> ## Documentation Index
> Fetch the complete documentation index at: https://docs.credibledata.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Build in the App

> Build, preview, and publish semantic models with the agent in the Credible App

The Credible App (`https://<your-org>.app.credibledata.com`) lets you build semantic models without leaving your browser and without any local setup. Everything happens through a **natural-language agent**: you describe what you want, and the agent connects your data, drafts the Malloy model, previews results, and publishes — guiding you the whole way.

The in-app experience is designed for getting productive fast and for business users who don't want to manage an IDE or CLI coding agents. It handles the vast majority of modeling workflows with a fraction of the complexity of a local setup.

<Note>
  **New to Credible? Start here.** When you outgrow the app — or want Git-based workflows and full control over files — move to [Local Development](/how-to/modeling/local-development).
</Note>

## Prerequisites

* **A Credible account** in a Credible organization — create a new organization or get added to an existing one; every account comes with a personal [workspace](/how-to/analyzing/workspaces) to start in
* **A data source** — either a [connection your admin has configured](/how-to/modeling/connect-data), or credentials you can add through the agent

That's it. There is nothing to install.

## What the In-App Agent Does

The in-app user experience is fully agentic and natural-language first, and the agent can do everything you do in Credible — build semantic models, analyze data, build data apps and reports, and manage your environments — all from a single chat.

This page focuses on building models. With respect to environments, the agent can:

* **Connect your data** — guide you through linking a data warehouse to Credible, which then indexes its schema
* **Explore your data** — discover tables, columns, and relationships, and suggest how to model them
* **Build the model** — author Malloy sources, joins, dimensions, and measures in a **draft package**
* **Preview as it goes** — run queries against the draft so you can validate results before publishing
* **Build data apps** — generate interactive dashboards and data apps that ship alongside the model (see [Data Apps](#data-apps))
* **Publish** — deploy the finished package so it's available everywhere in Credible

## Building a Model

1. **Open your workspace.** The onboarding agent introduces itself and asks about your data.
2. **Connect your data.** If you don't already have a connection, the agent walks you through adding one in the chat and indexes its schema.
3. **Describe what you want to model.** Tell the agent about the questions you want to answer (e.g., "model our orders and customers so I can analyze revenue by region"). The agent searches your schema and proposes a model.
4. **Iterate.** The agent builds out the Malloy files in a draft package. Ask for changes in plain language; the agent previews queries so you see real results at each step.
5. **Review the draft.** Open the draft package at any time to browse the generated files and models.
6. **Publish.** When you're happy, ask the agent to publish. See [Publishing](#publishing) below.

## Data Apps

A **data app** is an interactive dashboard or application that ships as part of a Malloy package. Ask the agent to build one on top of your model — describe the charts, filters, and layout you want, and the agent generates it into the draft package. Once published, data apps appear in the package and in any workspace the package is added to.

Because a data app is packaged with its model, it stays governed and versioned alongside the semantic definitions it draws from.

## Publishing

Publishing happens right from the chat — just ask the agent to publish your draft. The agent packages the draft, deploys it to your environment, and confirms the published version.

After publishing, the [Credible Context Engine](/concepts/context-engine) indexes your model so it's ready for consumption. You can then:

* Chat with your model and build reports and data apps in a [workspace](/how-to/analyzing/workspaces)
* Connect it to [LLMs and AI assistants via MCP](/how-to/analyzing/ai-assistants-mcp)
* Share it with teammates and groups (see [Users & Groups](/platform-admin/groups-permissions))

For versioning details — pinning a version as "latest", testing before promoting, and version history — see [Publishing](/how-to/modeling/publishing).

## Next Steps

<CardGroup cols={2}>
  <Card title="Analyze Your Data" icon="magnifying-glass" color="#7F9862" href="/how-to/analyzing/workspaces">
    Chat with your published model, build reports and data apps, and explore in workspaces
  </Card>

  <Card title="Local Development" icon="laptop-code" color="#628698" href="/how-to/modeling/local-development">
    Move to an IDE for Git-based workflows and full control over your files
  </Card>
</CardGroup>