@databricks/appkit-ui 0.12.0 → 0.12.2

package/docs/{docs/architecture.md → architecture.md}

@@ -20,7 +20,7 @@ The backend SDK that provides the plugin architecture and core functionality. It
 * Cache management and streaming capabilities
 * Type generation for SQL queries
 
-See the [Plugins](/appkit/docs/plugins.md) and [API reference](/appkit/docs/api/appkit.md) documentation for detailed information.
+See the [Plugins](./docs/plugins.md) and [API reference](./docs/api/appkit.md) documentation for detailed information.
 
 ### @databricks/appkit-ui[​](#databricksappkit-ui "Direct link to @databricks/appkit-ui")
 
@@ -31,7 +31,7 @@ A React UI library with pre-built components optimized for data applications:
 * Data visualization components
 * Type-safe integration with backend queries
 
-See the [API reference](/appkit/docs/api/appkit-ui.md) for component documentation.
+See the [API reference](./docs/api/appkit-ui.md) for component documentation.
 
 ## Application layers[​](#application-layers "Direct link to Application layers")
 
@@ -63,7 +63,7 @@ Integration with Databricks services:
 
 ## See also[​](#see-also "Direct link to See also")
 
-* [Plugins](/appkit/docs/plugins.md): Deep dive into the plugin system
-* [API reference](/appkit/docs/api.md): Complete API documentation
-* [Development](/appkit/docs/development.md): Explore development workflows
-* [Core Principles](/appkit/docs/core-principles.md): Learn about AppKit's design philosophy
+* [Plugins](./docs/plugins.md): Deep dive into the plugin system
+* [API reference](./docs/api.md): Complete API documentation
+* [Development](./docs/development.md): Explore development workflows
+* [Core Principles](./docs/core-principles.md): Learn about AppKit's design philosophy

package/docs/{docs/configuration.md → configuration.md}

@@ -146,5 +146,5 @@ For advanced Databricks Apps configuration (authorization, networking, resource
 
 ## See also[​](#see-also "Direct link to See also")
 
-* [App management](/appkit/docs/app-management.md) - Deploying and managing apps
-* [Plugins](/appkit/docs/plugins.md) - Plugin configuration options
+* [App management](./docs/app-management.md) - Deploying and managing apps
+* [Plugins](./docs/plugins.md) - Plugin configuration options

package/docs/development/ai-assisted-development.md

@@ -0,0 +1,88 @@
+# AI-Assisted development
+
+## Prerequisites[​](#prerequisites "Direct link to Prerequisites")
+
+* [Node.js](https://nodejs.org) v22+ environment with `npm`
+* Databricks CLI (v0.287.0 or higher): install and configure it according to the [official tutorial](https://docs.databricks.com/aws/en/dev-tools/cli/tutorial).
+* A new Databricks app with AppKit installed. See [Bootstrap a new Databricks app](./docs.md#quick-start-options) for more details.
+
+AppKit integrates with AI coding assistants through the Agent Skills.
+
+## Installing Agent Skills[​](#installing-agent-skills "Direct link to Installing Agent Skills")
+
+To install the Databricks Agent Skills for your preferred AI assistant, run:
+
+```bash
+databricks experimental aitools skills install
+
+```
+
+## Skills capabilities[​](#skills-capabilities "Direct link to Skills capabilities")
+
+The Agent Skills expose the following capabilities for AI assistants:
+
+* **Data exploration**: Query catalogs, schemas, tables, and execute SQL
+* **CLI command execution**: Deploy and manage apps, and run other workspace operations
+* **Workspace resource discovery**: Inspect and navigate workspace resources
+
+## Example prompts[​](#example-prompts "Direct link to Example prompts")
+
+Here are some basic examples you can use to explore your app and workspace:
+
+1. Creating a new basic app
+
+```text
+Create a new Databricks app that displays a dashboard of the users table in main.default.
+
+```
+
+1. Introspecting a table schema
+
+```text
+Show me the schema of the users table in main.default.
+
+```
+
+1. Creating a new query
+
+```text
+Create a new query to find users created in the last 7 days.
+
+```
+
+1. Deploying an app
+
+```text
+Deploy the app to Databricks with the name "my-app".
+
+```
+
+Possibilities are virtually endless. Ask your AI assistant to help you with your app and workspace.
+
+## LLM resources[​](#llm-resources "Direct link to LLM resources")
+
+AppKit provides specialized guidance files to help AI coding assistants work more effectively with the projects.
+
+If you're building applications using AppKit packages, reference the `llms.txt` file. There are two ways to access the documentation:
+
+1. Use the [hosted llms.txt file](https://databricks.github.io/appkit/llms.txt)
+2. Use the `npx @databricks/appkit docs` command to view the documentation in the terminal.
+
+```bash
+npx @databricks/appkit docs            # documentation index with section overview
+  npx @databricks/appkit docs <query> # for specific documentation file or section
+
+```
+
+Examples of documentation queries:
+
+```bash
+npx @databricks/appkit docs "appkit-ui API reference"  # view a specific section
+npx @databricks/appkit docs --full     # full index with all API entries
+npx @databricks/appkit docs ./docs.md  # view a specific documentation file
+
+```
+
+## See more[​](#see-more "Direct link to See more")
+
+To learn more about Agent Skills, see the [Agent Skills repository](https://github.com/databricks/databricks-agent-skills).

package/docs/{docs/development → development}/llm-guide.md

@@ -46,17 +46,18 @@ View API reference (docs only, NOT for scaffolding):
 
 ```bash
 # ONLY for viewing documentation - do NOT use for init/scaffold
-npx @databricks/appkit docs <path>
+npx @databricks/appkit docs <query>
 
 ```
 
-**IMPORTANT**: ALWAYS run `npx @databricks/appkit docs` (no path) FIRST to see available pages. DO NOT guess paths - use the index to find correct paths.
+**IMPORTANT**: ALWAYS run `npx @databricks/appkit docs` (no query) FIRST to see the documentation index. DO NOT guess paths - use the index to find correct paths.
 
-Examples of known paths:
+Examples:
 
-* Root index: `npx @databricks/appkit docs`
-* API reference: `npx @databricks/appkit docs ./docs/docs/api.md`
-* Component docs: `npx @databricks/appkit docs ./docs/docs/api/appkit-ui/components/Sidebar.md`
+* Documentation index: `npx @databricks/appkit docs`
+* View a section: `npx @databricks/appkit docs "appkit-ui API reference"`
+* Full index (all API entries): `npx @databricks/appkit docs --full`
+* View specific doc: `npx @databricks/appkit docs ./docs/plugins/analytics.md`
 
 ## LLM checklist (before finalizing code)[​](#llm-checklist-before-finalizing-code "Direct link to LLM checklist (before finalizing code)")
 
@@ -64,7 +65,7 @@ Examples of known paths:
 
 * `package.json` has `"type": "module"`
 * `tsx` is in devDependencies for dev server
-* `dev` script uses `NODE_ENV=development tsx watch server/index.ts`
+* `dev` script uses `NODE_ENV=development tsx watch server/server.ts`
 * `client/index.html` exists with `<div id="root"></div>` and script pointing to `client/src/main.tsx`
 
 ### Backend[​](#backend "Direct link to Backend")

package/docs/{docs/development → development}/local-development.md

@@ -4,9 +4,9 @@
 
 * [Node.js](https://nodejs.org) v22+ environment with `npm`
 * Databricks CLI (v0.287.0 or higher): install and configure it according to the [official tutorial](https://docs.databricks.com/aws/en/dev-tools/cli/tutorial).
-* A new Databricks app with AppKit installed. See the [Quick start](/appkit/docs.md#quick-start) for more details.
+* A new Databricks app with AppKit installed. See [Bootstrap a new Databricks app](./docs.md#quick-start-options) for more details.
 
-Once your app is bootstrapped according to the [Quick start](/appkit/docs.md#quick-start) guide, you can start the development server with hot reload for both UI and backend code.
+Once your app is bootstrapped according to the [Manual quick start](./docs.md#manual-quick-start) guide, you can start the development server with hot reload for both UI and backend code.
 
 In the application root directory, run the following command to start the development server:
 

package/docs/{docs/development → development}/project-setup.md

@@ -9,7 +9,7 @@ Recommended structure (client/server split):
 ```text
 my-app/
 ├── server/
-│   ├── index.ts              # backend entry point (AppKit)
+│   ├── server.ts              # backend entry point (AppKit)
 │   └── .env                  # optional local dev env vars (do not commit)
 ├── client/
 │   ├── index.html
@@ -44,9 +44,9 @@ The AppKit `server()` plugin automatically serves:
   "version": "0.0.0",
   "type": "module",
   "scripts": {
-    "dev": "NODE_ENV=development tsx watch server/index.ts",
+    "dev": "NODE_ENV=development tsx watch server/server.ts",
     "build": "npm run build:server && npm run build:client",
-    "build:server": "tsdown --out-dir build server/index.ts",
+    "build:server": "tsdown --out-dir build server/server.ts",
     "build:client": "tsc -b && vite build --config client/vite.config.ts",
     "start": "node build/index.mjs"
   },
@@ -149,7 +149,7 @@ export default defineConfig({
 
 ```
 
-### `server/index.ts`[​](#serverindexts "Direct link to serverindexts")
+### `server/server.ts`[​](#serverserverts "Direct link to serverserverts")
 
 ```ts
 import { createApp, server } from "@databricks/appkit";
@@ -193,7 +193,7 @@ If you don't already have a `client/` folder, create one and move your Vite app
 * Move `vite.config.ts` → `client/vite.config.ts`
 * Move `src/` → `client/src/`
 
-### 2. Create `server/index.ts` (New File)[​](#2-create-serverindexts-new-file "Direct link to 2-create-serverindexts-new-file")
+### 2. Create `server/server.ts` (New File)[​](#2-create-serverserverts-new-file "Direct link to 2-create-serverserverts-new-file")
 
 ```ts
 import { createApp, server } from "@databricks/appkit";
@@ -209,9 +209,9 @@ await createApp({
 ```json
 {
   "scripts": {
-    "dev": "NODE_ENV=development tsx watch server/index.ts",
+    "dev": "NODE_ENV=development tsx watch server/server.ts",
     "build": "npm run build:server && npm run build:client",
-    "build:server": "tsdown --out-dir build server/index.ts",
+    "build:server": "tsdown --out-dir build server/server.ts",
     "build:client": "tsc -b && vite build --config client/vite.config.ts",
     "start": "node build/index.mjs"
   }
@@ -228,7 +228,7 @@ AppKit's server plugin will automatically serve your Vite app in dev mode and `c
 To add SQL query execution capabilities:
 
 ```ts
-// server/index.ts
+// server/server.ts
 import { createApp, server, analytics } from "@databricks/appkit";
 
 await createApp({
@@ -241,6 +241,6 @@ Then create `config/queries/` and add your `.sql` files.
 
 ## See also[​](#see-also "Direct link to See also")
 
-* [Local development](/appkit/docs/development/local-development.md) - Running the dev server
-* [Configuration](/appkit/docs/configuration.md) - Environment variables
-* [Plugins](/appkit/docs/plugins.md) - Plugin configuration
+* [Local development](./docs/development/local-development.md) - Running the dev server
+* [Configuration](./docs/configuration.md) - Environment variables
+* [Plugins](./docs/plugins.md) - Plugin configuration

package/docs/{docs/development → development}/remote-bridge.md

@@ -4,7 +4,7 @@
 
 * [Node.js](https://nodejs.org) v22+ environment with `npm`
 * Databricks CLI (v0.287.0 or higher): install and configure it according to the [official tutorial](https://docs.databricks.com/aws/en/dev-tools/cli/tutorial).
-* A new Databricks app with AppKit installed. See the [Quick start](/appkit/docs.md#quick-start) for more details.
+* A new Databricks app with AppKit installed. See [Bootstrap a new Databricks app](./docs.md#quick-start-options) for more details.
 
 Remote bridge allows you to develop against a deployed backend while keeping your UI and queries local. This is useful for testing against production data or debugging deployed backend code without redeploying your app.
 

package/docs/{docs/development → development}/type-generation.md

@@ -106,5 +106,5 @@ data?.forEach(row => {
 
 ## See also[​](#see-also "Direct link to See also")
 
-* [Plugins](/appkit/docs/plugins.md) - Analytics plugin configuration
-* [API Reference](/appkit/docs/api/appkit-ui.md) - Complete UI components API documentation
+* [Plugins](./docs/plugins/analytics.md) - Analytics plugin configuration
+* [API Reference](./docs/api/appkit-ui.md) - Complete UI components API documentation

package/docs/development.md

@@ -0,0 +1,22 @@
+# Development
+
+AppKit provides multiple development workflows to suit different needs: local development with hot reload, AI-assisted development with Agent Skills, and remote tunneling to deployed backends.
+
+## Prerequisites[​](#prerequisites "Direct link to Prerequisites")
+
+* [Node.js](https://nodejs.org) v22+ environment with `npm`
+* Databricks CLI (v0.287.0 or higher): install and configure it according to the [official tutorial](https://docs.databricks.com/aws/en/dev-tools/cli/tutorial).
+* A new Databricks app with AppKit installed. See [Bootstrap a new Databricks app](./docs.md#quick-start-options) for more details.
+
+## Development flows[​](#development-flows "Direct link to Development flows")
+
+There are multiple supported development flows available with AppKit:
+
+1. **[Local development](./docs/development/local-development.md)**: Run the development server with hot reload for both UI and backend code. This is the default development flow and is suitable for most use cases.
+2. **[AI-assisted development](./docs/development/ai-assisted-development.md)**: Use an AI coding assistant with Agent Skills to explore data, run CLI commands, and scaffold your app interactively.
+3. **[Remote Bridge](./docs/development/remote-bridge.md)**: Create a remote bridge to a deployed backend while keeping your queries and UI local. This is useful for testing against production data or debugging deployed backend code without redeploying your app.
+
+## See also[​](#see-also "Direct link to See also")
+
+* [App management](./docs/app-management.md): Manage your AppKit application throughout its lifecycle using the Databricks CLI
+* [Architecture](./docs/architecture.md): Learn about the architecture of AppKit

package/docs/plugins/analytics.md

@@ -0,0 +1,169 @@
+# Analytics plugin
+
+Enables SQL query execution against Databricks SQL Warehouses.
+
+**Key features:**
+
+* File-based SQL queries with automatic type generation
+* Parameterized queries with type-safe [SQL helpers](./docs/api/appkit/Variable.sql.md)
+* JSON and Arrow format support
+* Built-in caching and retry logic
+* Server-Sent Events (SSE) streaming
+
+## Basic usage[​](#basic-usage "Direct link to Basic usage")
+
+```ts
+import { analytics, createApp, server } from "@databricks/appkit";
+
+await createApp({
+  plugins: [server(), analytics({})],
+});
+
+```
+
+## Query files[​](#query-files "Direct link to Query files")
+
+* Put `.sql` files in `config/queries/`
+* Query key is the filename without `.sql` (e.g. `spend_summary.sql` → `"spend_summary"`)
+
+### Execution context[​](#execution-context "Direct link to Execution context")
+
+* `queryKey.sql` executes as **service principal** (shared cache)
+* `queryKey.obo.sql` executes as **user** (OBO = on-behalf-of, per-user cache)
+
+The execution context is determined by the SQL file name, not by the hook call.
+
+## SQL parameters[​](#sql-parameters "Direct link to SQL parameters")
+
+Use `:paramName` placeholders and optionally annotate parameter types using SQL comments:
+
+```sql
+-- @param startDate DATE
+-- @param endDate DATE
+-- @param limit NUMERIC
+SELECT ...
+WHERE usage_date BETWEEN :startDate AND :endDate
+LIMIT :limit
+
+```
+
+**Supported `-- @param` types** (case-insensitive):
+
+* `STRING`, `NUMERIC`, `BOOLEAN`, `DATE`, `TIMESTAMP`, `BINARY`
+
+## Server-injected parameters[​](#server-injected-parameters "Direct link to Server-injected parameters")
+
+`:workspaceId` is **injected by the server** and **must not** be annotated:
+
+```sql
+WHERE workspace_id = :workspaceId
+
+```
+
+## HTTP endpoints[​](#http-endpoints "Direct link to HTTP endpoints")
+
+The analytics plugin exposes these endpoints (mounted under `/api/analytics`):
+
+* `POST /api/analytics/query/:query_key`
+* `GET /api/analytics/arrow-result/:jobId`
+
+## Format options[​](#format-options "Direct link to Format options")
+
+* `format: "JSON"` (default) returns JSON rows
+* `format: "ARROW"` returns an Arrow "statement\_id" payload over SSE, then the client fetches binary Arrow from `/api/analytics/arrow-result/:jobId`
+
+## Frontend usage[​](#frontend-usage "Direct link to Frontend usage")
+
+### useAnalyticsQuery[​](#useanalyticsquery "Direct link to useAnalyticsQuery")
+
+React hook that subscribes to an analytics query over SSE and returns its latest result.
+
+```ts
+import { useAnalyticsQuery } from "@databricks/appkit-ui/react";
+
+const { data, loading, error } = useAnalyticsQuery(queryKey, parameters, options);
+
+```
+
+**Return type:**
+
+```ts
+{
+  data: T | null;      // query result (typed array for JSON, TypedArrowTable for ARROW)
+  loading: boolean;    // true while the query is executing
+  error: string | null; // error message, or null on success
+}
+
+```
+
+**Options:**
+
+| Option              | Type                | Default  | Description                             |
+| ------------------- | ------------------- | -------- | --------------------------------------- |
+| `format`            | `"JSON" \| "ARROW"` | `"JSON"` | Response format                         |
+| `maxParametersSize` | `number`            | `102400` | Max serialized parameters size in bytes |
+| `autoStart`         | `boolean`           | `true`   | Start query on mount                    |
+
+**Example with loading/error/empty handling:**
+
+```tsx
+import { useAnalyticsQuery } from "@databricks/appkit-ui/react";
+import { sql } from "@databricks/appkit-ui/js";
+import { Skeleton } from "@databricks/appkit-ui";
+
+function SpendTable() {
+  const params = useMemo(() => ({
+    startDate: sql.date("2025-01-01"),
+    endDate: sql.date("2025-12-31"),
+  }), []);
+
+  const { data, loading, error } = useAnalyticsQuery("spend_summary", params);
+
+  if (loading) return <Skeleton className="h-32 w-full" />;
+  if (error) return <div className="text-destructive">{error}</div>;
+  if (!data?.length) return <div className="text-muted-foreground">No results</div>;
+
+  return (
+    <ul>
+      {data.map((row) => (
+        <li key={row.id}>{row.name}: ${row.cost_usd}</li>
+      ))}
+    </ul>
+  );
+}
+
+```
+
+### Type-safe queries[​](#type-safe-queries "Direct link to Type-safe queries")
+
+Augment the `QueryRegistry` interface to get full type inference on parameters and results:
+
+```ts
+// config/appKitTypes.d.ts
+declare module "@databricks/appkit-ui/react" {
+  interface QueryRegistry {
+    spend_summary: {
+      name: "spend_summary";
+      parameters: { startDate: string; endDate: string };
+      result: Array<{ id: string; name: string; cost_usd: number }>;
+    };
+  }
+}
+
+```
+
+See [Type generation](./docs/development/type-generation.md) for automatic generation from SQL files.
+
+### Memoization[​](#memoization "Direct link to Memoization")
+
+**Always wrap parameters in `useMemo`** to avoid refetch loops. The hook re-executes whenever the parameters reference changes:
+
+```ts
+// Good
+const params = useMemo(() => ({ status: sql.string("active") }), []);
+const { data } = useAnalyticsQuery("users", params);
+
+// Bad - creates a new object every render, causing infinite refetches
+const { data } = useAnalyticsQuery("users", { status: sql.string("active") });
+
+```

package/docs/{docs/plugins → plugins}/custom-plugins.md

@@ -11,7 +11,7 @@ For a deeper understanding of the plugin structure, read on.
 
 ## Basic plugin example[​](#basic-plugin-example "Direct link to Basic plugin example")
 
-Extend the [`Plugin`](/appkit/docs/api/appkit/Class.Plugin.md) class and export with `toPlugin()`:
+Extend the [`Plugin`](./docs/api/appkit/Class.Plugin.md) class and export with `toPlugin()`:
 
 ```typescript
 import { Plugin, toPlugin } from "@databricks/appkit";
@@ -128,7 +128,7 @@ This pattern allows:
 
 ## Key extension points[​](#key-extension-points "Direct link to Key extension points")
 
-* **Route injection**: Implement `injectRoutes()` to add custom endpoints using [`IAppRouter`](/appkit/docs/api/appkit/TypeAlias.IAppRouter.md)
+* **Route injection**: Implement `injectRoutes()` to add custom endpoints using [`IAppRouter`](./docs/api/appkit/TypeAlias.IAppRouter.md)
 
 * **Lifecycle hooks**: Override `setup()`, and `shutdown()` methods
 
@@ -136,10 +136,10 @@ This pattern allows:
 
   <!-- -->
 
-  * **Cache management**: Access the cache service via `this.cache`. See [`CacheConfig`](/appkit/docs/api/appkit/Interface.CacheConfig.md) for configuration.
-  * **Telemetry**: Instrument your plugin with traces and metrics via `this.telemetry`. See [`ITelemetry`](/appkit/docs/api/appkit/Interface.ITelemetry.md).
+  * **Cache management**: Access the cache service via `this.cache`. See [`CacheConfig`](./docs/api/appkit/Interface.CacheConfig.md) for configuration.
+  * **Telemetry**: Instrument your plugin with traces and metrics via `this.telemetry`. See [`ITelemetry`](./docs/api/appkit/Interface.ITelemetry.md).
 
-* **Execution interceptors**: Use `execute()` and `executeStream()` with [`StreamExecutionSettings`](/appkit/docs/api/appkit/Interface.StreamExecutionSettings.md)
+* **Execution interceptors**: Use `execute()` and `executeStream()` with [`StreamExecutionSettings`](./docs/api/appkit/Interface.StreamExecutionSettings.md)
 
 **Consuming your plugin programmatically**
 
@@ -158,4 +158,4 @@ AppKit.myPlugin.myCustomMethod();
 
 ```
 
-See the [`Plugin`](/appkit/docs/api/appkit/Class.Plugin.md) API reference for complete documentation.
+See the [`Plugin`](./docs/api/appkit/Class.Plugin.md) API reference for complete documentation.

package/docs/{docs/plugins → plugins}/server.md

@@ -31,7 +31,7 @@ The Server plugin uses the deferred initialization phase to access routes from o
 The smallest valid AppKit server:
 
 ```ts
-// server/index.ts
+// server/server.ts
 import { createApp, server } from "@databricks/appkit";
 
 await createApp({

package/docs/{docs/plugins.md → plugins.md}

@@ -2,7 +2,7 @@
 
 Plugins are modular extensions that add capabilities to your AppKit application. They follow a defined lifecycle and have access to shared services like caching, telemetry, and streaming.
 
-For complete API documentation, see the [`Plugin`](/appkit/docs/api/appkit/Class.Plugin.md) class reference.
+For complete API documentation, see the [`Plugin`](./docs/api/appkit/Class.Plugin.md) class reference.
 
 ## Using plugins[​](#using-plugins "Direct link to Using plugins")
 
@@ -20,7 +20,7 @@ const AppKit = await createApp({
 
 ```
 
-For complete configuration options, see [`createApp`](/appkit/docs/api/appkit/Function.createApp.md).
+For complete configuration options, see [`createApp`](./docs/api/appkit/Function.createApp.md).
 
 ## Plugin phases[​](#plugin-phases "Direct link to Plugin phases")
 

package/{docs/docs.md → docs.md}

@@ -21,7 +21,38 @@ AppKit simplifies building data applications on Databricks by providing:
 * [Node.js](https://nodejs.org) v22+ environment with `npm`
 * Databricks CLI (v0.287.0 or higher): install and configure it according to the [official tutorial](https://docs.databricks.com/aws/en/dev-tools/cli/tutorial).
 
-## Quick start[​](#quick-start "Direct link to Quick start")
+## Quick start options[​](#quick-start-options "Direct link to Quick start options")
+
+There are two ways to get started with AppKit:
+
+* **AI-assisted** (recommended): Use an AI coding assistant with Agent Skills to explore data, run CLI commands, and scaffold your app interactively.
+* **Manual**: Use the Databricks CLI directly to create, bootstrap, and deploy your app.
+
+Choose the path that best fits your workflow; both approaches produce the same kind of AppKit-based Databricks application.
+
+## AI-first quick start[​](#ai-first-quick-start "Direct link to AI-first quick start")
+
+Databricks AppKit is designed to work with AI coding assistants through Agent Skills.
+
+Install Agent Skills and configure it for use with your preferred AI assistant:
+
+```bash
+databricks experimental aitools skills install
+
+```
+
+Once configured for your development environment, you can use your AI assistant to create and deploy new Databricks applications, as well as to iteratively evolve your app's codebase.
+
+Just prompt your AI assistant to create a new Databricks app, such as:
+
+```text
+Create a new Databricks app that displays a dashboard of the nyc taxi trips dataset.
+
+```
+
+To learn more about the Agent Skills, see the [AI-assisted development](./docs/development/ai-assisted-development.md) documentation.
+
+## Manual quick start[​](#manual-quick-start "Direct link to Manual quick start")
 
 Learn how to create and deploy a sample Databricks application that uses AppKit with the Databricks CLI.
 
@@ -44,7 +75,7 @@ The command will guide you through the process of:
 * (optionally) deploying the app to Databricks
 * (optionally) running the app in development mode
 
-Learn more about the various [development flows](/appkit/docs/development.md) available with AppKit.
+Learn more about the various [development flows](./docs/development.md) available with AppKit.
 
 ### Deploy the app to Databricks[​](#deploy-the-app-to-databricks "Direct link to Deploy the app to Databricks")
 
@@ -59,6 +90,6 @@ This deploys the sample app to Databricks.
 
 ## Next steps[​](#next-steps "Direct link to Next steps")
 
-* **[App management](/appkit/docs/app-management.md)**: Manage your AppKit application throughout its lifecycle using the Databricks CLI
-* **[API reference](/appkit/docs/api/appkit.md)**: Explore the complete API documentation
-* **[Core concepts](/appkit/docs/core-principles.md)**: Learn about AppKit's design principles and architecture
+* **[App management](./docs/app-management.md)**: Manage your AppKit application throughout its lifecycle using the Databricks CLI
+* **[API reference](./docs/api/appkit.md)**: Explore the complete API documentation
+* **[Core concepts](./docs/core-principles.md)**: Learn about AppKit's design principles and architecture