# Avra

> AI frontier lab building the Graph Foundation Model for enterprise decision intelligence. Pre-trained on 1B+ entity relationships across the Brazilian economy. Deployed for fraud, credit, and growth decisions in milliseconds.

## Docs

- [Timeline](https://docs.avra.ai/changelog/index.md): Product updates and announcements
- [Audit Logs](https://docs.avra.ai/dashboard/audit-logs.md): Tamper-evident record of sensitive actions across the dashboard and API.
- [Authentication & Sessions](https://docs.avra.ai/dashboard/authentication.md): Learn how Avra secures access and how to enable SSO for your organization.
- [Notifications](https://docs.avra.ai/dashboard/notifications.md): Email and in-app alerts for the events that matter to your team — driven by the same event catalog as webhooks.
- [Dashboard Overview](https://docs.avra.ai/dashboard/overview.md): Navigate the Avra dashboard to manage access, monitor usage, and orchestrate data operations.
- [Roles & Permissions](https://docs.avra.ai/dashboard/roles-permissions.md): Understand workspace-level access control and role-based permissions.
- [Team Management](https://docs.avra.ai/dashboard/team-management.md): Invite teammates, manage seats, and keep your workspace secure.
- [Batch Inference](https://docs.avra.ai/data-operations/batch-inference.md): Process portfolios, refresh segments, or generate large embedding sets asynchronously.
- [Customer Context Data Contracts](https://docs.avra.ai/data-operations/ingesting-context.md): Structure relational datasets and temporal features so Avra can train your Relational Foundation Model and downstream models safely.
- [Model Versioning](https://docs.avra.ai/data-operations/model-lifecycle.md): How Avra manages the Graph Foundation Model, your Relational Foundation Model, and the downstream models served from both — with versioning, aliases, and rollback you control.
- [SFTP Batch Inference](https://docs.avra.ai/data-operations/sftp-batch-inference.md): Run large-scale inference by dropping CSV / JSONL files in a secure SFTP bucket.
- [Webhooks](https://docs.avra.ai/data-operations/webhook-notifications.md): Real-time HTTPS callbacks for batch, model, workspace, and API-key events — configured per workspace.
- [Welcome to Avra](https://docs.avra.ai/getting-started/overview.md): Pre-trained foundation models for relational intelligence — composed into every decision your business makes.
- [Quickstart](https://docs.avra.ai/getting-started/quickstart.md): From first conversation to predictions in production.
- [Platform Architecture](https://docs.avra.ai/platform/architecture.md): A three-layer foundation for relational intelligence — pre-trained on the economy, adapted to your relational data, deployed inside your decisions.
- [Graph Foundation Model](https://docs.avra.ai/platform/foundational-model.md): A pre-trained model that understands entities and relationships before it ever sees your data.
- [Knowledge Graph](https://docs.avra.ai/platform/large-knowledge-graph.md): The temporal graph that underlies the Graph Foundation Model — 1B+ entities, the relationships between them, and how both evolve over time.
- [Adaptive Embeddings](https://docs.avra.ai/platform/matryoshka-embeddings.md): How our embeddings automatically adapt to your model's complexity without losing predictive power.
- [Relational Foundation Model](https://docs.avra.ai/platform/relational-foundation-model.md): A customer-specific relational representation layer pre-trained with self-supervised objectives on your schema, temporal history, and entity relationships.
- [Data Privacy & Compliance](https://docs.avra.ai/security/data-privacy-and-compliance.md): How Avra handles your data, ensures privacy, and complies with LGPD, GDPR, and related regulations.
- [Security Overview](https://docs.avra.ai/security/overview.md): Learn how Avra ensures the confidentiality, integrity, and availability of your data.
- [Vulnerability Disclosure Policy](https://docs.avra.ai/security/vulnerability-disclosure-policy.md): Our guidelines and commitment for working with the security community to report and resolve vulnerabilities.
- [Risk Bands](https://docs.avra.ai/solutions/credit-score/homogeneous-groups.md): Optimal score binning and homogeneous risk groups for operationalizing credit decisions.
- [Credit Intelligence](https://docs.avra.ai/solutions/credit-score/overview-and-methodology.md): Dynamic credit risk assessment powered by two pre-trained foundation models and your business outcomes.
- [Score Range and Interpretation](https://docs.avra.ai/solutions/credit-score/score-range-and-interpretation.md): How Avra delivers credit scores, probability of default, and embeddings — and how to use them.
- [Applications](https://docs.avra.ai/solutions/embeddings/embedding-applications.md): Learn how Avra's embeddings are applied across various use cases to deliver actionable insights for businesses.
- [Build with Embeddings](https://docs.avra.ai/solutions/embeddings/overview.md): Use Avra's learned representations as features in your own models.
- [Technical Guide](https://docs.avra.ai/solutions/embeddings/technical-implementation.md): Embedding specifications, dimension selection, and integration patterns.
- [Fraud Detection](https://docs.avra.ai/solutions/fraud/overview.md): Network-based fraud intelligence that catches patterns invisible to rule engines and isolated entity analysis.
- [Field Sales](https://docs.avra.ai/solutions/growth/field-sales.md): Optimize territory planning and visit prioritization with entity intelligence.
- [Lead Scoring](https://docs.avra.ai/solutions/growth/lead-scoring.md): Prioritize prospects by predicted value, not just firmographics.
- [Paid Media Optimization](https://docs.avra.ai/solutions/growth/paid-media.md): Enrich your ad platform data with entity intelligence for smarter targeting and bidding.
- [Overview](https://docs.avra.ai/solutions/overview.md): Two pre-trained foundations, composed into any relational prediction task your business can label.
- [Our Approach](https://docs.avra.ai/why-avra/foundation-models.md): Two relational intelligence layers — one pre-trained on the economy, one adapted to your business — composed into every decision.
- [The Graph Advantage](https://docs.avra.ai/why-avra/how-were-different.md): Why relationships are more predictive than records.
- [The Problem](https://docs.avra.ai/why-avra/the-challenge.md): Why most entities remain invisible to traditional risk systems — and why that matters for your decisions.

## Optional

- [Trust Center](https://trust.avra.ai)
- [API Status](https://status.avra.ai)