Docs: TinyMCE AI updates from review feedback

kemister85 · kemister85 · commit 6ed3a99d98c8 · 2026-03-25T22:19:18.000+10:00
- Nav: move legacy AI Assistant under TinyMCE AI; rename plugin nav to Plugin configuration
- Introduction: early access messaging, trial/portal, regional LLM note, on-premises partial
- Chat: demo before Using Chat; drop redundant screenshot; clarify chat history note
- Actions: menu/control ID column; fix table syntax; rename API column for accuracy
- Integration options: CDN or self-hosted; hosted AI vs on-premises AI early access
- API quick start: remove multi-region Cloud section
- Limits, models, options, JWT intro: contact link, model stability note, languages, token provider
diff --git a/modules/ROOT/images/tinymceai/tinymce-ai-chat-editor-with-ai-chat-sidebar-open.png b/modules/ROOT/images/tinymceai/tinymce-ai-chat-editor-with-ai-chat-sidebar-open.png
diff --git a/modules/ROOT/nav.adoc b/modules/ROOT/nav.adoc
@@ -254,12 +254,6 @@
 ** Premium plugins
 *** xref:a11ychecker.adoc[Accessibility Checker]
 *** xref:advanced-typography.adoc[Advanced Typography]
-*** xref:ai.adoc[AI Assistant]
-**** xref:ai-openai.adoc[OpenAI ChatGPT integration guide]
-**** xref:ai-azure.adoc[Azure AI integration guide]
-**** xref:ai-bedrock.adoc[Amazon Bedrock integration guide]
-**** xref:ai-gemini.adoc[Google Gemini integration guide]
-**** xref:ai-proxy.adoc[AI proxy server reference guide]
 *** TinyMCE AI
 **** xref:tinymceai-introduction.adoc[Introduction]
 **** xref:tinymceai-chat.adoc[Chat]
@@ -268,7 +262,7 @@
 **** xref:tinymceai-models.adoc[AI Models]
 **** xref:tinymceai-limits.adoc[Limits]
 **** xref:tinymceai-integration-options.adoc[Integration Options]
-***** xref:tinymceai.adoc[Plugin quick start]
+***** xref:tinymceai.adoc[Plugin configuration]
 ***** REST API
 ****** xref:tinymceai-api-overview.adoc[API Overview]
 ****** xref:tinymceai-api-quick-start.adoc[API quick start]
@@ -278,6 +272,12 @@
 ***** Guides
 ****** xref:tinymceai-with-jwt-authentication-nodejs.adoc[JWT authentication (Node.js)]
 ****** xref:tinymceai-with-jwt-authentication-php.adoc[JWT authentication (PHP)]
+*** xref:ai.adoc[AI Assistant (legacy)]
+**** xref:ai-openai.adoc[OpenAI ChatGPT integration guide]
+**** xref:ai-azure.adoc[Azure AI integration guide]
+**** xref:ai-bedrock.adoc[Amazon Bedrock integration guide]
+**** xref:ai-gemini.adoc[Google Gemini integration guide]
+**** xref:ai-proxy.adoc[AI proxy server reference guide]
 *** xref:casechange.adoc[Case Change]
 *** xref:checklist.adoc[Checklist]
 *** Comments
diff --git a/modules/ROOT/pages/tinymceai-actions-plugin.adoc b/modules/ROOT/pages/tinymceai-actions-plugin.adoc
@@ -98,46 +98,64 @@ By default, the Quick Actions feature includes several built-in actions that spe
 Custom actions can be added to the list, and default actions can be removed or reordered by configuring `tinymceai_quickactions_menu`. See xref:tinymceai-actions-plugin.adoc#configuring-quick-actions-menu[Configuring Quick Actions menu].
 
 [[quick-actions-reference-table]]
-The following table lists built-in Quick Actions. The **Editor command** column is the menu label. The **API action** column is the identifier: for preview actions it is the `actionName` segment in `+/v1/actions/system/{actionName}/calls+` (see xref:tinymceai-actions-plugin.adoc#actions-api[Actions API]); for Chat commands it is the prompt id used with the xref:tinymceai-chat.adoc[Conversations API], not a system `actionName`. Configure the Translate submenu in the UI with `tinymceai_languages`.
+The following table lists built-in Quick Actions. The **Editor command** column is the menu label. The **Menu or control ID** column lists values used in `tinymceai_quickactions_menu`, `tinymceai_quickactions_chat_prompts`, `tinymceai_quickactions_change_tone_menu`, and the toolbar when adding individual controls (see xref:tinymceai-actions-plugin.adoc#configuring-quick-actions-menu[Configuring Quick Actions menu]). The **System `actionName` or quick-action prompt id** column is the service identifier: for preview actions it is the `actionName` path segment in `+/v1/actions/system/{actionName}/calls+` (see xref:tinymceai-actions-plugin.adoc#actions-api[Actions API]); for Chat commands it is the built-in quick-action prompt id (`explain`, `summarize`, `highlight-key-points`) used when opening xref:tinymceai-chat.adoc[Chat] with a pre-filled prompt—not a system `actionName` and not sent on the system actions path.
 
-[cols="1,2,4,^,^",options="header"]
+[cols="1,3,2,3,1,1",options="header"]
 |===
-|Editor command |API action |Description |Editor UI |API
+|Editor command |Menu or control ID |System `actionName` or quick-action prompt id |Description |Editor UI |API
 
-|**Explain** |`explain` |Opens Chat with the selected text and a pre-filled prompt. Uses the Conversations API, not the system actions path. |✓ |—
+|**Explain** |`ai-chat-explain` |`explain` |Opens Chat with the selected text and a pre-filled prompt. Uses the Conversations API, not the system actions path. |✓ |—
 
-|**Summarize** |`summarize` |Opens Chat with a summarize prompt. Uses the Conversations API, not the system actions path. |✓ |—
+|**Summarize** |`ai-chat-summarize` |`summarize` |Opens Chat with a summarize prompt. Uses the Conversations API, not the system actions path. |✓ |—
 
-|**Highlight key points** |`highlight-key-points` |Opens Chat with a key-points prompt. Uses the Conversations API, not the system actions path. |✓ |—
+|**Highlight key points** |`ai-chat-highlight-key-points` |`highlight-key-points` |Opens Chat with a key-points prompt. Uses the Conversations API, not the system actions path. |✓ |—
 
-|**Improve Writing** |`improve-writing` |Enhance clarity, word choice, and sentence structure. |✓ |✓
+|**Improve Writing** |`ai-quickactions-improve-writing` |`improve-writing` |Enhance clarity, word choice, and sentence structure. |✓ |✓
 
-|**Continue Writing** |`continue` |Complete unfinished sentences, paragraphs, or entire documents. |✓ |✓
+|**Continue Writing** |`ai-quickactions-continue-writing` |`continue` |Complete unfinished sentences, paragraphs, or entire documents. |✓ |✓
 
-|**Fix Grammar** |`fix-grammar` |Correct grammar, spelling, and punctuation errors. |✓ |✓
+|**Fix Grammar** |`ai-quickactions-check-grammar` |`fix-grammar` |Correct grammar, spelling, and punctuation errors. |✓ |✓
 
-|**Adjust length**
-a|
-`make-shorter` +
-`make-longer`
-|Shorten or lengthen the selection. Each option is its own system action. |✓ |✓
+|**Adjust length** |`ai-quickactions-change-length` |`make-shorter`, `make-longer` |Shorten or lengthen the selection. Each option is its own system action. |✓ |✓
 
 |**Adjust Tone**
 a|
+`ai-quickactions-change-tone` +
+`ai-quickactions-tone-casual` +
+`ai-quickactions-tone-direct` +
+`ai-quickactions-tone-friendly` +
+`ai-quickactions-tone-confident` +
+`ai-quickactions-tone-professional`
+a|
 `make-tone-casual` +
 `make-tone-direct` +
 `make-tone-friendly` +
 `make-tone-confident` +
 `make-tone-professional`
 |Change writing style; each menu option maps to its own system action. |✓ |✓
 
-|**Translate** |`translate` |Convert content between languages. Request body uses `args: { language: string }` with values such as `english`, `spanish`, `russian`, `swedish`, `german`, `japanese`, `portuguese`, `korean`, `italian`, or `chinese`. Configure the editor submenu with `tinymceai_languages`. |✓ |✓
+|**Translate**
+a|
+`ai-quickactions-translate` +
+`ai-quickactions-translate-english` +
+`ai-quickactions-translate-spanish` +
+`ai-quickactions-translate-russian` +
+`ai-quickactions-translate-swedish` +
+`ai-quickactions-translate-german` +
+`ai-quickactions-translate-japanese` +
+`ai-quickactions-translate-portuguese` +
+`ai-quickactions-translate-korean` +
+`ai-quickactions-translate-italian` +
+`ai-quickactions-translate-chinese`
+a|
+`translate`
+|Convert content between languages. Request body uses `args: { language: string }` with values such as `english`, `spanish`, `russian`, `swedish`, `german`, `japanese`, `portuguese`, `korean`, `italian`, or `chinese`. Configure the editor submenu with `tinymceai_languages`. |✓ |✓
 |===
 
 [NOTE]
 ====
-* A checkmark in the Editor UI column means the action can appear when included in `tinymceai_quickactions_menu` (and related sub-menu options such as `tinymceai_quickactions_chat_prompts`).
-* A checkmark in the API column means the action is invoked through the system Actions API path `+/v1/actions/system/{actionName}/calls+`. An em dash means the command is Chat-based and uses the Conversations API instead.
+* A checkmark in the **Editor UI** column means the action can appear when included in `tinymceai_quickactions_menu` (and related sub-menu options such as `tinymceai_quickactions_chat_prompts`).
+* A checkmark in the **API** column means the action is invoked through the system Actions API path `+/v1/actions/system/{actionName}/calls+`. An em dash means the command is Chat-based and uses the Conversations API instead.
 ====
 
 For system action endpoints, schemas, and streaming details, see the https://tinymceai.api.tiny.cloud/docs#tag/Actions[Actions API] reference.
diff --git a/modules/ROOT/pages/tinymceai-api-quick-start.adoc b/modules/ROOT/pages/tinymceai-api-quick-start.adoc
@@ -42,7 +42,7 @@ After signing up, access to the link:{accountpageurl}[customer dashboard (Custom
 
 Log in to the link:{accountpageurl}[Customer Portal] and navigate to link:{accountjwturl}["JWT Keys"].
 
-image::tinymceai/tinymce-ai-customer-portal-jwt-keys-page.png[JWT Keys page showing Secure Keys List, Generate New Keypair, and Import Public Key sections,width=80%]
+image::tinymceai/tinymce-ai-customer-portal-jwt-keys-page.png[JWT Keys page showing Secure Keys List, Generate New Keypair, and Import Public Key sections,width=100%]
 
 During the free trial, the demo identity service can provide JWT tokens without creating a custom token endpoint. See xref:tinymceai-jwt-authentication-intro.adoc#trial-demo-identity-service[Trial: demo identity service] in the JWT Authentication guide for a quick start.
 
@@ -56,11 +56,6 @@ The next step for production is to create a security token endpoint in the appli
 
 To create a custom security token endpoint, generate a keypair in the link:{accountjwturl}[JWT Keys] area of the Customer Portal. In the "Generate New Keypair" section, enter a description, select the key length, and click "Add Key". Alternatively, use "Import Public Key" to add an existing key.
 
-[[cloud-region]]
-== Cloud region
-
-Cloud Services can reside in either US or EU region or in both. The region is set per subscription and cannot be changed for existing environments. For Custom plan with multi-region, the region can be chosen during environment creation.
-
 [[api-integration]]
 == API Integration
 
diff --git a/modules/ROOT/pages/tinymceai-chat.adoc b/modules/ROOT/pages/tinymceai-chat.adoc
@@ -14,10 +14,15 @@ The Chat feature is available as a plugin UI and through the Conversations API.
 * Plugin sections describe user-facing features and configuration (xref:tinymceai.adoc#options-chat[Chat configuration]).
 * API sections cover REST API access (starting at xref:tinymceai-chat.adoc#conversations-api[Conversations API]).
 
+[[demo]]
+== Demo
+
+liveDemo::tinymceai[]
+
 [[using-chat]]
 == Using Chat
 
-image::tinymceai/tinymce-ai-chat-editor-with-ai-chat-sidebar-open.png[{pluginname} Chat interface showing the conversational AI assistant,width=80%]
+The <<demo,interactive demo>> above shows the Chat sidebar open beside the document. The following sections describe how Chat behaves in the editor.
 
 [[working-with-the-document]]
 === Working with the document
@@ -36,11 +41,6 @@ Users can chat with the AI and use it to introduce changes to the document. Ask
 
 The chat feature accelerates the creative process. Begin with a blank document and ask the AI for ideas. Build content step by step by chatting and applying changes. Then review or have the AI rewrite the final draft for best results, all in one place.
 
-[[demo]]
-== Demo
-
-liveDemo::tinymceai[]
-
 [[integration]]
 == Integration
 
@@ -148,11 +148,6 @@ tinymce.init({
 
 When asking the AI for changes to the document, for instance, _"Bold key facts in the document"_, the AI proposes a series of changes. The changes are displayed directly in the document content, making it easy to see what will be modified.
 
-[NOTE]
-====
-AI output may need review. The chat interface displays this reminder below the prompt input.
-====
-
 [[previewing-changes]]
 === Previewing changes
 
@@ -193,9 +188,7 @@ Any conversation from the chat history can be continued as long as the AI model
 
 [NOTE]
 ====
-The ability to apply suggestions to the document or generate Suggested Edits from historical conversations may be restricted in some scenarios:
-
-After closing the browser and reopening AI chat, previous conversations will no longer interact with the document content. To continue working with a conversation, reopen it from the chat history.
+After starting a new browser session, opening AI Chat does not restore an active link between the editor and a previous conversation's pending suggestions. To apply or dismiss suggestions from an earlier conversation, open that conversation again from Chat history so the editor and the conversation are connected in the current session.
 ====
 
 [[conversations-api]]
diff --git a/modules/ROOT/pages/tinymceai-integration-options.adoc b/modules/ROOT/pages/tinymceai-integration-options.adoc
@@ -13,14 +13,21 @@
 
 |
 [.lead]
-xref:tinymceai.adoc[**Plugin Quick Start**]
+xref:tinymceai.adoc[**Plugin configuration**]
 
-Integrate AI features directly into the TinyMCE editor interface. Works with CDN or self-hosted TinyMCE installations. A quick way to add AI capabilities to the editor.
+Integrate {pluginname} features directly into the {productname} editor interface. Works with the {cloudname} CDN or self-hosted {productname}; both use the hosted AI service with JWT authentication.
 
 |
 [.lead]
 xref:tinymceai-api-overview.adoc[**AI service**]
 
 Use the AI service API to build custom integrations and workflows. Suitable for server-side processing, custom UI implementations, and advanced use cases. Start with the xref:tinymceai-api-quick-start.adoc[API Quick Start] guide.
 
-|===
+|
+[.lead]
+**On-Premises Deployment**
+
+include::partial$misc/tinymceai-on-premises-early-access-note.adoc[]
+
+a|
+|===
diff --git a/modules/ROOT/pages/tinymceai-introduction.adoc b/modules/ROOT/pages/tinymceai-introduction.adoc
@@ -24,17 +24,22 @@ Teams can implement a full suite of AI writing tools quickly, delivering efficie
 The core components of {pluginname} are:
 
 * **xref:introduction-to-tinymce.adoc[{productname}]**: A modern rich text editor with dozens of features that improve writing workflows, including collaboration.
-* **xref:tinymceai-api-overview.adoc[AI service]**: A state-of-the-art back-end AI engine that incorporates multiple models and delivers high-quality content. *Currently available in Cloud setup only.* See xref:tinymceai-introduction.adoc#on-premises-deployment[On-Premises Deployment] for deployment options.
+* **xref:tinymceai-api-overview.adoc[AI service]**: A state-of-the-art back-end AI engine that incorporates multiple models and delivers high-quality content. *The hosted AI service is currently available in Cloud setup only.*
+
+include::partial$misc/tinymceai-on-premises-early-access-note.adoc[]
 
 [[features]]
 == {pluginname} features
 
-There are three main features of {pluginname}. All features can be tested using the free trial.
+There are three main features of {pluginname}.
 
 * xref:tinymceai-chat.adoc[**Chat**]: Interactive AI chats with history and persistent context.
 * xref:tinymceai-review-plugin.adoc[**Review**]: Content analysis and proofreading, optimized for larger content.
 * xref:tinymceai-actions-plugin.adoc[**Actions**]: Fast, stateless operations for specific tasks.
 
+[NOTE]
+Existing customers on paid plans can request a full featured free trial through the link:{accountpageurl}[Customer Portal].
+
 [[integration-options]]
 == Integration Options
 
@@ -53,10 +58,7 @@ Developers can control access to AI features, models, and capabilities based on
 
 All data stored by {pluginname} follows the region settings of the {productname} Cloud Services environment, ensuring compliance with data residency requirements and optimal performance for the geographic location.
 
-[IMPORTANT]
-====
-Data sent to LLM providers for processing is currently processed in the US region, regardless of the Cloud Services environment region.
-====
+NOTE: Data sent to LLM providers for processing is currently handled in the US region, regardless of the Cloud Services environment region. {productname} does not offer separate LLM processing regions to choose from.
 
 [[data-retention-policy]]
 === Data Retention Policy
@@ -77,7 +79,4 @@ All data is encrypted in transit and at rest with end-to-end encryption. Convers
 
 On-premises deployment allows the AI service to run within an organization's infrastructure, giving teams more control over data and infrastructure.
 
-[NOTE]
-====
-On-premises deployment is currently in development. link:{contactpage}[Contact {supportname}] for availability updates and timeline information.
-====
+include::partial$misc/tinymceai-on-premises-early-access-note.adoc[]
diff --git a/modules/ROOT/pages/tinymceai-jwt-authentication-intro.adoc b/modules/ROOT/pages/tinymceai-jwt-authentication-intro.adoc
@@ -237,7 +237,7 @@ tinymce.init({
   plugins: 'tinymceai',
   toolbar: 'tinymceai-chat tinymceai-quickactions tinymceai-review',
   tinymceai_token_provider: () => {
-    return fetch('https://example.com/cs-token-endpoint', {
+    return fetch('http://localhost:3000/jwt', {
       method: 'POST',
       headers: { 'Content-Type': 'application/json' },
     }).then(response => response.json());
@@ -250,8 +250,6 @@ tinymce.init({
 The editor will not be ready to use until the first token is obtained from the token endpoint. If an error occurs during the initial request, the editor will not start correctly.
 ====
 
-For more advanced token request customization, see xref:tinymceai-with-jwt-authentication-nodejs.adoc#configure-tinymce[Configure {productname}] in the implementation guides.
-
 [[token-responses]]
 == Responses from the Token Endpoint
 
diff --git a/modules/ROOT/pages/tinymceai-limits.adoc b/modules/ROOT/pages/tinymceai-limits.adoc
@@ -18,7 +18,7 @@ This page describes the limits that ensure fair usage, optimal performance, and
 
 Rate limits control the frequency of requests to prevent abuse and ensure service stability. These limits apply to both plugin usage and direct API calls, as the plugin uses the API under the hood. The service implements limits on requests, token usage, web search, and web scraping requests per minute. All rate limits are applied at both organization level (higher limits) and individual user level (lower limits) to ensure fair usage.
 
-NOTE: Specific rate limit values are subject to change and may vary based on the subscription tier. Contact support for current rate limit details for the environment.
+NOTE: Specific rate limit values are subject to change and may vary based on the subscription tier. For current rate limit details for the environment, link:{contactpage}[contact {supportname}].
 
 [[context-limits]]
 == Context Limits
diff --git a/modules/ROOT/pages/tinymceai-models.adoc b/modules/ROOT/pages/tinymceai-models.adoc
diff --git a/modules/ROOT/partials/configuration/tinymceai_options.adoc b/modules/ROOT/partials/configuration/tinymceai_options.adoc
diff --git a/modules/ROOT/partials/misc/tinymceai-on-premises-early-access-note.adoc b/modules/ROOT/partials/misc/tinymceai-on-premises-early-access-note.adoc
