> For the complete documentation index, see [llms.txt](https://docs.jetadmin.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.jetadmin.io/getting-started/start-here.md). # Build your first app with AI This walks you through building a working app in Jet Admin, end to end: describe it, connect your data, and publish it. You'll have something running in a few minutes. ## Before you begin Use a project where you can build an app and a small test dataset. Prepare a **Tickets** table with **Name**, **Status**, **Priority**, and **Assigned to** fields. Add three clearly labeled test records: two Open tickets and one Closed ticket. Use [Jet Databases](/user-guide/jet-databases.md) or an existing connected source. [Download sample ticket records](https://3448227606-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LQ08RFAKZvFADEiXKFy%2Fuploads%2FGsaJpVZels9y5R5amfGm%2Fsample-tickets.csv?alt=media). Import them into a test table, then check the field types. The Assigned to values are demo text labels; map them to your own users if your schema uses user references. ![New-app prompt with Design, microphone, and Create controls](https://3448227606-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LQ08RFAKZvFADEiXKFy%2Fuploads%2FLYcXgzVcQB0CAC4z5quh%2Fai-create-app-prompt.jpg?alt=media) Enter your app description in the dashboard prompt. The Design control is beside the attachment control. ## 1. Describe the app you want From your dashboard, type what you want to build into the prompt box. Be specific about the data and the view you need — for example: ``` Create a customer support ticket management app with a ticket queue and a ticket details panel. ``` Jet generates a working interface from your description: tables, forms, and detail views, already wired to the data model it inferred from your prompt. {% embed url="" %} ## 2. Connect your data Open the AI Assistant and [select the connected resource](/ai-app-builder/ai-assistant/select-data-sources.md) containing Tickets. If you didn't already point Jet at a data source, connect one now — or start on Jet's built-in Postgres database if you don't have one ready. See [Connecting your data](/user-guide/jet-databases.md) for the full list of supported sources. {% embed url="" %} Jet reads your schema and wires the generated tables, forms, and dashboards to read and write your real data — not a copy. Row- and column-level permissions are enforced automatically as part of this step. ## 3. Inspect the result and refine it Open [the Tickets page in Preview](/ai-app-builder/refine-an-app/select-a-page.md). Confirm all three test tickets appear. Choose Open in the filter and confirm only the two Open tickets remain. Open a ticket and compare its details with the source. Keep iterating with follow-up prompts (for example, on the Tickets page: "add a search field for Name, keep the current columns and Status filter"), or switch to the visual editor and click any element — like [selecting it in Preview](/ai-app-builder/refine-an-app/edit-components-in-preview.md) — to change it directly. If you need more control, drop into the code — React, Vue, or Angular — right in the editor. {% embed url="" %} Along the way, try [Desktop, Tablet, and Mobile](/ai-app-builder/preview-and-troubleshoot/control-app-preview.md), apply [a theme preset](/ai-app-builder/themes-and-appearance/apply-a-theme-template.md) if needed, and use [an invited test user](/ai-app-builder/preview-and-troubleshoot/preview-as-an-invited-user.md) to check the app's access behavior. ## 4. Publish When you're ready, publish your app. You can publish to a Jet Cloud URL or a custom domain (on paid plans) — see [Preview and publish an AI app](/ai-app-builder/test-and-publish/preview-and-publish-an-ai-app.md). Repeat the ticket list, filter, detail, and access checks in the published app. {% embed url="" %} If the app fails to load or an interaction fails, inspect [Console and logs](/ai-app-builder/preview-and-troubleshoot/inspect-app-console-and-logs.md). To extend this example with an assignment action, continue with [Build a support dashboard](/ai-app-builder/practical-guides/build-a-support-dashboard.md). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.jetadmin.io/getting-started/start-here.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.