> ## Documentation Index
> Fetch the complete documentation index at: https://evalgate.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Platform map

> A task-oriented map of EvalGate surfaces when the product feels too large.

# Platform map

EvalGate is one product with many surfaces. Use this page when you know the job but not which manual to open. Maturity and client gaps stay in [Feature status](https://evalgate.com/docs/platform/feature-status.md); behavior detail stays in the [current-behavior manuals](https://evalgate.com/docs/platform/feature-manuals.md).

## Choose by job

| You are trying to do this | Start here | Do not confuse it with |
| - | - | - |
| Understand the repository and current integration | [Repository activation](https://evalgate.com/docs/platform/repository-activation.md) | Proof that application behavior was executed |
| Inspect what happened | [Logs & Trace Explorer](https://evalgate.com/docs/platform/logs-explorer.md) | A complete run when required evidence is absent |
| Preserve examples of expected behavior | [Dataset Hub](https://evalgate.com/docs/platform/dataset-hub.md) and [feature manuals](https://evalgate.com/docs/platform/feature-manuals.md#dataset-hub) | Independently qualified truth merely because a row was saved |
| Define a reusable check | [Scorer Studio](https://evalgate.com/docs/platform/scorer-studio.md) or [LLM judges](https://evalgate.com/docs/concepts/llm-judge.md) | Proof that the check is accurate |
| Make a bounded semantic decision | [Decision judges (Jev)](https://evalgate.com/docs/platform/decision-judges.md) | A generative explanation or deployment approval |
| Compare application changes | [Playground](https://evalgate.com/docs/platform/feature-manuals.md#playground) and [Experiments](https://evalgate.com/docs/platform/experiments.md) | An evaluator-only benchmark |
| Measure the evaluator | [Compare evaluators](https://evalgate.com/docs/guides/compare-evaluators.md) and [Evaluator qualification](https://evalgate.com/docs/platform/evaluator-qualification.md) | The application's business success rate |
| Compare score regimes | [Calibration control plane](https://evalgate.com/docs/platform/calibration-control-plane.md) | Task-specific qualification or action permission |
| Review failures and suggestions | [Prepare review](https://evalgate.com/docs/help/review/prepare-review.md) and [Review Queue](https://evalgate.com/docs/platform/feature-manuals.md#review-queue) | Automatic approval from AI assistance |
| Govern a model call or side effect | [Runtime controls](https://evalgate.com/docs/platform/runtime-controls.md) | Universal interception of traffic outside EvalGate |
| Publish an artifact and verify its use | [Deployable assets](https://evalgate.com/docs/platform/deployable-assets.md) | An experiment's pending publish proposal |
| Explain the full remediation | [Unified Eval Loop](https://evalgate.com/docs/platform/unified-eval-loop.md) | Proof that every deployment has completed all stages |
| Read inconclusive results | [Resolve inconclusive results](https://evalgate.com/docs/help/evaluations/resolve-inconclusive-results.md) | Treating unknown as pass or fail |
| Connect a control to evidence | [Connect controls to evidence](https://evalgate.com/docs/guides/connect-controls-to-evidence.md) and [Risks & controls](https://evalgate.com/docs/platform/risks-and-controls.md) | A shipped universal audit registry |
| Inspect named production failure patterns | [Failure patterns](https://evalgate.com/docs/platform/failure-topics.md) | Inventory-only topic queues without why-it-matters |

## Four distinctions

1. **The application is not its evaluator.** A better answer and a better judge are different experiments.
2. **An observation is not an authoritative decision.** Acceptance policy and terminal composition decide how an observation is interpreted.
3. **Qualification is not permission.** Strong measurement evidence can coexist with an absent action approval.
4. **Source is not release proof.** Code, a declared API, a local test, an installed package, and a verified live workflow are separate evidence levels.

## Layer bridge

For how application behavior, evaluation, evaluator measurement, qualification, and authorization relate, start with [How the evaluation system fits together](https://evalgate.com/docs/concepts/evaluation-layers.md).

## Inventory

Every named product surface and its Shipped / Experimental status is listed in [Feature status](https://evalgate.com/docs/platform/feature-status.md). Prefer that inventory over historical section stamps in older manuals.

Canonical docs URL: [evalgate.com/docs](https://www.evalgate.com/docs).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.