Skip to content
Open
Show file tree
Hide file tree
Changes from 2 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
3 changes: 2 additions & 1 deletion trento-docs-site/modules/user-guide/nav_user_guide.adoc
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
*** xref:trento-mcp-install.adoc[Installing Trento MCP Server]
*** xref:trento-mcp-config.adoc[Configuring Trento MCP Server]
*** xref:trento-mcp-how-to-use.adoc[Using the Trento MCP Server]
** xref:trento-liz-ai-assistant.adoc[Liz AI assistant in Trento Web]
** xref:trento-core-features.adoc[Core Features]
*** xref:trento-user-manage.adoc[User management]
*** xref:trento-sso-integration.adoc[Single Sign-On integration]
Expand All @@ -29,7 +30,7 @@
** xref::trento-compliance-features.adoc[Compliance Features]
*** xref:trento-checks.adoc[Performing configuration checks]
*** xref:trento-checks-customization.adoc[Checks Customization]
** xref:trento-web-console.adoc[Using Trento Web]
** xref:trento-web-console.adoc[Monitoring SAP health in the Trento Web console]

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

just a note: I forgot to update this in the trento web PR, so I am fixing that here

** xref:trento-smlm-integration.adoc[Integration with SUSE Multi-Linux Manager]
** xref:trento-operations.adoc[Operations]
** xref:trento-report-issue.adoc[Reporting an issue]
Expand Down
1 change: 1 addition & 0 deletions trento/adoc/product-attributes.adoc
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@
:tr_mcp_health_port: 8080
:tr_mcp_health_api_path: /api/healthz
:mcp_host: MCPHost
:liz: Liz

// PROJECT REPOSITORY URL
:repo-url: https://github.com/SUSE/doc-[PRODUCT]
Expand Down
1 change: 1 addition & 0 deletions trento/adoc/trento-guide.adoc
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ include::trento-update.adoc[]
include::trento-uninstall.adoc[]
include::trento-integration-prometheus.adoc[]
include::trento-mcp-integration.adoc[]
include::trento-liz-ai-assistant.adoc[]
include::trento-core-features.adoc[]
include::trento-compliance-features.adoc[]
include::trento-web-console.adoc[]
Expand Down
113 changes: 113 additions & 0 deletions trento/adoc/trento-liz-ai-assistant.adoc
Original file line number Diff line number Diff line change
@@ -0,0 +1,113 @@
include::product-attributes.adoc[]

[[sec-trento-liz-ai-assistant]]
== {liz} AI assistant in {tr_web}
:revdate: 2026-09-17

{liz} is a chat-based AI assistant built directly into {tr_web}. It lets you ask questions about your SAP landscape in natural language. By analyzing the live state of your systems and best-practice validations, {liz} helps you actively monitor health and identify issues, all without requiring any additional deployment.

[[sec-about-liz]]
=== About the {liz} AI assistant

Unlike the {tr_mcp}, which is an optional component you install separately to connect external AI tools to {trento}, {liz} is part of {tr_web} itself. You only need to supply an API key for a supported large language model (LLM) provider.
Comment thread
eromanova97 marked this conversation as resolved.
Outdated
Comment thread
eromanova97 marked this conversation as resolved.
Outdated

{liz} is guided by built-in system instructions tailored for {trento}, ensuring it understands your SAP landscape right out of the box.

[IMPORTANT]
.Data privacy
====
{liz} sends your prompts and the system data needed to answer them to the third-party LLM provider you configure. Review your organization's data handling policy before enabling this feature..
Comment thread
eromanova97 marked this conversation as resolved.
Outdated
====

[[sec-liz-providers]]
==== Which providers and models are supported

{liz} AI assistant currently supports the following LLM providers:

* Anthropic Claude
* Google Gemini
* OpenAI GPT

Each provider offers several models. To ensure compatibility, {liz} only displays models capable of powering the assistant.
Comment thread
eromanova97 marked this conversation as resolved.
Outdated
Comment thread
eromanova97 marked this conversation as resolved.
Outdated

[[sec-liz-data-access]]
==== How does {liz} access data

{liz} answers using the same tools the {tr_mcp} exposes: live SAP landscape state from {tr_web}, and check results from {tr_wanda}.
Comment thread
eromanova97 marked this conversation as resolved.
Outdated

Access is bound to your {trento} user account. When you open a chat session, {liz} can only access data you are authorized to see. Your existing {trento} roles and permissions remain unchanged.

[[sec-configuring-liz]]
=== Configuring {liz}

You can configure {liz} from your user profile in {tr_web}.

Requirements:

* A user account in {tr_web}. AI configuration is per user and each user configures their own provider and model.
* An API key for one of the supported providers.
Comment thread
eromanova97 marked this conversation as resolved.
Outdated

To configure {liz}:

[.procedure]
. In the {tr_web} console, click your user icon and select *Profile* to open your profile page.

. Go to the *AI Configuration* section and click *Edit Settings*.

. Select a provider and model from the supported list.

. Enter your API key for the chosen provider.

. Click *Save* to save your configuration.

{liz} becomes available as soon as the configuration is saved.

[NOTE]
====
You can change your model or provider at any time from the *Profile* page. Changes
apply to an active conversation immediately without the need to reload the web console.
Comment thread
eromanova97 marked this conversation as resolved.
Outdated
====

To stop using {liz}, clear your AI configuration from the *Profile* page. The chat launcher is disabled after the configuration is removed.
Comment thread
eromanova97 marked this conversation as resolved.
Outdated
Comment thread
eromanova97 marked this conversation as resolved.
Outdated

[[sec-using-liz]]
=== Using {liz}

Open the chat launcher in {tr_web} and type your question. Your chat session remains active as long as you are logged into the {tr_web} console.

*Example queries:*

* _What is the tuning status of the registered hosts?_
* _Which hosts are affected by patch XYZ?_
* _Provide a summary of checks not passing for cluster XYZ and step-by-step remediation instructions._

If you did not configure a provider and model, the launcher is disabled. See <<sec-configuring-liz>> for more information.

While a conversation is open you can perform the following actions:

[cols="1,7", options="header"]
|===
| Action | Description
| *Stop*
| Stop {liz} processing the current question. The assistant stays available for your next question.
| *Retry*
| Re-send your last prompt.
| *Copy*
| Copy a reply to the clipboard. {liz} formats its responses in Markdown, so pasting into compatible tools (like wikis or issue trackers) preserves the text formatting.
|===

Selecting **Learn more** in the assistant opens the {trento} documentation in a new

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@abravosuse in Liz we have the disclaimer "AI assistants can make mistakes." an then the link to Learn more that opens trento documentation.

Are we good with that link or should we change it to something different?

browser tab.

[WARNING]
====
Clicking *New chat* in {liz} immediately ends the active conversation and clears its history. Previous chats cannot be recovered once a new session starts.
====