---
title: Quickstart
description: From first conversation to predictions in production.
---

## Onboarding journey

1. **Scope the engagement**

    Contact your Avra representative at **sales@avra.ai**. We start by understanding the decisions you want to improve, the data you have, and the integration shape — API, batch, or embeddings — that fits your operation.

2. **Provision your workspace**

    Avra provisions a tenant-isolated workspace. You receive credentials for [app.avra.ai](https://app.avra.ai) and access to your **Data Contract** — the agreed schema for the relational data you will send.

3. **Send your data**

    Stream or upload your relational data through API, connectors, or SFTP. Every event is validated against your data contract; deviations trigger a notification, not a silent failure.

4. **Train your Relational Foundation Model**

    Avra pre-trains your RFM on your relational schema and temporal business data. For managed deployments, this runs in your tenant-isolated environment. For on-premise deployments, this runs inside your perimeter.

5. **Train downstream models**

    Task-specific models — credit, fraud, growth, custom — are trained on top of your RFM and the Graph Foundation Model. Each training run feeds signal back into your RFM, making the next iteration sharper.

6. **Promote to production**

    Validate offline against your holdouts. Mirror against production traffic. Promote when you meet your performance bar. Roll back with one alias reassignment if anything regresses.

## Once you are live

**[Dashboard](/dashboard)**

Monitor usage, manage models and versions, and govern access

**[API Reference](/api-reference)**

Real-time predictions, model discovery, and version control

**[Batch Inference](/integrate/batch-inference)**

Score entire portfolios on a schedule

**[Embeddings](/use-cases/embeddings)**

Use Avra representations as features in your own ML models

## Where to go from here

**I want to understand the platform first**

Read [Why Avra](/why-avra/the-challenge), then the [Platform Architecture](/platform) — the three layers, the flywheel, and how they compose.

**I want to see specific use cases**

[Credit Intelligence](/use-cases/credit-intelligence), [Fraud Detection](/use-cases/fraud-detection), [Growth & Sales](/use-cases/growth/lead-scoring), or [build your own model](/use-cases/embeddings) with embeddings.

**I'm ready to integrate**

Start with the [API Reference](/api-reference) for authentication, endpoints, and integration patterns.