From idea to running application.

Build the application around your idea.

Start a web or mobile app, choose a sample with its own database, or import a GitHub repository. Give an agent coding tasks, review its changes, and try the application in a private preview.

1. 1.Create
2. 2.Preview
3. 3.Publish

• Keep application code, Git history, and agent conversations together.
• Start with managed Onyx credentials and configure Firebase for deployment.
• Publish web releases or build Android and iOS apps through Expo.

Investigate, understand, and act.

Give an agent a question or a task. It investigates your data, runs analysis, and can create dashboards, scripts, documents, and other resources with the permissions you grant.

1. 1.Ask
2. 2.Investigate
3. 3.Act

• Choose the model, thinking level, and actions available to each task.
• Follow progress, review evidence, and download supporting files.
• Continue with follow-ups or resume interrupted work from saved progress.

Give your application a connected foundation.

Model your data, define relationships, search records, and access your backend through APIs and SDKs. The database sits alongside the tools you use to build your application.

1. 1.Model
2. 2.Query
3. 3.Connect

• Work with structured data, schema-defined relationships, and search.
• Manage schemas, access keys, snapshots, and database deployments.
• Integrate through TypeScript, Python, Kotlin, and Go SDKs.

Turn database queries into predictions.

Build neural networks from saved Onyx queries. Map features and targets, configure the architecture, monitor training, and publish a model your applications can call.

1. 1.Map data
2. 2.Train
3. 3.Predict

• Configure input transforms, output mappings, and model layers.
• Inspect training runs and test published model versions.
• Predict from input objects or saved scripts through the API and TypeScript SDK.