From 79fdbd31f13ec1e0ee154748e36e8fe3e038c4cb Mon Sep 17 00:00:00 2001
From: "sg-doc-holiday[bot]"
<219201796+sg-doc-holiday[bot]@users.noreply.github.com>
Date: Wed, 4 Feb 2026 09:29:45 +0000
Subject: [PATCH 1/7] ai-assistance: update overview.mdx
Replace the escaped MDX NarrowImage tag with a normal JSX self-closing component so the page renders correctly in the documentation site.
---
ai-assistance/overview.mdx | 1 -
1 file changed, 1 deletion(-)
diff --git a/ai-assistance/overview.mdx b/ai-assistance/overview.mdx
index 014c576f..e8fa321e 100644
--- a/ai-assistance/overview.mdx
+++ b/ai-assistance/overview.mdx
@@ -32,7 +32,6 @@ AI assistance in OpenOps is available in several forms:
Once enabled, the AI assistant chat becomes available in sidebars in every OpenOps view:
-
You can use it to ask a variety of questions about OpenOps, your cloud resources, and FinOps in general, such as:
* "What can I do in OpenOps and how do I use its [features](/introduction/features-and-benefits/)?"
* "How do I [create a workflow](/workflow-management/building-workflows/) that does what I want to achieve?"
From 5a459ceceef00f2a94a3642c991c2292a739975c Mon Sep 17 00:00:00 2001
From: "sg-doc-holiday[bot]"
<219201796+sg-doc-holiday[bot]@users.noreply.github.com>
Date: Wed, 4 Feb 2026 09:30:15 +0000
Subject: [PATCH 2/7] ai-assistance: update overview.mdx
Fix the remaining escaped NarrowImage tag so the AI Step screenshot renders correctly in MDX.
---
ai-assistance/overview.mdx | 1 -
1 file changed, 1 deletion(-)
diff --git a/ai-assistance/overview.mdx b/ai-assistance/overview.mdx
index e8fa321e..43f84a6b 100644
--- a/ai-assistance/overview.mdx
+++ b/ai-assistance/overview.mdx
@@ -53,7 +53,6 @@ The **AI Step** action lets you run AI prompts in a separate step in your workfl
You add **AI Step** as you would [add any other action](workflow-management/building-workflows#adding-more-actions). You then specify a prompt in the **Prompt** field and any relevant outputs of previous steps in the **Additional input** section:
-
Alternatively, you can combine prompt text and outputs from previous steps in the **Prompt** field.
### Generating commands and queries
From 65075a5f2f947338f9c0d9fd387da0955cb03dee Mon Sep 17 00:00:00 2001
From: "sg-doc-holiday[bot]"
<219201796+sg-doc-holiday[bot]@users.noreply.github.com>
Date: Wed, 4 Feb 2026 09:30:29 +0000
Subject: [PATCH 3/7] ai-assistance: update overview.mdx
Fix the escaped NarrowImage tag for the Generate with AI screenshot so it renders correctly.
---
ai-assistance/overview.mdx | 1 -
1 file changed, 1 deletion(-)
diff --git a/ai-assistance/overview.mdx b/ai-assistance/overview.mdx
index 43f84a6b..7b593dd2 100644
--- a/ai-assistance/overview.mdx
+++ b/ai-assistance/overview.mdx
@@ -59,7 +59,6 @@ Alternatively, you can combine prompt text and outputs from previous steps in th
Whenever you work with an [action](/workflow-management/actions) that requires writing a CLI command or SQL query, you'll see the **Generate with AI** command next to the relevant property in the action's properties pane:
-
When you click **Generate with AI**, use the AI chat window to describe the outcome you want the command or query to achieve, and your LLM will generate it for you:
Click **Inject command** in the AI chat window to insert the generated command into the action's **Command** field.
From 2034f22e9294f5de30fc39d9f953a93932e60572 Mon Sep 17 00:00:00 2001
From: "sg-doc-holiday[bot]"
<219201796+sg-doc-holiday[bot]@users.noreply.github.com>
Date: Wed, 4 Feb 2026 09:31:04 +0000
Subject: [PATCH 4/7] ai-assistance: update overview.mdx
Fix the escaped NarrowImage tag for the AI chat window screenshot so it renders correctly.
---
ai-assistance/overview.mdx | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/ai-assistance/overview.mdx b/ai-assistance/overview.mdx
index 7b593dd2..678ed455 100644
--- a/ai-assistance/overview.mdx
+++ b/ai-assistance/overview.mdx
@@ -60,8 +60,7 @@ Alternatively, you can combine prompt text and outputs from previous steps in th
Whenever you work with an [action](/workflow-management/actions) that requires writing a CLI command or SQL query, you'll see the **Generate with AI** command next to the relevant property in the action's properties pane:
When you click **Generate with AI**, use the AI chat window to describe the outcome you want the command or query to achieve, and your LLM will generate it for you:
-
-Click **Inject command** in the AI chat window to insert the generated command into the action's **Command** field.
+Click **Inject command** in the AI chat window to insert the generated command into the action's **Command** field.
### Generating code steps
From 2ab385482ee332d814f58bf733cfd1764ecd2d50 Mon Sep 17 00:00:00 2001
From: "sg-doc-holiday[bot]"
<219201796+sg-doc-holiday[bot]@users.noreply.github.com>
Date: Wed, 4 Feb 2026 09:41:00 +0000
Subject: [PATCH 5/7] ai-assistance: update overview.mdx
Insert concise guidance on per-chat model selection and how tool output (including errors) can appear in AI assistant replies, aligning with AI chat/tool output changes while keeping existing structure.
---
ai-assistance/overview.mdx | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/ai-assistance/overview.mdx b/ai-assistance/overview.mdx
index 678ed455..633b78b1 100644
--- a/ai-assistance/overview.mdx
+++ b/ai-assistance/overview.mdx
@@ -47,6 +47,25 @@ It can also work with Amazon MCP servers, namely AWS Cost Explorer MCP Server, A
When available, the AI assistant includes reasoning in its replies, showing which tools (such as MCP servers) it used, displaying the raw data retrieved from those tools, and outlining next steps in plain language.
+#### Selecting the model for a chat
+
+OpenOps lets you pick the language model for each AI chat (for example, the assistant chat sidebar and the **Generate with AI** chat in step settings).
+
+To change the model:
+1. Open the AI chat.
+2. In the composer area, use the model selector to pick a different model.
+
+If the model is not supported by the configured provider, OpenOps rejects the selection.
+
+#### Understanding tool output in replies
+
+AI assistant replies can include tool output. For example, when the assistant uses MCP tools, the reply can show:
+* The tool name.
+* The tool input.
+* The tool output.
+
+Some tool outputs are marked as errors. When a tool output is an error, OpenOps still persists and displays the tool output, but it is flagged as an error.
+
### AI Step action
The **AI Step** action lets you run AI prompts in a separate step in your workflow, using outputs of its previous steps as context.
From 9086d52593c049f1a0a58ffbe9806f850a9c6a5b Mon Sep 17 00:00:00 2001
From: "sg-doc-holiday[bot]"
<219201796+sg-doc-holiday[bot]@users.noreply.github.com>
Date: Wed, 4 Feb 2026 09:41:29 +0000
Subject: [PATCH 6/7] getting-started: update user-management.mdx
Add a password requirements section reflecting current validation rules (8-64 characters and allowed special characters including square brackets), and add language tags to HTTP request examples per style guide.
---
getting-started/user-management.mdx | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/getting-started/user-management.mdx b/getting-started/user-management.mdx
index b7c7685f..3c4531a7 100644
--- a/getting-started/user-management.mdx
+++ b/getting-started/user-management.mdx
@@ -10,13 +10,20 @@ When you deploy OpenOps for the first time, it creates an admin user account. Th
The admin user account created this way has exactly one distinction: it can be used to create other user accounts.
+## Password requirements
+
+When setting a user's password (including the initial admin password in `.env`), the password:
+* Is 8-64 characters long.
+* Contains at least one lowercase letter, one uppercase letter, one number, and one special character.
+* Uses only alphanumeric characters and these special characters: `!@#$%^&*()_+-=[]{};':"\\|,.<>/?`.
+
## Creating new user accounts
OpenOps doesn't currently provide a UI for creating user accounts; instead, you can do it with two API calls.
The first API call is to sign in the admin user:
-```
+```http
POST http://your-openops-installation/api/v1/authentication/sign-in
Content-Type: application/json
@@ -28,7 +35,7 @@ Content-Type: application/json
This call will return a JSON object that contains a property called `token`. Copy the value of this property and use it in the authorization header in the next call. This next call actually creates a new user account. Before making the call, in the body, don't forget to specify actual values for the four properties that are left empty in the sample below:
-```
+```http
POST http://your-openops-installation/api/v1/authentication/sign-up
Authorization: Bearer your-admin-token
Content-Type: application/json
From 10ae496042f07141d18216c0ca4bbc9490b3c1f9 Mon Sep 17 00:00:00 2001
From: "sg-doc-holiday[bot]"
<219201796+sg-doc-holiday[bot]@users.noreply.github.com>
Date: Wed, 4 Feb 2026 09:42:45 +0000
Subject: [PATCH 7/7] ai-assistance: update overview.mdx
Demote the added subsection heading to H3 to comply with the style guide (avoid H4 outside long walkthrough guides).
---
ai-assistance/overview.mdx | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/ai-assistance/overview.mdx b/ai-assistance/overview.mdx
index 633b78b1..bf3a0cef 100644
--- a/ai-assistance/overview.mdx
+++ b/ai-assistance/overview.mdx
@@ -57,7 +57,7 @@ To change the model:
If the model is not supported by the configured provider, OpenOps rejects the selection.
-#### Understanding tool output in replies
+### Understanding tool output in replies
AI assistant replies can include tool output. For example, when the assistant uses MCP tools, the reply can show:
* The tool name.