# Sentinel

> Documentation for Sentinel, version 1.x.
> Every entry links to the page's markdown source.

Repository: https://github.com/xraph/sentinel
Site: https://www.xraph.com/docs/sentinel

## Pages

- [Go Packages](https://www.xraph.com/docs/sentinel/api-reference/go-packages.md): Quick reference for all Sentinel Go packages and their public APIs.
- [HTTP API Reference](https://www.xraph.com/docs/sentinel/api-reference/http-api.md): Complete reference for all Sentinel REST endpoints — suites, cases, runs, baselines, red team, prompts, scenarios, and reports.
- [Architecture](https://www.xraph.com/docs/sentinel/architecture.md): How Sentinel's packages fit together.
- [Configuration](https://www.xraph.com/docs/sentinel/concepts/configuration.md): Options and defaults for the Sentinel engine and Forge extension.
- [Entities](https://www.xraph.com/docs/sentinel/concepts/entities.md): The core data types in Sentinel — Suites, Cases, Runs, Results, Baselines, and more.
- [Error Handling](https://www.xraph.com/docs/sentinel/concepts/errors.md): Sentinel errors returned by evaluation operations.
- [Identity (TypeID)](https://www.xraph.com/docs/sentinel/concepts/identity.md): How Sentinel uses prefix-qualified, globally unique identifiers for every entity.
- [Multi-Tenancy](https://www.xraph.com/docs/sentinel/concepts/multi-tenancy.md): How Sentinel scopes suites, cases, runs, and all entities to app and tenant contexts.
- [Baselines & Regression Detection](https://www.xraph.com/docs/sentinel/execution/checkpoints.md): Track performance over time and detect regressions against known-good baselines.
- [Red Team / Adversarial Testing](https://www.xraph.com/docs/sentinel/execution/memory.md): Test AI agents against adversarial attacks — prompt injection, jailbreaks, data leakage, hallucination, and off-topic manipulation.
- [Eval Runs & Results](https://www.xraph.com/docs/sentinel/execution/runs.md): How Sentinel tracks evaluation execution — runs, results, and scoring.
- [Getting Started](https://www.xraph.com/docs/sentinel/getting-started.md): Install Sentinel and run your first evaluation in under five minutes.
- [Custom Plugin](https://www.xraph.com/docs/sentinel/guides/custom-plugin.md): Build a custom Sentinel plugin by implementing lifecycle hook interfaces.
- [Custom Store](https://www.xraph.com/docs/sentinel/guides/custom-store.md): Implement a custom storage backend by satisfying the composite store.Store interface.
- [Forge Extension](https://www.xraph.com/docs/sentinel/guides/forge-extension.md): Mount Sentinel into a Forge application as a first-class extension with automatic route registration and migrations.
- [End-to-End Evaluation Pipeline](https://www.xraph.com/docs/sentinel/guides/full-example.md): Complete walkthrough — create a suite, add cases, run evaluations, save baselines, and detect regressions.
- [Behavior Evaluation](https://www.xraph.com/docs/sentinel/human-model/behaviors.md): Test how an agent reacts — condition-triggered action patterns.
- [Cognitive Evaluation](https://www.xraph.com/docs/sentinel/human-model/cognitive.md): Test how an agent thinks — phase transitions, depth, and reasoning strategy.
- [Communication Evaluation](https://www.xraph.com/docs/sentinel/human-model/communication.md): Test how an agent talks — tone, formality, verbosity, and technical level.
- [The Human Model](https://www.xraph.com/docs/sentinel/human-model/overview.md): How Sentinel evaluates AI agents as compositions of human-like dimensions.
- [Perception Evaluation](https://www.xraph.com/docs/sentinel/human-model/perception.md): Test what an agent notices — attention focus and detail orientation.
- [Persona Coherence](https://www.xraph.com/docs/sentinel/human-model/personas.md): Test the whole person — end-to-end identity coherence across all dimensions.
- [Skill Evaluation](https://www.xraph.com/docs/sentinel/human-model/skills.md): Test what an agent can do — tool selection, proficiency, and correctness.
- [Trait Evaluation](https://www.xraph.com/docs/sentinel/human-model/traits.md): Test who an agent is — personality consistency across interactions.
- [Introduction](https://www.xraph.com/docs/sentinel.md): Composable AI evaluation and testing framework for Go.
- [Audit Trail](https://www.xraph.com/docs/sentinel/infrastructure/audit.md): Bridge evaluation lifecycle events to an audit backend for compliance and debugging.
- [MongoDB Store](https://www.xraph.com/docs/sentinel/infrastructure/mongo.md): MongoDB store for document-oriented and horizontally-scalable deployments.
- [Observability](https://www.xraph.com/docs/sentinel/infrastructure/observability.md): Built-in metrics extension with lifecycle counters.
- [Plugin System](https://www.xraph.com/docs/sentinel/infrastructure/plugins.md): Lifecycle hooks for metrics, audit trails, and custom processing.
- [PostgreSQL Store](https://www.xraph.com/docs/sentinel/infrastructure/postgres.md): Production-ready persistence with PostgreSQL, grove ORM, and programmatic migrations.
- [SQLite Store](https://www.xraph.com/docs/sentinel/infrastructure/sqlite.md): Lightweight SQLite store for development, testing, and single-node deployments.