight: 501
     - name: Further Configuration
       url: containers/kubernetes/configuration
       parent: containers_kubernetes
       identifier: containers_kubernetes_configuration
-      weight: 402
+      weight: 502
     - name: Distributions
       url: containers/kubernetes/distributions
       parent: containers_kubernetes
       identifier: containers_kubernetes_distributions
-      weight: 403
+      weight: 503
     - name: APM
       url: containers/kubernetes/apm/
       parent: containers_kubernetes
       identifier: containers_kubernetes_apm
-      weight: 404
+      weight: 504
     - name: Log collection
       url: containers/kubernetes/log/
       parent: containers_kubernetes
       identifier: containers_kubernetes_log
-      weight: 405
+      weight: 505
     - name: Tag extraction
       url: containers/kubernetes/tag/
       parent: containers_kubernetes
       identifier: containers_kubernetes_tag
-      weight: 406
+      weight: 506
     - name: Integrations
       url: containers/kubernetes/integrations/
       parent: containers_kubernetes
       identifier: containers_kubernetes_integrations
-      weight: 407
+      weight: 507
     - name: Prometheus & OpenMetrics
       url: containers/kubernetes/prometheus/
       parent: containers_kubernetes
       identifier: containers_kubernetes_prometheus
-      weight: 408
+      weight: 508
     - name: Control plane monitoring
       url: containers/kubernetes/control_plane/
       parent: containers_kubernetes
       identifier: containers_kubernetes_control_plane
-      weight: 409
+      weight: 509
     - name: Data collected
       url: containers/kubernetes/data_collected/
       parent: containers_kubernetes
       identifier: containers_kubernetes_data_collected
-      weight: 410
+      weight: 510
     - name: Datadog CSI Driver
       url: containers/kubernetes/csi_driver
       parent: containers_kubernetes
       identifier: csi_driver
-      weight: 411
+      weight: 511
     - name: Data security
       url: data_security/kubernetes
       parent: containers_kubernetes
       identifier: container_kubernetes_data_security
-      weight: 412
+      weight: 512
     - name: Cluster Agent
       url: containers/cluster_agent/
       parent: containers
       identifier: containers_cluster
-      weight: 5
+      weight: 6
     - name: Setup
       url: containers/cluster_agent/setup/
       parent: containers_cluster
       identifier: cluster_agent_setup
-      weight: 501
+      weight: 601
     - name: Commands & Options
       url: containers/cluster_agent/commands/
       identifier: cluster_agent_commands
       parent: containers_cluster
-      weight: 502
+      weight: 602
     - name: Cluster Checks
       identifier: containers_cluster_agent_clusterchecks
       url: containers/cluster_agent/clusterchecks/
       parent: containers_cluster
-      weight: 503
+      weight: 603
     - name: Endpoint Checks
       identifier: containers_cluster_agent_endpoint_checks
       url: containers/cluster_agent/endpointschecks/
       parent: containers_cluster
-      weight: 504
+      weight: 604
     - name: Admission Controller
       identifier: containers_cluster_agent_admission_controller
       url: containers/cluster_agent/admission_controller/
       parent: containers_cluster
-      weight: 505
+      weight: 605
     - name: Amazon ECS
       url: containers/amazon_ecs/
       parent: containers
       identifier: containers_amazon_ecs
-      weight: 6
+      weight: 7
     - name: APM
       url: containers/amazon_ecs/apm/
       parent: containers_amazon_ecs
       identifier: containers_amazon_ecs_apm
-      weight: 601
+      weight: 701
     - name: Log collection
       url: containers/amazon_ecs/logs/
       parent: containers_amazon_ecs
       identifier: containers_amazon_ecs_logs
-      weight: 602
+      weight: 702
     - name: Tag extraction
       url: containers/amazon_ecs/tags/
       parent: containers_amazon_ecs
       identifier: containers_amazon_ecs_tags
-      weight: 603
+      weight: 703
     - name: Data collected
       url: containers/amazon_ecs/data_collected/
       parent: containers_amazon_ecs
       identifier: containers_amazon_ecs_data_collected
-      weight: 604
+      weight: 704
     - name: AWS Fargate
       url: integrations/ecs_fargate/
       parent: containers
       identifier: ecs_fargate
-      weight: 7
+      weight: 8
     - name: Datadog Operator
       url: containers/datadog_operator
       identifier: containers_datadog_operator
       parent: containers
-      weight: 8
+      weight: 9
     - name: Advanced Install
       url: containers/datadog_operator/advanced_install
       identifier: containers_datadog_operator_installation
       parent: containers_datadog_operator
-      weight: 801
+      weight: 901
     - name: Configuration
       url: containers/datadog_operator/config
       identifier: containers_datadog_operator_configuration
       parent: containers_datadog_operator
-      weight: 802
+      weight: 902
     - name: Custom Checks
       url: containers/datadog_operator/custom_check
       identifier: containers_datadog_operator_customchecks
       parent: containers_datadog_operator
-      weight: 803
+      weight: 903
     - name: Data Collected
       url: containers/datadog_operator/data_collected
       identifier: containers_datadog_operator_datacollected
       parent: containers_datadog_operator
-      weight: 804
+      weight: 904
     - name: kubectl Plugin
       url: containers/datadog_operator/kubectl_plugin
       identifier: containers_datadog_operator_kubectlplugin
       parent: containers_datadog_operator
-      weight: 805
+      weight: 905
     - name: Secret Management
       url: containers/datadog_operator/secret_management
       identifier: containers_datadog_operator_secretmanagement
       parent: containers_datadog_operator
-      weight: 806
+      weight: 906
     - name: DatadogDashboard CRD
       url: containers/datadog_operator/crd_dashboard
       identifier: containers_datadog_operator_crd_dashboard
       parent: containers_datadog_operator
-      weight: 807
+      weight: 907
     - name: DatadogMonitor CRD
       url: containers/datadog_operator/crd_monitor
       identifier: containers_datadog_operator_crd_monitor
       parent: containers_datadog_operator
-      weight: 808
+      weight: 908
     - name: DatadogSLO CRD
       url: containers/datadog_operator/crd_slo
       identifier: containers_datadog_operator_crd_slo
       parent: containers_datadog_operator
-      weight: 809
+      weight: 909
     - name: Troubleshooting
       url: containers/troubleshooting/
       parent: containers
       identifier: containers_troubleshooting
-      weight: 9
+      weight: 10
     - name: Duplicate hosts
       url: containers/troubleshooting/duplicate_hosts
       parent: containers_troubleshooting
       identifier: containers_troubleshooting_duplicate_hosts
-      weight: 901
+      weight: 1001
     - name: Cluster Agent
       url: containers/troubleshooting/cluster-agent
       parent: containers_troubleshooting
       identifier: containers_troubleshooting_cluster_agent
-      weight: 902
+      weight: 1002
     - name: Cluster Checks
       url: containers/troubleshooting/cluster-and-endpoint-checks
       parent: containers_troubleshooting
       identifier: containers_troubleshooting_cluster_and_endpoint_checks
-      weight: 903
+      weight: 1003
     - name: HPA and Metrics Provider
       url: containers/troubleshooting/hpa
       parent: containers_troubleshooting
       identifier: containers_troubleshooting_hpa
-      weight: 904
+      weight: 1004
     - name: Admission Controller
       url: containers/troubleshooting/admission-controller
       parent: containers_troubleshooting
       identifier: containers_troubleshooting_admission_controller
-      weight: 905
+      weight: 1005
     - name: Guides
       url: containers/guide
       parent: containers
       identifier: containers_guide
-      weight: 10
+      weight: 11
     - name: Processes
       url: infrastructure/process
       identifier: process

content/en/bits_ai/bits_ai_dev_agent/_index.md

@@ -27,7 +27,7 @@ Bits AI Dev Agent is available for the following Datadog products:
 | [Code Security][2]        | Preview              | Remediates code vulnerabilities individually or in bulk    |
 | [Test Optimization][4]    | Preview              | Provides code fixes for flaky tests and verifies that tests remain stable                                                         |
 | [Continuous Profiler][3]  | Preview              | Provides code changes for [Automated Analysis][10] insights                  |
-| [Containers][12]          | Preview              | Provides code changes for Container Recommendations                  |
+| [Containers][12]          | Preview              | Provides code changes for [Kubernetes Remediations][13]                  |
 
 **Note**: Enabling Bits AI Dev Agent is product-specific. Even if it's active for one Datadog product, it must be separately enabled for each additional product you use.
 
@@ -119,3 +119,4 @@ To enable Bits AI Dev Agent, see [Setup][6].
 [10]: /profiler/automated_analysis/
 [11]: /tracing/trace_explorer/
 [12]: /containers/
+[13]: /containers/bits_ai_kubernetes_remediation

content/en/containers/bits_ai_kubernetes_remediation.md

@@ -0,0 +1,59 @@
+---
+title: Bits AI Kubernetes Remediation
+description: Discover and automatically remediate Kubernetes errors with Bits AI Kubernetes Remediation
+further_reading:
+  - link: 'https://www.datadoghq.com/blog/kubernetes-active-remediation-ai/'
+    tag: 'blog'
+    text: 'Accelerate Kubernetes issue resolution with AI-powered guided remediation'
+---
+
+Bits AI Kubernetes Remediation analyzes and fixes Kubernetes errors in your infrastructure.
+
+The following Kubernetes errors are supported:
+- `CrashLoopBackOff`
+- `ErrImagePull`
+- `ImagePullBackOff`
+- `OOMKilled`
+- `CreateContainerError`
+- `CreateContainerConfigError`
+
+## Usage
+
+You can launch Bits AI Kubernetes Remediation from multiple locations within Datadog:
+- **From a Kubernetes monitor**: In the _Troubleshooting_ section, select a workload under _Problematic Workloads_.
+- **From [Kubernetes Explorer][2]**: Hover over an error to see more information about the alert and the affected workload(s), and click _Start Remediation_.
+- **From the [Kubernetes Remediation][1] tab**: Select a workload from the list.
+
+Any one of these actions opens a Remediation side panel that displays:
+
+- An AI-powered explanation for root cause, based on collected telemetry and known patterns
+- Recommended next steps, which you may be able to [perform directly from Datadog](#remediate-from-datadog)
+- Related information, including recent deployments, error logs, Kubernetes events, etc.
+
+{{< img src="containers/remediation/side_panel2.png" alt="Remediation side panel opened for a workload with a CrashLoopBackOff error. Displays a What Happened section with a Bits AI-powered explanation of the error's root cause. Below, a Recommended Next Steps section where the user can inspect the workload manifest. Step-by-step instructions for a suggested fix are also displayed." style="width:80%;" >}}
+
+### Remediate from Datadog
+
+If your repositories are [connected to Datadog][4], and an error can be fixed by changing code in one of these connected repositories, then you can use Bits AI to perform the remediation action directly from Datadog. For other problem scenarios, Bits AI provides a detailed list of remediation steps to follow.
+
+{{% collapse-content title="Example: Increasing memory limit for a deployment" level="h4" expanded=true id="example-pr" %}}
+
+{{< img src="containers/remediation/bitsai_action2.mp4" alt="In a Remediation side panel, the Recommended Next Steps section suggests that the user 'Increase memory limit'. The user enters a new value for the memory limit, increasing it from 10 mebibytes to 20 mebibytes. Clicking Fix with Bits AI brings up a dialog that prompts the user to select a connected repository. " video="true" style="width:80%;" >}}
+
+When a pod is terminated because the memory usage exceeded its limit, you may be able to fix the error by increasing your container's memory limit.
+
+1. Click **Edit Memory Limit**.
+2. Adjust your limit so that it is higher than what your container normally uses.
+3. Click **Fix with Bits AI**.
+4. On the next page, select the repository where your deployment is defined, and review the proposed changes. Click **Fix with Bits** to create a pull request.
+5. You are redirected to a Bits [Code Session][3], where you can verify that the Bits AI Dev Agent identified the specific configuration file where your memory limits are defined. Click **View Pull Request** to view the pull request in GitHub.
+{{% /collapse-content %}}
+
+## Further reading
+
+{{< partial name="whats-next/whats-next.html" >}}
+
+[1]: https://app.datadoghq.com/orchestration/remediation
+[2]: https://app.datadoghq.com/orchestration/explorer/pod
+[3]: https://app.datadoghq.com/code?tab=my-sessions
+[4]: https://docs.datadoghq.com/integrations/guide/source-code-integration/?tab=githubsaasonprem#connect-your-git-repositories-to-datadog