openops-cloud · gorohoroh · Dec 11, 2025 · Dec 10, 2025 · Dec 10, 2025 · Dec 10, 2025
diff --git a/ai-assistance/llm-connections.mdx b/ai-assistance/llm-connections.mdx
@@ -14,22 +14,22 @@ To enable AI and configure an LLM connection:
 1. In the OpenOps left sidebar, click the **Settings** icon at the bottom:
     <NarrowImage src="/images/access-llm-settings-icon.png" alt="Settings icon" widthPercent={30} />
 2. In the **Settings** view, click **OpenOps AI**:
-![AI providers](/images/access-llm-ai-providers.png)
-3. Switch on the **Enable OpenOps AI** toggle.
-4. In the **Connection** dropdown, select **Create Connection**. The **Create AI Connection** view opens:
+![OpenOps AI settings](/images/access-llm-ai-providers.png)
+3. Under **AI Connection**, click the dropdown and select **Create new connection**. The **Create AI Connection** view opens:
 ![Create AI Connection](/images/access-llm-create-connection.png)
-5. In the **Provider** dropdown, select one of the supported LLM providers. Anthropic, Azure OpenAI, Cerebras, Cohere, Deep Infra, DeepSeek, Google Generative AI, Google Vertex AI, Groq, Mistral, OpenAI, OpenAI-compatible providers, Perplexity, Together.ai, and xAI Grok are currently supported.
-6. In the **Model** dropdown, select one of the models your LLM provider supports. (If you're configuring Azure OpenAI, select **Custom** instead of a model and complete the other [Azure OpenAI-specific steps](#azure-openai).)
-7. (Optional) If the model you're looking for is not listed, specify a custom model in the **Custom model** field. This overrides whatever you've selected under **Model**.
-8. Enter your API key for the selected LLM provider in the **API Key** field.
-9. (Optional) Enter a **Base URL** for the selected model. This is useful if you want to use a proxy or if your LLM provider does not use the default base URL. If you selected _OpenAI Compatible_ as the provider, then you are required to enter the base URL.
-10. (Optional) Use the **Provider settings** and **Model settings** fields to specify custom parameters as JSON. The JSON schema varies depending on the chosen provider and model:
-    * See the [Azure OpenAI](#azure-openai) and [Google Vertex AI](#google-vertex-ai) instructions for custom provider settings required by these providers.
-    * If you've selected OpenAI, use **Provider settings** for JSON you'd normally pass to the `createOpenAI` function, and **Model settings** for JSON you'd normally pass to the `streamText` function. For more details, see the [OpenAI documentation](https://platform.openai.com/docs/api-reference).
-11. Click **Save** to apply your changes in the **Create AI Connection** view.
-12. (Optional) Back in the **AI providers** section, if you're working with AWS and you want your AI connection to have access to AWS MCP servers, click **AWS Cost** in the **MCP** section, and select an [AWS connection](/cloud-access/access-levels-permissions#aws-connections) to use. This enables access to AWS Cost Explorer MCP Server, AWS Pricing MCP Server, and AWS Billing and Cost Management MCP Server.
-![AWS Cost MCP connection](/images/access-llm-mcp.png)
-13. Click **Save** to apply your changes in the **AI providers** section.
+4. In the **Provider** dropdown, select one of the supported LLM providers. Anthropic, Azure OpenAI, Cerebras, Cohere, Deep Infra, DeepSeek, Google Generative AI, Google Vertex AI, Groq, Mistral, OpenAI, OpenAI-compatible providers, Perplexity, Together.ai, and xAI Grok are currently supported.
+5. In the **Model** dropdown, select one of the models your LLM provider supports. (If you're configuring Azure OpenAI, select **Custom** instead of a model and complete the other [Azure OpenAI-specific steps](#azure-openai).)
+6. (Optional) If the model you're looking for is not listed, specify a custom model in the **Custom model** field. This overrides whatever you've selected under **Model**.
+7. Enter your API key for the selected LLM provider in the **API Key** field.
+8. (Optional) Enter a **Base URL** for the selected model. This is useful if you want to use a proxy or if your LLM provider does not use the default base URL. If you selected _OpenAI Compatible_ as the provider, then you are required to enter the base URL.
+9. (Optional) Use the **Provider settings** and **Model settings** fields to specify custom parameters as JSON. The JSON schema varies depending on the chosen provider and model:
+   * See the [Azure OpenAI](#azure-openai) and [Google Vertex AI](#google-vertex-ai) instructions for custom provider settings required by these providers.
+   * If you've selected OpenAI, use **Provider settings** for JSON you'd normally pass to the `createOpenAI` function, and **Model settings** for JSON you'd normally pass to the `streamText` function. For more details, see the [OpenAI documentation](https://platform.openai.com/docs/api-reference).
+10. Click **Save** to apply your changes in the **Create AI Connection** view.
+11. (Optional) Back in the **OpenOps AI** section, if you're working with AWS and you want your AI connection to have access to AWS MCP servers, go to the **MCP** section and select an [AWS connection](/cloud-access/access-levels-permissions/#aws-connections) in the **AWS Cost** dropdown:
+    ![AWS Cost MCP connection](/images/access-llm-mcp.png)
+    This enables access to AWS Cost Explorer MCP Server, AWS Pricing MCP Server, and AWS Billing and Cost Management MCP Server.
+
 
 Configuring an LLM connection enables all [AI assistance features](/ai-assistance/overview) in OpenOps.
 

diff --git a/images/access-connection-from-workflow.png b/images/access-connection-from-workflow.png
diff --git a/images/access-llm-ai-providers.png b/images/access-llm-ai-providers.png
diff --git a/images/access-llm-ask-ai-action.png b/images/access-llm-ask-ai-action.png
diff --git a/images/access-llm-generate-with-ai.png b/images/access-llm-generate-with-ai.png
diff --git a/images/access-llm-mcp.png b/images/access-llm-mcp.png
diff --git a/images/actions-high-risk.png b/images/actions-high-risk.png
diff --git a/images/cookbook/aws-ebs-get-snapshots.png b/images/cookbook/aws-ebs-get-snapshots.png
diff --git a/images/cookbook/aws-get-account-ids-properties.png b/images/cookbook/aws-get-account-ids-properties.png
diff --git a/images/cookbook/azure-command-inside-loop.png b/images/cookbook/azure-command-inside-loop.png
diff --git a/images/cookbook/azure-list-subscriptions-properties.png b/images/cookbook/azure-list-subscriptions-properties.png
diff --git a/images/cookbook/gcp-command-inside-loop.png b/images/cookbook/gcp-command-inside-loop.png
diff --git a/images/cookbook/gcp-list-projects-properties.png b/images/cookbook/gcp-list-projects-properties.png
diff --git a/images/parameters-dynamic-value.png b/images/parameters-dynamic-value.png
diff --git a/images/qsg-aws-step-properties.png b/images/qsg-aws-step-properties.png
diff --git a/images/workflow-editor-action-mandatory-fields.png b/images/workflow-editor-action-mandatory-fields.png
diff --git a/images/workflow-editor-action-properties.png b/images/workflow-editor-action-properties.png
diff --git a/workflow-management/actions.mdx b/workflow-management/actions.mdx
@@ -86,7 +86,6 @@ These actions implement [Human-in-the-Loop](/workflow-management/human-in-the-lo
 * **Linear**: create and update issues and comments.
 * **Zendesk**: create or update tickets, perform other Zendesk API calls.
 
-
 ## Make changes to cloud resources
 
 These are integration actions that provide various ways to make and request changes to your cloud resources via cloud provider APIs, infrastructure-as-code (IaC) tools, or pull requests.
@@ -103,6 +102,9 @@ These are integration actions that provide various ways to make and request chan
     * **GitHub**: retrieve file content, create pull requests, or trigger GitHub Actions runs.
     * **Archera**: apply commitment plans for cloud providers.
 
+Since many of these actions can make destructive changes in your cloud environment, they are considered high-risk and are marked with a red shield icon in the [workflow editor](/workflow-management/building-workflows/):
+<NarrowImage src="/images/actions-high-risk.png" alt="An action with a high-risk warning icon" widthPercent={50} />
+
 ## Interact with project management tools
 
 These actions allow you to retrieve and update data in issues and boards in project management tools.

diff --git a/workflow-management/building-workflows.mdx b/workflow-management/building-workflows.mdx
@@ -155,8 +155,8 @@ Under **Step output**, you can click **Test Step** to test or retest the step in
 Sometimes, the **Test Step** button may be grayed out, like this:
 <NarrowImage src="/images/workflow-editor-action-test-fix-inputs.png" alt="Test button grayed out" />
 
-Your step will also have a yellow warning icon next to it. If this happens, make sure you have filled in every mandatory input field in the step's properties pane. You may need to scroll through the properties pane to see all required fields:
-<NarrowImage src="/images/workflow-editor-action-mandatory-fields.png" alt="Scrolling the properties pane to reveal mandatory input fields" />
+Your step will also have a yellow warning icon next to it. If this happens, make sure you have filled in every mandatory input field in the step's properties pane. You may need to scroll through the properties pane to see all required fields.
+<NarrowImage src="/images/workflow-editor-action-mandatory-fields.png" alt="Mandatory input fields in the properties pane" />
 
 Once you've filled in all mandatory fields, the **Test Step** button becomes active. Click it to run the test and view the output generated by the step:
 <NarrowImage src="/images/workflow-editor-action-generate-sample-data.png" alt="Output data generated for an Umbrella integration action" />