AI Action

AI Action allows you to integrate AI capabilities into your playbooks by leveraging the rich context that Mission Control maintains about your infrastructure. When executed against configs or components, the AI action automatically injects:

• Component/config manifests and specifications
• Related configurations with configurable relationship depth
• Historical analysis data within the specified time period
• Change history across related infrastructure within defined time ranges

This comprehensive context enables AI models to provide more informed analysis and insights about your infrastructure state and relationships. For example, when a Kubernetes pod fails, it examines the pod spec, ConfigMap changes, service logs together, revealing patterns that single-component analysis might overlook.

diagnose-kubernetes-resource.yaml
---
# yaml-language-server: $schema=../../config/schemas/playbook.schema.json
apiVersion: mission-control.flanksource.com/v1
kind: Playbook
metadata:
  name: diagnose-kubernetes-resource
spec:
  description: Use AI to diagnose unhealthy kubernetes resources
  configs:
    - types:
        - Kubernetes::DaemonSet
        - Kubernetes::Deployment
        - Kubernetes::Pod
        - Kubernetes::StatefulSet
  parameters:
    - name: prompt
      label: Prompt
      default: Find out why {{.config.name}} is unhealthy
      properties:
        multiline: 'true'
  actions:
    - name: query
      ai:
        connection: connection://mc/anthropic
        systemPrompt: |
          **Role:** Seasoned Kubernetes engineer and Diagnostic Expert

          **Objective:** Assist users in diagnosing issues with unhealthy Kubernetes resources by analyzing provided manifests and related resources.

          **Instructions:**

          1. **Resource Analysis:** Examine the manifest of the unhealthy resource thoroughly.
          2. **Contextual Investigation:** Consider additional related resources provided (e.g., pods, replica sets, namespaces) to gain a comprehensive understanding of the issue.
          3. **Diagnostic Steps:** Clearly outline the steps taken during the investigation, focusing on precision and brevity.
          4. **One-Time Diagnosis:** Aim to diagnose the issue in a single response without requiring follow-up questions.

          **Output:** Provide a concise diagnosis and potential solutions based on the analysis.
        prompt: '{{.params.prompt}}'
        changes:
          since: 2d
        analysis:
          since: 2d
        relationships:
          - depth: 3
            direction: outgoing
            changes:
              since: 24h
          - depth: 5
            direction: incoming
            changes:
              since: 24h

Field	Description	Scheme
name*	Step Name	string
prompt*	Main prompt	string
systemPrompt*	Context-setting system prompt	string
analysis.since	Select the analysis of the playbook resource to feed into the AI	Duration
apiKey	AI service API key
apiURL	Custom API endpoint (applicable when behind a proxy or using Ollama)	string
backend	LLM provider
changes.since	Select the changes of the playbook resource to feed into the AI	Duration
connection	Connection string for the LLM	string
formats	Output format. (Only markdown supported as of now)
model	LLM model (e.g. gpt-4)	string
relationships	Select the related configs and their changes and analysis to feed into the AI
delay	A delay before running the action e.g. 8h
filter	Conditionally run an action
runsOn	Which runner (agent) to run the action on
templatesOn	Where templating (and secret management) of actions should occur
timeout	Timeout on this action.	Duration

Relationship

The AI Action can maintain relationships with other elements:

Field	Description	Scheme
analysis.since	Select the analysis of the related resources to feed into the AI	Duration
changes.since	Select the changes of the related resources to feed into the AI	Duration
depth	Depth of the relationship	integer
direction	Direction of the relationship

Templating

CEL Expressions

The following variables can be used within the CEL expressions of filter, if, delays and parameters.default:

Field	Description	Schema
config	Config passed to the playbook	ConfigItem
component	Component passed to the playbook	Component
check	Canary Check passed to the playbook	Check
playbook	Playbook passed to the playbook	Playbook
run	Current run	Run
params	User provided parameters to the playbook	map[string]any
request	Webhook request	Webhook Request
env	Environment variables defined on the playbook	map[string]any
user.name	Name of the user who invoked the action	string
user.email	Email of the user who invoked the action	string
agent.id	ID of the agent the resource belongs to.	string
agent.name	Name of the agent the resource belongs to.	string

Conditionally Running Actions

Playbook actions can be selectively executed based on CEL expressions. These expressions must either return

• a boolean value (true indicating run the action & skip the action otherwise)
• or a special function among the ones listed below

Function	Description
always()	run no matter what; even if the playbook is cancelled/fails
failure()	run if any of the previous actions failed
skip()	skip running this action
success()	run only if all previous actions succeeded (default)
timeout()	run only if any of the previous actions timed out

delete-kubernetes-pod.yaml
---
apiVersion: mission-control.flanksource.com/v1
kind: Playbook
metadata:
  name: notify-send-with-filter
spec:
  parameters:
    - name: message
      label: The message for notification
      default: '{{.config.name}}'
  configs:
    - types: 
        - Kubernetes::Pod
  actions:
    - name: Send notification
      exec:
        script: notify-send "{{.config.name}} was created"
    - name: Bad script
      exec:
        script: deltaforce
    - name: Send all success notification
      if: success() # this filter practically skips this action as the second action above always fails
      exec:
        script: notify-send "Everything went successfully"
    - name: Send notification regardless
      if: always()
      exec:
        script: notify-send "a Pod config was created"

Defaulting Parameters

delete-kubernetes-pod.yaml
apiVersion:
  mission-control.flanksource.com/v1
  kind: Playbook
  metadata:
    name: edit
  spec:
    title: 'Edit Kustomize Resource'
    icon: flux
    parameters:
    - default: 'chore: update $(.config.type)/$(.config.name)'
      name: commit_message

Go Templating

When templating actions with Go Templates, the context variables are available as fields of the template's context object . eg .config, .user.email

Templating Actions

delete-kubernetes-pod.yaml
apiVersion: mission-control.flanksource.com/v1
kind: Playbook
metadata:
  name: scale-deployment
spec:
  description: Scale Deployment
  configs:
    - types:
        - Kubernetes::Deployment
  parameters:
    - name: replicas
      label: The new desired number of replicas.
  actions:
    - name: kubectl scale
      exec:
        script: |
          kubectl scale --replicas={{.params.replicas}} \
            --namespace={{.config.tags.namespace}} \
            deployment {{.config.name}}

Functions

Function	Description	Return
getLastAction()	Returns the result of the action that just run	Action Specific
getAction({action})	Return the result of a specific action	Action Specific

Printing out Results

Reusing Action Results

action-results.yaml
apiVersion: mission-control.flanksource.com/v1
kind: Playbook
metadata:
  name: use-previous-action-result
spec:
  description: Creates a file with the content of the config
  configs:
    - types:
        - Kubernetes::Pod
  actions:
    - name: Fetch all changes
      sql:
        query: SELECT id FROM config_changes WHERE config_id = '{{.config.id}}'
        driver: postgres
        connection: connection://postgres/local
    - name: Send notification
      if: 'last_result().count > 0'
      notification:
        title: 'Changes summary for {{.config.name}}'
        connection: connection://slack/flanksource
        message: |
          {{$rows:=index last_result "count"}}
          Found {{$rows}} changes