diff --git a/microsoft-edge/developer/index.yml b/microsoft-edge/developer/index.yml
index a59e9b8820..89e9781d91 100644
--- a/microsoft-edge/developer/index.yml
+++ b/microsoft-edge/developer/index.yml
@@ -58,6 +58,12 @@ landingContent:
           - text: Use origin trials in Microsoft Edge
             url: ../origin-trials/index.md
 
+          - text: Prompt a built-in language model with the Prompt API
+            url: ../web-platform/prompt-api.md
+
+          - text: Summarize, write, and rewrite text with the Writing Assistance APIs
+            url: ../web-platform/writing-assistance-apis.md
+
 # -----------------------------------------------------------------------------
 # Card for toc bucket 3 - r1c2
   - title: Microsoft Edge DevTools
diff --git a/microsoft-edge/devtools-guide-chromium/whats-new/2025/05/devtools-136-images/dom-adorner.png b/microsoft-edge/devtools-guide-chromium/whats-new/2025/05/devtools-136-images/dom-adorner.png
new file mode 100644
index 0000000000..34747a7a43
Binary files /dev/null and b/microsoft-edge/devtools-guide-chromium/whats-new/2025/05/devtools-136-images/dom-adorner.png differ
diff --git a/microsoft-edge/devtools-guide-chromium/whats-new/2025/05/devtools-136.md b/microsoft-edge/devtools-guide-chromium/whats-new/2025/05/devtools-136.md
new file mode 100644
index 0000000000..7e11e57e23
--- /dev/null
+++ b/microsoft-edge/devtools-guide-chromium/whats-new/2025/05/devtools-136.md
@@ -0,0 +1,54 @@
+---
+title: What's New in DevTools (Microsoft Edge 136)
+description: "DOM tree in Elements tool highlights semantic errors. And more."
+author: MSEdgeTeam
+ms.author: msedgedevrel
+ms.topic: conceptual
+ms.service: microsoft-edge
+ms.subservice: devtools
+ms.date: 05/05/2025
+---
+# What's New in DevTools (Microsoft Edge 136)
+
+These are the latest features in the Stable release of Microsoft Edge DevTools.
+
+
+<!-- ====================================================================== -->
+## DOM tree in Elements tool highlights semantic errors
+
+<!-- Subtitle: DOM elements with semantic errors are highlighted with a wavy line and a tooltip with a link. -->
+
+You can now easily identify semantic issues in the DOM tree of the **Elements** tool, such as: 
+* An invalid descendant of `<select>`.
+* Mismatched ARIA definitions.
+* Missing ARIA attributes.
+
+Each DOM node that has a semantic issue displays a red wavy line, and has a tooltip with details about the specific issue and a link to the entry in the **Issues** tool:
+
+![DOM adorner in Elements](./devtools-136-images/dom-adorner.png)
+
+To enable this feature, in DevTools experiments, select the checkbox [Highlights a violating node or attribute in the Elements panel DOM tree](../../../experimental-features/index.md#highlights-a-violating-node-or-attribute-in-the-elements-panel-dom-tree).
+
+See also:
+* [Turning an experiment on or off](../../../experimental-features/index.md#turning-an-experiment-on-or-off) in _Experimental features in Microsoft Edge DevTools_.
+
+
+<!-- ====================================================================== -->
+## Announcements from the Chromium project
+
+Microsoft Edge 136 also includes the following updates from the Chromium project:
+
+* [Performance panel improvements](https://developer.chrome.com/blog/new-in-devtools-136#perf)
+   * [New performance insights](https://developer.chrome.com/blog/new-in-devtools-136#perf-insights)
+   * [Click to highlight](https://developer.chrome.com/blog/new-in-devtools-136#click-to-highlight)
+   * [Server timings in Summary of network requests](https://developer.chrome.com/blog/new-in-devtools-136#server-timings)
+* [Filter cookies in 'Privacy and security'](https://developer.chrome.com/blog/new-in-devtools-136#cookies-filter)
+* [Sizes in kB units in tables across panels](https://developer.chrome.com/blog/new-in-devtools-136#kb-units)
+* [Autocomplete supports corner-shape and corner-*- shape in Elements > Styles](https://developer.chrome.com/blog/new-in-devtools-136#corner-shape-autocomplete)
+
+
+<!-- ====================================================================== -->
+## See also
+
+* [What's New in Microsoft Edge DevTools](../../whats-new.md)
+* [Release notes for Microsoft Edge web platform](../../../../web-platform/release-notes/index.md)
diff --git a/microsoft-edge/extensions-chromium/publish/create-dev-account.md b/microsoft-edge/extensions-chromium/publish/create-dev-account.md
index 88e9d643cd..7c8d881f83 100644
--- a/microsoft-edge/extensions-chromium/publish/create-dev-account.md
+++ b/microsoft-edge/extensions-chromium/publish/create-dev-account.md
@@ -23,7 +23,7 @@ To add and manage users in the Microsoft Edge program to manage extensions, you
 | Type of account | Description |
 |---|---|
 | _Microsoft account (MSA)_ | An Outlook.com, Live.com, or Hotmail.com account. |
-| _GitHub account_ | A user account at GitHub.com.  You can use your personal GitHub account to sign in to Partner Center—a Microsoft account (MSA) will be created for you. |
+| _GitHub account_ | A user account at GitHub.com.  You can use your personal GitHub account to sign in to Partner Center — a Microsoft account (MSA) will be created for you. |
 | _Partner Center account_, _Partner Center developer account_ | A _Partner Center account_ is an account on partner.microsoft.com.  To submit Microsoft Edge extensions, you need a _Partner Center developer account_, which is a Partner Center account that has a Microsoft account (MSA) as the Primary Owner. |
 | _Microsoft Edge Program account_ | Enables multiple users to work with Microsoft Edge extensions at Partner Center. |
 | _Microsoft Entra ID_ | A Microsoft Entra ID account; see [What is Microsoft Entra ID?](/entra/fundamentals/whatis) |
diff --git a/microsoft-edge/index.yml b/microsoft-edge/index.yml
index 1808e1dcba..a4471ab847 100644
--- a/microsoft-edge/index.yml
+++ b/microsoft-edge/index.yml
@@ -209,6 +209,14 @@ conceptualContent:
               url: ./origin-trials/index.md
               itemType: whats-new
 
+            - text: Prompt a built-in language model with the Prompt API
+              url: ./web-platform/prompt-api.md
+              itemType: whats-new
+
+            - text: Summarize, write, and rewrite text with the Writing Assistance APIs
+              url: ./web-platform/writing-assistance-apis.md
+              itemType: whats-new
+
 # -----------------------------------------------------------------------------
 # Card for toc bucket 3 - r1c2
         - title: Microsoft Edge DevTools
diff --git a/microsoft-edge/progressive-web-apps-chromium/how-to/app-actions.md b/microsoft-edge/progressive-web-apps-chromium/how-to/app-actions.md
new file mode 100644
index 0000000000..0ef4b27f0f
--- /dev/null
+++ b/microsoft-edge/progressive-web-apps-chromium/how-to/app-actions.md
@@ -0,0 +1,413 @@
+---
+title: Enable App Actions on Windows for a PWA
+description: How to author and test an App Action for the App Actions on Windows framework, for a Progressive Web App (PWA) that you've created.
+author: MSEdgeTeam
+ms.author: msedgedevrel
+ms.topic: conceptual
+ms.service: microsoft-edge
+ms.subservice: pwa
+ms.date: 05/19/2025
+---
+# Enable App Actions on Windows for a PWA
+
+You can author and test an App Action for the App Actions on Windows framework, for a Progressive Web App (PWA) that you've created.  An App Action on Windows is an individual unit of behavior that a Windows app can implement and register.  The App Action can then be accessed from other apps and experiences, seamlessly integrating into user workflows.
+
+An app builds and registers each App Action, and then Windows apps and experiences can recommend registered App Actions to the user at contextually relevant times and locations within the user's workflow.
+
+You can build Windows App Actions to increase discoverability and engagement of your app's features.
+
+See also:
+* [App Actions on Windows Overview](/windows/ai/app-actions/)
+
+**Detailed contents:**
+
+* [Recommended scenarios](#recommended-scenarios)
+* [Define App Actions in the action definition manifest](#define-app-actions-in-the-action-definition-manifest)
+   * [Properties supported in an action definition manifest](#properties-supported-in-an-action-definition-manifest)
+   * [Supported Entity types for App Actions for PWAs](#supported-entity-types-for-app-actions-for-pwas)
+* [How a PWA is launched through URI activation](#how-a-pwa-is-launched-through-uri-activation)
+   * [uri in the action definition manifest](#uri-in-the-action-definition-manifest)
+   * [Receive ValueSet data and map it to a share target](#receive-valueset-data-and-map-it-to-a-share-target)
+* [Prerequisites for your PWA to support App Actions](#prerequisites-for-your-pwa-to-support-app-actions)
+   * [share_target in the web app manifest](#share_target-in-the-web-app-manifest)
+     * [Handle the entity of an App Action](#handle-the-entity-of-an-app-action)
+   * [protocol_handlers in the web app manifest](#protocol_handlers-in-the-web-app-manifest)
+   * [launch_handler in the web app manifest](#launch_handler-in-the-web-app-manifest)
+* [Package a store PWA in Edge Stable](#package-a-store-pwa-in-edge-stable)
+* [Package a store PWA in Edge Canary](#package-a-store-pwa-in-edge-canary)
+* [Test App Actions for a PWA](#test-app-actions-for-a-pwa)
+* [See also](#see-also)
+
+
+<!-- ------------------------------ -->
+#### Recommended scenarios
+
+The Windows App Actions framework is for exposing and executing key pieces of app functionality, not generic user activities such as opening a right-click menu (context menu).  See [Recommended scenarios for App Actions](/windows/ai/app-actions#recommended-scenarios-for-app-actions) in _App Actions on Windows Overview_.
+
+
+<!-- ====================================================================== -->
+## Define App Actions in the action definition manifest
+
+You define App Actions that your PWA supports in an action definition manifest file (such as `ActionsManifest.json`).  This is an action definition JSON file for App Actions on Windows.
+
+The present article shows how to author an App Action that uses the sample PWA, [wami, the Web App to Manipulate Images](https://github.com/MicrosoftEdge/Demos/tree/main/wami).  The wami demo supports image manipulation tasks, such as resizing or applying post-processing styles.
+
+The following example action definition manifest file (named `ActionsManifest.json`), defines a **Paint** App Action for the Paint feature of the wami sample app.  The Paint feature, referenced by the **Paint** App Action, generates an oil-painting-style version of the image.
+
+```json
+{
+   "version": 1,
+   "actions": [{
+      "id": "Wami.Paint",
+      "description": "Convert the image to oil paint style",
+      "kind": "Search",
+      "inputs": [{
+         "name": "File",
+         "kind": "Photo"
+        }],
+      "outputs": [],
+      "invocation": {
+         "type": "Uri",
+         "uri": "web+wami://paint"
+      },
+      "inputCombinations": [{
+         "inputs": [ "File" ],
+         "description": "Photo to be converted to oil paint style."
+      }]
+   }]
+}
+```
+
+As the input, the **Paint** App Action accepts the image file that user selected.
+
+The **Paint** App Action returns the stylized output.
+
+
+<!-- ------------------------------ -->
+#### Properties supported in an action definition manifest
+
+The action definition manifest file (such as `ActionsManifest.json`) is a descriptive file which is used by Windows App Actions Runtime for an app, to declare the App Actions that the app supports.
+
+For the definition of each supported JSON property, see [Action definition JSON properties](/windows/ai/app-actions/actions-json#action-definition-json-properties) in _Action definition JSON schema for App Actions on Windows_.
+
+Under `Invocation`, only the `uri` type is supported.  The `com` type is not applicable for PWAs.
+
+
+<!-- ------------------------------ -->
+#### Supported Entity types for App Actions for PWAs
+
+In the action definition manifest file (such as `ActionsManifest.json`), the `ActionEntityKind` enumeration specifies the types of entities that are supported by App Actions on Windows.
+
+In the context of a JSON App Action definition, the entity kinds are string literals that are case-sensitive.  The supported entities are listed in [ActionEntityKind enumeration](/windows/ai/app-actions/actions-json#actionentitykind-enumeration) in _Action definition JSON schema for App Actions on Windows_.
+
+`StreamingText` and `RemoteFile` are not yet supported for PWAs.  For `File`, `Photo`, `Document` and `Text` entity kinds, see [Entity properties](/windows/ai/app-actions/actions-json#entity-properties) in _Action definition JSON schema for App Actions on Windows_.
+
+
+<!-- ====================================================================== -->
+## How a PWA is launched through URI activation
+
+When a PWA's App Action is called, the PWA App Action is launched by Windows through custom protocol URI activation.  A PWA must register for custom protocol handling by using the `protocol_handlers` field in the PWA's web app manifest, such as [Demos/wami/manifest.json](https://github.com/MicrosoftEdge/Demos/blob/main/wami/manifest.json).
+
+Windows' `LaunchUriAsync(Uri, LauncherOptions, ValueSet)` method is used by the Action Framework for URI activation.  `LaunchUriAsync` doesn't return a value or error status.
+
+
+<!-- ------------------------------ -->
+#### `uri` in the action definition manifest
+
+Use a custom protocol URI, not an HTTPS URI.
+
+For a PWA that has multiple App Actions, use the syntax:
+
+```json
+"uri": "web+{app name}://{custom action name}"
+```
+
+For example:
+
+```json
+"uri": "web+wami://paint"
+```
+
+The above line is shown in context in [Define App Actions in the action definition manifest](#define-app-actions-in-the-action-definition-manifest), above.
+
+
+<!-- ------------------------------ -->
+#### Receive `ValueSet` data and map it to a share target
+
+The activated protocol URI will be mapped to the `url` field of the share target data.
+
+The input `ValueSet` will be converted to a valid JSON string and mapped to the `text` field of the share target data.  That enables Microsoft Edge to determine that the protocol handler launch represents an App Action.
+
+The app's web app manifest (such as [Demos/wami/manifest.json](https://github.com/MicrosoftEdge/Demos/blob/main/wami/manifest.json)) must correctly configure the `share_target` field, to enable being launched as a share target for an App Action.  See [`share_target` in the web app manifest](#share_target-in-the-web-app-manifest), below.
+
+
+<!-- ====================================================================== -->
+## Prerequisites for your PWA to support App Actions
+
+To correctly integrate your PWA with the App Actions on Windows framework, the following web app manifest members are required:
+
+* `share_target`
+* `protocol_handlers`
+* `launch_handler`
+
+
+<!-- ------------------------------ -->
+#### `share_target` in the web app manifest
+
+For a PWA to use App Actions, the `share_target` field must be present in the PWA's web app manifest file, such as [Demos/wami/manifest.json](https://github.com/MicrosoftEdge/Demos/blob/main/wami/manifest.json).
+
+* The method must be "POST".
+* The `enctype` must be `multipart/form-data`.
+* `text` and `url` in `params` are required to support App Actions. 
+* `files` is optional.  You can omit `files` if you don't want your PWA to support the normal _share target_ feature.
+
+Example `share_target` declaration, from [Demos/wami/manifest.json](https://github.com/MicrosoftEdge/Demos/blob/main/wami/manifest.json):
+
+```json
+"share_target": {
+   "action": "./share-target",
+   "method": "POST",
+   "enctype": "multipart/form-data",
+   "params": {
+      "title": "title",
+      "text": "text",
+      "url": "url"
+   }
+}
+```
+
+See also:
+* [Receiving shared content](./share.md#receiving-shared-content)
+
+
+<!-- ---------- -->
+###### Handle the entity of an App Action
+
+The entity of an App Action is passed to the PWA through POST share data.  To handle POST share data, you can use or combine the following approaches:
+
+* Handle POST share data by using server-side code. 
+
+* In a service worker, use a fetch event listener to intercept the HTTP POST request.  This provides a better experience for offline users.  See:
+
+  * [share_target - Receiving share data using POST](https://developer.mozilla.org/docs/Web/Progressive_web_apps/Manifest/Reference/share_target#receiving_share_data_using_post)
+  * [share_target - Receiving shared files](https://developer.mozilla.org/docs/Web/Progressive_web_apps/Manifest/Reference/share_target#receiving_shared_files)
+
+The following code is from the wami demo's example service worker handler in [Demos/wami/sw.js](https://github.com/MicrosoftEdge/Demos/blob/main/wami/sw.js), to support App Action launch for the app:
+
+```javascript
+// Extract data
+const data = {
+   text: formData.get('text') || '',
+   url: formData.get('url') || ''
+};
+const files = formData.getAll('windowsActionFiles');
+```
+
+Explanation of the `formData` keys:
+
+* **text:** A JSON string that lists all input entities.  The input parameter value must be identical to the value you set in your PWA's web app manifest `share_target.params.text`.  The file paths that are contained in **text** are safe to consume.  To protect users' privacy, Edge sanitizes any user-supplied path information before it reaches your service worker, leaving only the file name.
+
+* **url:** The protocol URI (for example, `web+wami://paint` in the sample) that identifies which App Action triggered the launch.  The input parameter value must be identical to the value that you set in the PWA's web app manifest `share_target.params.url`.
+
+* **files:** File objects attached to the App Action invocation. 
+
+
+<!-- ------------------------------ -->
+#### `protocol_handlers` in the web app manifest
+
+For a PWA to use App Actions, the `protocol_handlers` field must be present in the PWA's web app manifest file (such as [Demos/wami/manifest.json](https://github.com/MicrosoftEdge/Demos/blob/main/wami/manifest.json)).  The `protocol_handlers.protocol` field must match the first part of the `invocation.uri` in the action definition manifest file (such as `ActionsManifest.json`).
+
+Example `protocol_handlers` declaration, from [Demos/wami/manifest.json](https://github.com/MicrosoftEdge/Demos/blob/main/wami/manifest.json):
+
+```json
+"protocol_handlers": [{
+   "protocol": "web+wami",
+   "url": "./?url=%s"
+}]
+```
+
+The matching `invocation.uri` field from `ActionsManifest.json`:
+
+```json
+"invocation": {
+   "type": "Uri",
+   "uri": "web+wami://paint"
+},
+```
+
+The above snippet is shown in context in [Define App Actions in the action definition manifest](#define-app-actions-in-the-action-definition-manifest), above.
+
+See also:
+* [Handle protocols in a PWA](./handle-protocols.md)
+
+
+<!-- ------------------------------ -->
+#### `launch_handler` in the web app manifest
+
+If you want to keep a single PWA window, you can set [launch_handler](https://developer.mozilla.org/docs/Web/Progressive_web_apps/Manifest/Reference/launch_handler) as `navigate-existing` in your PWA's web app manifest file (such as [Demos/wami/manifest.json](https://github.com/MicrosoftEdge/Demos/blob/main/wami/manifest.json)).
+
+Example declaration:
+
+```json
+"launch_handler": {
+   "client_mode": " navigate-existing"
+}
+```
+
+The above code is not in [Demos/wami/manifest.json](https://github.com/MicrosoftEdge/Demos/blob/main/wami/manifest.json).
+
+
+<!-- ====================================================================== -->
+## Package a store PWA in Edge Stable
+
+At the current stage, your PWA needs to be packaged as a Microsoft Store PWA, to be called by the Windows App Actions framework.  You must use Microsoft Edge 137 or greater.
+
+The Stable release of Edge 137 will be available on May 29, 2025.  If you'd like to try it out before May 29, 2025, you can package your PWA in Edge Canary; see [Package a store PWA in Edge Canary](#package-a-store-pwa-in-edge-canary), below.
+
+1. Upgrade to Edge Stable 137 version.  (Edge 137 stable will be available after May 29, 2025.)
+
+1. Package your PWA for [PWABuilder.com](https://www.pwabuilder.com); see [Package your PWA for the Store](./microsoft-store.md#package-your-pwa-for-the-store) in _Publish a PWA to the Microsoft Store_.
+
+1. In **All settings**, scroll down to **Actions – Enable Actions** at the bottom.
+
+1. Make sure your PWA's web app manifest file (such as [Demos/wami/manifest.json](https://github.com/MicrosoftEdge/Demos/blob/main/wami/manifest.json)) has `protocol_handlers` and `share_target` fields.  PWABuilder.com will run a check, and if either field is missing from the app's web app manifest, the **Enable Actions** checkbox will be greyed out.
+
+1. In the **Actions** section, click **Choose File**, and upload the action definition manifest file (such as `ActionsManifest.json`) that you prepared for your PWA.
+
+1. Click the **Download** button.
+
+1. Unzip your download archive.  Then you can [publish your PWA to the Microsoft Store](./microsoft-store.md) and install the app from the Store, or install it directly by running `install.ps1`.
+
+1. Launch your PWA by clicking the PWA icon.
+
+
+<!-- ====================================================================== -->
+## Package a store PWA in Edge Canary
+
+The Stable release of Edge 137 will be available on May 29, 2025; see [Package a store PWA in Edge Stable](#package-a-store-pwa-in-edge-stable), above.
+
+Edge Canary gives a preview of the functionalities that's not available in stable yet.
+
+If you want to try out App Actions for PWAs before May 29, 2025, you can package your PWA in Edge Canary, as follows:
+
+1. Install [Edge Canary](https://www.microsoft.com/edge/download/insider) and upgrade to the latest version.
+
+1. Get the **Package ID**, **Publisher ID**, and **Publisher display name** of your PWA; see [Publish a PWA to the Microsoft Store](./microsoft-store.md).
+
+1. Go to [PWABuilder.Windows.Chromium tester](https://pwabuilder-windows-docker.azurewebsites.net/).
+
+1. Enter your PWA configs in the input box, for the following fields:
+
+   * `name`: Your PWA's name.
+   * `packageId`: Not needed if you won't publish the Edge Canary version of your app to the store; can be an empty string.
+   * `url`: Your PWA's url.
+   * `publisher.displayName`: The publisher's name.  Not needed if you won't publish the Edge Canary version of your app to the store; can be an empty string.
+   * `publisher.commonName`: Your Publisher ID.  Not needed if you won't publish the Edge Canary version of your app to the store; can be an empty string.
+   * `startUrl`: Your PWA's `startUrl`.
+
+   Example JSON listing that you can copy and paste into the text field of the [PWABuilder.Windows.Chromium tester](https://pwabuilder-windows-docker.azurewebsites.net/):
+
+   ```json
+   {
+      "name": "Wami for Canary",
+      "packageId": "",
+      "url": "https://microsoftedge.github.io/Demos/wami",
+      "version": "1.0.2",
+      "allowSigning": true,
+      "classicPackage": {
+         "generate": true,
+         "version": "1.0.0"
+      },
+      "publisher": {
+         "displayName": "",
+         "commonName": ""
+      },
+      "edgeChannel": "canary",
+      "appUserModelId": "Microsoft.Canary_8wekyb3d8bbwe!MSEDGE",
+      "generateModernPackage": true,
+      "resourceLanguage": "EN-US",
+      "startUrl": "https://microsoftedge.github.io/Demos/wami"
+   }
+   ```
+
+   Replace the above attributes with your app's actual attributes.
+
+1. Upload the action definition manifest file (such as `ActionsManifest.json`), and then click the **Download** button.
+
+1. Your download is a `.zip` archive that contains files such as `.msix` and `.msixbundle` files.  Unzip it and run `install.ps1` to install your PWA directly.
+
+1. Click the icon for your PWA.
+
+   Your PWA starts.
+
+1. Launch Edge Canary, and then go to `edge://apps`.
+
+   Your PWA is listed.
+
+1. Click the **Details** button.
+
+   Your PWA is indicated as installed from Microsoft Store.
+
+Your PWA has now been installed as a Store PWA in Edge Canary.
+
+
+<!-- ====================================================================== -->
+## Test App Actions for a PWA
+
+To test App Actions for your PWA:
+
+1. Make sure your PWA has been set up and packaged successfully, as discussed in the above sections.
+
+1. Make sure Windows is updated to support App Actions; see [Windows 11 Insider Preview Build 26120.4151 (Beta Channel)](https://blogs.windows.com/windows-insider/2025/05/19/announcing-windows-11-insider-preview-build-26120-4151-beta-channel/).
+
+1. Make sure Microsoft Edge is updated to the latest version, and install your PWA successfully; see [Package a store PWA in Edge Stable](#package-a-store-pwa-in-edge-stable) or [Package a store PWA in Edge Canary](#package-a-store-pwa-in-edge-canary), above.
+
+1. Launch Edge Canary or Edge Stable (whichever channel you installed the PWA on).
+
+1. Go to `edge://flags`, search for **App Actions**, and locate the entry **Enable App Actions on Windows for web apps**.  (The flag name is `#edge-app-actions-on-windows-for-web-apps`.)
+
+1. Change the status to **Enabled**, and then click the **Restart** button in the lower right.
+
+1. Launch your PWA.
+
+   Your PWA must be launched at least one time, to initialize your PWA for the App Action, before being called by the App Actions runtime.
+
+1. Use the [App Actions Testing Playground app](/windows/ai/app-actions/actions-test-tool) to test the App Actions for your PWA.
+
+1. Add an entity that that App Action needs.  For example, if the App Action processes images, add an image.  Then run the App Action.
+
+   The PWA is launched, and executes the App Action.
+
+
+<!-- ====================================================================== -->
+## See also
+<!-- all links in file -->
+
+* [Receiving shared content](./share.md#receiving-shared-content)
+* [Publish a PWA to the Microsoft Store](./microsoft-store.md) 
+   * [Package your PWA for the Store](./microsoft-store.md#package-your-pwa-for-the-store) in _Publish a PWA to the Microsoft Store_.
+
+Windows articles:
+* [App Actions on Windows Overview](/windows/ai/app-actions/)
+   * [Recommended scenarios for App Actions](/windows/ai/app-actions#recommended-scenarios-for-app-actions) in _App Actions on Windows Overview_.
+* [Action definition JSON schema for App Actions on Windows](/windows/ai/app-actions/actions-json)
+   * [Action definition JSON properties](/windows/ai/app-actions/actions-json#action-definition-json-properties)
+   * [ActionEntityKind enumeration](/windows/ai/app-actions/actions-json#actionentitykind-enumeration)
+   * [Entity properties](/windows/ai/app-actions/actions-json#entity-properties)
+* [App Actions Testing Playground app](/windows/ai/app-actions/actions-test-tool)
+* [Windows 11 Insider Preview Build 26120.4151 (Beta Channel)](https://blogs.windows.com/windows-insider/2025/05/19/announcing-windows-11-insider-preview-build-26120-4151-beta-channel/) - blog post.
+
+Sites:
+* [Become a Microsoft Edge Insider](https://www.microsoft.com/edge/download/insider) - install a preview channel of Edge.
+* [PWABuilder.com](https://www.pwabuilder.com)
+* [PWABuilder.Windows.Chromium tester](https://pwabuilder-windows-docker.azurewebsites.net/)
+
+MDN:
+* [launch_handler](https://developer.mozilla.org/docs/Web/Progressive_web_apps/Manifest/Reference/launch_handler) 
+* [share_target](https://developer.mozilla.org/docs/Web/Progressive_web_apps/Manifest/Reference/share_target)
+   * [Receiving share data using POST](https://developer.mozilla.org/docs/Web/Progressive_web_apps/Manifest/Reference/share_target#receiving_share_data_using_post) in _share_target_.
+   * [Receiving shared files](https://developer.mozilla.org/docs/Web/Progressive_web_apps/Manifest/Reference/share_target#receiving_shared_files) in _share_target_.
+
+Demos repo:
+* [wami, the Web App to Manipulate Images](https://github.com/MicrosoftEdge/Demos/tree/main/wami)
+   * [Demos/wami/sw.js](https://github.com/MicrosoftEdge/Demos/blob/main/wami/sw.js) - supports AI Action launch.
diff --git a/microsoft-edge/progressive-web-apps-chromium/how-to/offline.md b/microsoft-edge/progressive-web-apps-chromium/how-to/offline.md
index 27b70acf28..c4aaa39613 100644
--- a/microsoft-edge/progressive-web-apps-chromium/how-to/offline.md
+++ b/microsoft-edge/progressive-web-apps-chromium/how-to/offline.md
@@ -18,18 +18,18 @@ The following table describes the different options, and the rest of this articl
 
 | Storage option | Description |
 |:--- |:--- |
-| Web Storage | Web Storage has two types: session and local. Web Storage is useful to store small amounts of data from your app's front-end code. The data is structured as key-value pairs and is only available to the current app origin. In the case of session storage, the data is cleared when the session ends, for example when the app is closed, or when the user browses to another origin in the same window or tab. Local storage persists until the app removes the data. |
-| IndexedDB | IndexedDB is an API for storing larger amounts of structured data. The API is asynchronous and can be used both from your app's front-end code and service worker code. Use the IndexedDB API to store a significant amount of structured data on the client, or binary data, such as encrypted media objects or files. |
-| Cache | The Cache API can be used to manage cached resources. The Cache API is Promise-based and allows developers to store and retrieve many web resources—HTML, CSS, JavaScript, images, JSON, and so on. Usually, the Cache API is used within the context of a service worker, but it's also available to your app's front-end code. |
+| Web Storage | Web Storage has two types: session and local.  Web Storage is useful to store small amounts of data from your app's front-end code.  The data is structured as key-value pairs and is only available to the current app origin.  In the case of session storage, the data is cleared when the session ends, for example when the app is closed, or when the user browses to another origin in the same window or tab.  Local storage persists until the app removes the data. |
+| IndexedDB | IndexedDB is an API for storing larger amounts of structured data.  The API is asynchronous and can be used both from your app's front-end code and service worker code.  Use the IndexedDB API to store a significant amount of structured data on the client, or binary data, such as encrypted media objects or files. |
+| Cache | The Cache API can be used to manage cached resources.  The Cache API is Promise-based and allows developers to store and retrieve many web resources — HTML, CSS, JavaScript, images, JSON, and so on.  Usually, the Cache API is used within the context of a service worker, but it's also available to your app's front-end code. |
 | File System Access | The File System Access API allows your PWA to read files and folders on the user's device and save changes back to them. |
 
-**Note**: Do not use WebSQL or Application Cache. While these are two other browser storage mechanisms, they have both been deprecated. Instead of WebSQL, use IndexedDB. Instead of Application Cache, use the Cache API.
+**Note**: Do not use WebSQL or Application Cache.  While these are two other browser storage mechanisms, they have both been deprecated.  Instead of WebSQL, use IndexedDB. Instead of Application Cache, use the Cache API.
 
 
 <!-- ====================================================================== -->
 ## Web Storage
 
-Web Storage is useful for storing small amounts of string data on the user's device. The simplicity of the key-value pair system of Web Storage makes it easy to use.
+Web Storage is useful for storing small amounts of string data on the user's device.  The simplicity of the key-value pair system of Web Storage makes it easy to use.
 
 Web Storage works synchronously in your app's main thread only. This means that Web Storage isn't available for use within service workers, and that heavy usage of Web Storage may create performance issues for your application.
 
diff --git a/microsoft-edge/progressive-web-apps-chromium/index.md b/microsoft-edge/progressive-web-apps-chromium/index.md
index f9b0f16c04..dc3a09277b 100644
--- a/microsoft-edge/progressive-web-apps-chromium/index.md
+++ b/microsoft-edge/progressive-web-apps-chromium/index.md
@@ -94,7 +94,7 @@ To find examples of what PWAs can do, see [Myth Busting PWAs](https://www.davrou
 <!-- ====================================================================== -->
 ## The Microsoft Store
 
-Because Progressive Web Apps (PWAs) are just like other apps in the [Microsoft Store](https://apps.microsoft.com), users can fully engage with them—from discovery, to installation, to execution—without<!-- em dashes--> ever opening the browser.
+Because Progressive Web Apps (PWAs) are just like other apps in the [Microsoft Store](https://apps.microsoft.com), users can fully engage with them — from discovery, to installation, to execution — without ever opening the browser.
 
 The Microsoft Store provides a trustworthy and familiar experience for users to install your app.  Additionally, you can view detailed usage statistics and charts that let you know how your apps in the Microsoft Store are doing.
 
diff --git a/microsoft-edge/progressive-web-apps-chromium/whats-new/pwa.md b/microsoft-edge/progressive-web-apps-chromium/whats-new/pwa.md
index 6743783f4f..5c2c0f381c 100644
--- a/microsoft-edge/progressive-web-apps-chromium/whats-new/pwa.md
+++ b/microsoft-edge/progressive-web-apps-chromium/whats-new/pwa.md
@@ -245,7 +245,7 @@ We expect the [protocol handlers origin trial](#protocol-handlers-origin-trial)
 <!-- ====================================================================== -->
 ## What's New in Microsoft Edge 94
 
-Microsoft Edge version 94 moved to Stable on September 23, 2021. This release cycle was short—just<!-- em dash --> 3 weeks from Microsoft Edge 93 Stable to Microsoft Edge 94 Stable, as we snapped to the new [4-week release cycle](https://blogs.windows.com/msedgedev/2021/03/12/new-release-cycles-microsoft-edge-extended-stable/).  This new release cadence matches the new cadence of Chromium milestones, described in [Speeding up Chrome's release cycle](https://blog.chromium.org/2021/03/speeding-up-release-cycle.html).
+Microsoft Edge version 94 moved to Stable on September 23, 2021. This release cycle was short — just 3 weeks from Microsoft Edge 93 Stable to Microsoft Edge 94 Stable, as we snapped to the new [4-week release cycle](https://blogs.windows.com/msedgedev/2021/03/12/new-release-cycles-microsoft-edge-extended-stable/).  This new release cadence matches the new cadence of Chromium milestones, described in [Speeding up Chrome's release cycle](https://blog.chromium.org/2021/03/speeding-up-release-cycle.html).
 
 Due to the shortened release cycle of Microsoft Edge version 94, we focused on stabilizing the release cycle logistics, and we shifted feature development to Microsoft Edge version 95.
 
@@ -259,7 +259,7 @@ We expect the [protocol handlers origin trial](#protocol-handlers-origin-trial)
 <!-- ====================================================================== -->
 ## What's New in Microsoft Edge 93
 
-Microsoft Edge version 93 became the Stable channel of Microsoft Edge on September 2, 2021. This article lists updates we made to Progressive Web Apps (PWAs) from both a developer and consumer point of view.
+Microsoft Edge version 93 became the Stable channel of Microsoft Edge on September 2, 2021.  This article lists updates we made to Progressive Web Apps (PWAs) from both a developer and consumer point of view.
 
 
 <!-- ------------------------------ -->
diff --git a/microsoft-edge/toc.yml b/microsoft-edge/toc.yml
index c0a68bcafa..f8a74ebf56 100644
--- a/microsoft-edge/toc.yml
+++ b/microsoft-edge/toc.yml
@@ -66,7 +66,7 @@
         - name: Sign up for the Ad Selection API
           href: ./web-platform/ad-selection-api.md
 
-        - name: Prompting a built-in language model with the Prompt API
+        - name: Prompt a built-in language model with the Prompt API
           href: ./web-platform/prompt-api.md
 
         - name: Summarize, write, and rewrite text with the Writing Assistance APIs
@@ -89,6 +89,10 @@
               href: ./devtools-guide-chromium/whats-new/whats-new.md
               displayName: release notes, announcements
 # latest 10 What's New
+            - name: Microsoft Edge 136
+              href: ./devtools-guide-chromium/whats-new/2025/05/devtools-136.md
+              displayName: What's New in DevTools (Microsoft Edge 136)  # page title
+
             - name: Microsoft Edge 135
               href: ./devtools-guide-chromium/whats-new/2025/04/devtools-135.md
               displayName: What's New in DevTools (Microsoft Edge 135)  # page title
@@ -125,16 +129,16 @@
               href: ./devtools-guide-chromium/whats-new/2024/07/devtools-127.md
               displayName: What's New in DevTools (Microsoft Edge 127)  # page title
 
-            - name: Microsoft Edge 126
-              href: ./devtools-guide-chromium/whats-new/2024/06/devtools-126.md
-              displayName: What's New in DevTools (Microsoft Edge 126)  # page title
-
             # keep 10 items above
             - name: Archive
               items:
                 - name: What's New in DevTools archive
                   href: ./devtools-guide-chromium/whats-new/whats-new-archive.md
 
+                - name: Microsoft Edge 126
+                  href: ./devtools-guide-chromium/whats-new/2024/06/devtools-126.md
+                  displayName: What's New in DevTools (Microsoft Edge 126)  # page title
+
                 - name: Microsoft Edge 125
                   href: ./devtools-guide-chromium/whats-new/2024/05/devtools-125.md
                   displayName: What's New in DevTools (Microsoft Edge 125)  # page title
@@ -1276,6 +1280,9 @@
             - name: Build a PWA for the sidebar in Microsoft Edge
               href: ./progressive-web-apps-chromium/how-to/sidebar.md
 
+            - name: Enable App Actions on Windows for a PWA
+              href: ./progressive-web-apps-chromium/how-to/app-actions.md
+
         - name: Distribute a PWA with the Microsoft Store
           items:
             - name: Publish a PWA to the Microsoft Store
diff --git a/microsoft-edge/web-platform/prompt-api-images/model-downloading.png b/microsoft-edge/web-platform/prompt-api-images/model-downloading.png
index ed4db0b055..b99ee11ffa 100644
Binary files a/microsoft-edge/web-platform/prompt-api-images/model-downloading.png and b/microsoft-edge/web-platform/prompt-api-images/model-downloading.png differ
diff --git a/microsoft-edge/web-platform/prompt-api.md b/microsoft-edge/web-platform/prompt-api.md
index 90a9b1a4e6..836732f63d 100644
--- a/microsoft-edge/web-platform/prompt-api.md
+++ b/microsoft-edge/web-platform/prompt-api.md
@@ -10,40 +10,39 @@ ms.date: 05/19/2025
 # Prompt a built-in language model with the Prompt API
 <!-- https://aka.ms/edge-prompt-api-docs -->
 
-The [Prompt API](https://github.com/webmachinelearning/prompt-api) is an experimental web API that allows you to prompt a small language model (SLM) that is built into Microsoft Edge, from your website's or browser extension's JavaScript code.  Use the Prompt API to generate and analyze text or create application logic based on user input – and discover innovative ways to integrate prompt engineering capabilities into your web application.
+The [Prompt API](https://github.com/webmachinelearning/prompt-api) is an experimental web API that allows you to prompt a small language model (SLM) that is built into Microsoft Edge, from your website's or browser extension's JavaScript code.  Use the Prompt API to generate and analyze text or create application logic based on user input, and discover innovative ways to integrate prompt engineering capabilities into your web application.
 
 
 **Detailed contents:**
 
-* [Prompt a built-in language model with the Prompt API](#prompt-a-built-in-language-model-with-the-prompt-api)
-  * [Availability of the Prompt API](#availability-of-the-prompt-api)
-  * [Alternatives to and benefits of the Prompt API](#alternatives-to-and-benefits-of-the-prompt-api)
-  * [The Phi-4-mini model](#the-phi-4-mini-model)
-      * [Disclaimer](#disclaimer)
-      * [Hardware requirements](#hardware-requirements)
-      * [Model availability](#model-availability)
-  * [Enable the Prompt API](#enable-the-prompt-api)
-  * [See a working example](#see-a-working-example)
-  * [Use the Prompt API](#use-the-prompt-api)
-      * [Check if the API is enabled](#check-if-the-api-is-enabled)
-      * [Check if the model can be used](#check-if-the-model-can-be-used)
-      * [Create a new session](#create-a-new-session)
-          * [Monitor the progress of the model download](#monitor-the-progress-of-the-model-download)
-          * [Provide the model with a system prompt](#provide-the-model-with-a-system-prompt)
-          * [N-shot prompting with initialPrompts](#n-shot-prompting-with-initialprompts)
-          * [Set topK and temperature](#set-topk-and-temperature)
-      * [Clone a session to start the conversation again with the same options](#clone-a-session-to-start-the-conversation-again-with-the-same-options)
-      * [Prompt the model](#prompt-the-model)
-          * [Wait for the final response](#wait-for-the-final-response)
-          * [Display tokens as they are generated](#display-tokens-as-they-are-generated)
-          * [Constrain the model output by using a JSON schema or regular expression](#constrain-the-model-output-by-using-a-json-schema-or-regular-expression)
-          * [Send multiple messages per prompt](#send-multiple-messages-per-prompt)
-      * [Stop generating text](#stop-generating-text)
-      * [Destroy a session](#destroy-a-session)
-          * [Destroy a session by using the destroy() method](#destroy-a-session-by-using-the-destroy-method)
-          * [Destroy a session by using an AbortController](#destroy-a-session-by-using-an-abortcontroller)
-  * [Send feedback](#send-feedback)
-  * [See also](#see-also)
+* [Availability of the Prompt API](#availability-of-the-prompt-api)
+* [Alternatives to and benefits of the Prompt API](#alternatives-to-and-benefits-of-the-prompt-api)
+* [The Phi-4-mini model](#the-phi-4-mini-model)
+    * [Disclaimer](#disclaimer)
+    * [Hardware requirements](#hardware-requirements)
+    * [Model availability](#model-availability)
+* [Enable the Prompt API](#enable-the-prompt-api)
+* [See a working example](#see-a-working-example)
+* [Use the Prompt API](#use-the-prompt-api)
+    * [Check if the API is enabled](#check-if-the-api-is-enabled)
+    * [Check if the model can be used](#check-if-the-model-can-be-used)
+    * [Create a new session](#create-a-new-session)
+        * [Monitor the progress of the model download](#monitor-the-progress-of-the-model-download)
+        * [Provide the model with a system prompt](#provide-the-model-with-a-system-prompt)
+        * [N-shot prompting with initialPrompts](#n-shot-prompting-with-initialprompts)
+        * [Set topK and temperature](#set-topk-and-temperature)
+    * [Clone a session to start the conversation again with the same options](#clone-a-session-to-start-the-conversation-again-with-the-same-options)
+    * [Prompt the model](#prompt-the-model)
+        * [Wait for the final response](#wait-for-the-final-response)
+        * [Display tokens as they are generated](#display-tokens-as-they-are-generated)
+        * [Constrain the model output by using a JSON schema or regular expression](#constrain-the-model-output-by-using-a-json-schema-or-regular-expression)
+        * [Send multiple messages per prompt](#send-multiple-messages-per-prompt)
+    * [Stop generating text](#stop-generating-text)
+    * [Destroy a session](#destroy-a-session)
+        * [Destroy a session by using the destroy() method](#destroy-a-session-by-using-the-destroy-method)
+        * [Destroy a session by using an AbortController](#destroy-a-session-by-using-an-abortcontroller)
+* [Send feedback](#send-feedback)
+* [See also](#see-also)
 
 
 <!-- ====================================================================== -->
@@ -69,23 +68,23 @@ To leverage AI capabilities in websites and browser extensions, you can also use
 
 The Prompt API uses an SLM that runs on the same device where the inputs to and outputs of the model are used (that is, locally).  This has the following benefits compared to cloud-based solutions:
 
-* Reduced cost: there's no cost associated with using a cloud AI service.
+* **Reduced cost:** There's no cost associated with using a cloud AI service.
 
-* Network independence: beyond the initial model download, there's no network latency when prompting the model, and may also be used when the device is offline.
+* **Network independence:** Beyond the initial model download, there's no network latency when prompting the model, and may also be used when the device is offline.
 
-* Improved privacy: the data input to the model never leaves the device and is not collected to train AI models.
+* **Improved privacy:** The data input to the model never leaves the device and is not collected to train AI models.
 
 The Prompt API uses a model that's provided by Microsoft Edge and built into the browser, which comes with the additional benefits over custom local solutions such as those based on WebGPU, WebNN, or WebAssembly:
 
-* Shared one-time cost: the browser-provided model is downloaded the very first time the API is called and shared across all websites that run in the browser, reducing network costs for the user and developer.
+* **Shared one-time cost:** The browser-provided model is downloaded the very first time the API is called and shared across all websites that run in the browser, reducing network costs for the user and developer.
 
-* Simplified usage for web developers: the built-in model can be run by using straightforward web APIs and doesn't require AI/ML expertise or using third-party frameworks.
+* **Simplified usage for web developers:** The built-in model can be run by using straightforward web APIs and doesn't require AI/ML expertise or using third-party frameworks.
 
 
 <!-- ====================================================================== -->
 ## The Phi-4-mini model
 
-The Prompt API allows you to prompt Phi-4-mini -- a powerful small language model that excels at text-based tasks -- built into Microsoft Edge.  To learn more about Phi-4-mini and its capabilities, see the model card at [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct).
+The Prompt API allows you to prompt Phi-4-mini — a powerful small language model that excels at text-based tasks — built into Microsoft Edge.  To learn more about Phi-4-mini and its capabilities, see the model card at [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct).
 
 
 <!-- ------------------------------ -->
@@ -167,13 +166,19 @@ To see the Prompt API in action, and review existing code that uses the API:
 
    The Prompt API is only supported on devices that meet certain hardware requirements.  For more information, see [Hardware requirements](#hardware-requirements), above.
 
-1. Either use the provided default prompt and setting values or modify them by changing values such as **User prompt**, **System prompt**, **Response constraint schema**, **N-shot prompt instructions**, **TopK**, or **Temperature**.
+1. Optionally change the prompt settings values, such as:
+      * **User prompt**
+      * **System prompt**
+      * **Response constraint schema**
+      * **More settings** > **N-shot prompt instructions**
+      * **TopK**
+      * **Temperature**
 
 1. Click the **Prompt** button, at the bottom of the page.
 
    The response is generated in the response section of the page:
 
-   ![Prompting and the Stop button](./prompt-api-images/prompting.png)
+   ![The Prompt demo page with settings and a Prompt button](./prompt-api-images/prompting.png)
 
 1. To stop generating the response, at any time, click the **Stop** button.
 
@@ -570,7 +575,7 @@ controller.abort();
 <!-- ====================================================================== -->
 ## Send feedback
 
-The Prompt API developer preview is intended to help discover use-cases for browser-provided language models.  We're very interested in learning about the range of scenarios for which you intend to use the Prompt API, any issues with the API or language models, and whether more specific task-specific APIs, such as APIs for Writing Assistance or Translation, would be useful.
+The Prompt API developer preview is intended to help discover use-cases for browser-provided language models.  We're very interested in learning about the range of scenarios for which you intend to use the Prompt API, any issues with the API or language models, and whether new task-specific APIs, such as for proofreading or translation, would be useful.
 
 To send feedback about your scenarios and the tasks you want to achieve, please add a comment to [the Prompt API feedback issue](https://github.com/MicrosoftEdge/MSEdgeExplainers/issues/1012).
 
diff --git a/microsoft-edge/web-platform/release-notes/136.md b/microsoft-edge/web-platform/release-notes/136.md
index 2ed5fc3a8f..6cfc734bab 100644
--- a/microsoft-edge/web-platform/release-notes/136.md
+++ b/microsoft-edge/web-platform/release-notes/136.md
@@ -60,10 +60,7 @@ To stay up-to-date and get the latest web platform features, download a preview
 <!-- ====================================================================== -->
 ## Edge DevTools
 
-See [What's New in Microsoft Edge DevTools](../../devtools-guide-chromium/whats-new/whats-new.md).
-<!-- todo: when exists, use instead:
 See [What's New in DevTools (Microsoft Edge 136)](../../devtools-guide-chromium/whats-new/2025/05/devtools-136.md).
--->
 
 
 <!-- ====================================================================== -->
diff --git a/microsoft-edge/web-platform/writing-assistance-apis.md b/microsoft-edge/web-platform/writing-assistance-apis.md
index 76a8e801bc..83378b870f 100644
--- a/microsoft-edge/web-platform/writing-assistance-apis.md
+++ b/microsoft-edge/web-platform/writing-assistance-apis.md
@@ -65,18 +65,17 @@ To leverage AI capabilities in websites and browser extensions, you can also use
 
 The Writing Assistance APIs use a small language model (SLM) that runs on the same device where the inputs to and outputs of the model are used (that is, locally).  This has the following benefits compared to cloud-based solutions:
 
-* **Reduced cost:**  There's no cost associated with using a cloud AI service.
+* **Reduced cost:** There's no cost associated with using a cloud AI service.
 
-* **Network independence:**  Beyond the initial model download, there's no network latency when prompting the model, and may also be used when the device is offline.
-
-* **Improved privacy:**  The data input to the model never leaves the device and is not collected to train AI models.
+* **Network independence:** Beyond the initial model download, there's no network latency when prompting the model, and may also be used when the device is offline.
 
+* **Improved privacy:** The data input to the model never leaves the device and is not collected to train AI models.
 
 The Writing Assistance APIs use a model that's provided by Microsoft Edge and built into the browser, which comes with the additional benefits over custom local solutions such as those based on WebGPU, WebNN, or WebAssembly:
 
-* **Shared one-time cost:**  The browser-provided model is downloaded the very first time the API is called and shared across all websites that run in the browser, reducing network costs for the user and developer.
+* **Shared one-time cost:** The browser-provided model is downloaded the very first time the API is called and shared across all websites that run in the browser, reducing network costs for the user and developer.
 
-* **Simplified usage for web developers:**  The built-in model can be run by using straightforward web APIs and doesn't require AI/ML expertise or using third-party frameworks.
+* **Simplified usage for web developers:** The built-in model can be run by using straightforward web APIs and doesn't require AI/ML expertise or using third-party frameworks.
 
 
 <!-- ====================================================================== -->
@@ -174,15 +173,15 @@ To see the Writing Assistance APIs in action, and review existing code that uses
 
    The Writing Assistance APIs are only supported on devices that meet certain hardware requirements.  For more information, see [Hardware requirements](#hardware-requirements), above.
 
-1. To run the APIs, optionally change the settings in the playground pages, such as the text to summarize, write, or rewrite or the length and format of the expected output.
+1. Optionally change the settings in the playground pages, such as the text to summarize, write, or rewrite, or the length and format of the expected output.
 
 1. Click the **Summarize**, **Write**, or **Rewrite** button, at the bottom of the page.
 
-   The output is generated in the response section of the page.
+   The output is generated in the response section of the page:
 
-1. Click the **Stop** button at any time to stop generating text:
+   ![The Summarizer demo page with settings and a Summarize button](./writing-assistance-apis-images/summarizing.png)
 
-   ![The Stop button](./writing-assistance-apis-images/summarizing.png)
+1. To stop generating the response, at any time, click the **Stop** button.
 
 To view the source code of the Writing Assistance APIs playground, see the [MicrosoftEdge/Demos](https://github.com/MicrosoftEdge/Demos/tree/main/built-in-ai/) repo at GitHub.
 
@@ -537,7 +536,7 @@ controller.abort();
 <!-- ====================================================================== -->
 ## Send feedback
 
-We're very interested in learning about the range of scenarios for which you intend to use the Writing Assistance APIs, any issues with the APIs or language models, and whether new APIs, such as APIs for proofreading would be useful.
+We're very interested in learning about the range of scenarios for which you intend to use the Writing Assistance APIs, any issues with the APIs or language models, and whether new task-specific APIs, such as for proofreading or translation, would be useful.
 
 To send feedback about your scenarios and the tasks you want to achieve, please add a comment to [the Writing Assistance APIs feedback issue](https://github.com/MicrosoftEdge/MSEdgeExplainers/issues/1031).