Examples

Pipeline applications are the primary product path. The model API, MCP tools, and terminal client are supporting capabilities. This section is organized by task. Each recipe answers one question — "how do I scaffold an app", "how do I validate and build it", or "how do I verify a managed deployment" — and stays on that one outcome.

Every recipe follows the same skeleton: the goal, what you need first, the commands, the output you should see, and a pointer to the reference page and troubleshooting for when it does not. The commands are copied from the reference pages and clients they document, not invented for the recipe; each recipe names its source page at the bottom.

Pipeline applications

Use this learning track to understand and review a managed pipeline application:

1. Pipeline application walkthrough — inspect one pipeline TOML and Rust transform together with the customer/Redgold ownership boundary.
2. Managed application artifacts — understand the schema, manifest, transform, tests, and contract reviewed in Git.
3. Validate a pipeline application change — check schema evolution, manifest lowering, transforms, and the public contract in one reviewable change.
4. Build a vertical — see how Redgold connects ingestion, datasets, transforms, routes, and deployment into the application repository.
5. Verify a managed application deployment — match the approved application version to a healthy environment and run a bounded owner-scoped smoke request.

Pipeline-app routes are managed-preview routes. The generated V1 route inventory is the authority for self-service public routes; it currently lists the model API routes only. Redgold coordinates application creation, dataset provisioning, route review, publication, and environment deployment directly during the preview.

Model API (supporting capability)

• Create an API key and make your first call — mint a key, set it in your environment, and confirm it against the model list.
• Call the model API from Python — drive /v1/chat/completions with the OpenAI SDK.
• Use the Anthropic Messages API — point the Anthropic SDK at the same endpoint with a bearer token.
• Check your model-API credit balance — read /v1/credits before a long run.
• Retry model API calls under rate limits — handle 429, 402, and 502 the way the API expects.

Your data and agents

• Connect an MCP client and query your data — attach Claude Code (or any MCP client) and run read-only SQL against a dataset you own.
• Drive an agent session from an MCP client — spawn a session and send it a prompt through the approval-gated agent tools.
• Delegate a task to another agent — choose the customer REST or authorized managed agent-cli path for a bounded subtask.

Repositories and pipeline applications

• Connect GitHub review automation — prepare an onboarded repository for App-based reviewer and fixer workflows.
• Validate a pipeline application change — check schema, manifest, transform, tests, and generated references together.
• Walk through the tickets API — exercise a complete owner-scoped application's lifecycle.
• Verify a managed application deployment — match a deployed version to its repository change and smoke result.

Terminal client

• Install the terminal client — install redgold and rac with one command and confirm the client picked up your key.
• Point the terminal client at another API host — connect the client to a self-hosted instance.
• Run a one-shot agent task in CI — drive a single task to completion with an exit code you can gate on.