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

# Policy Gateway overview

> Policy Gateway is abliteration.ai's governance layer — rules, rollout modes, and audit events for every request.

<Note>
  Policy Gateway is a paid add-on. Every feature described here and in the subsections requires an active Policy Gateway plan. See [pricing](https://abliteration.ai/pricing).
</Note>

Policy Gateway is abliteration.ai's governance layer. It sits between your application and the model, evaluates every request and response, and emits a structured policy event.

## Plans

Three plans scale by usage volume, not by feature. Every plan gets the full Policy Gateway surface — projects, policies, all rollout modes, every connector, streaming metadata, policy events:

| Plan       | Volume vs base |
| ---------- | -------------- |
| Control    | 6×             |
| Advanced   | 20×            |
| Enterprise | 60×            |

See the [pricing page](https://abliteration.ai/pricing) for current prices.

## What a policy decides

Each request resolves to exactly one policy. The policy returns one of five **decisions**:

| Decision   | Meaning                                                        |
| ---------- | -------------------------------------------------------------- |
| `allow`    | Pass through unchanged                                         |
| `rewrite`  | Apply a rewrite before calling the model                       |
| `summary`  | Replace the output with a short summary                        |
| `escalate` | Forward to the escalation path (email or URL) for human review |
| `refuse`   | Block the request                                              |

The policy-level `enforcement_action` is one of `rewrite | block | summarize | escalate`. When a rule fires, the action maps to the decision (`summarize` → `summary`, `block` → `refuse`, others pass through). Every decision has a corresponding `reason_code` in uppercase: `ALLOW`, `REWRITE`, `SUMMARY`, `ESCALATE`, `REFUSE`.

## What a rule looks at

Rules are flat — there's no nested `match:` DSL.

| Field                | Effect                                                                                                                                                        |
| -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `allowlist`          | If non-empty, the message **must** contain at least one listed term, otherwise the decision is forced to `refuse`.                                            |
| `denylist`           | Any listed term triggers `enforcement_action`.                                                                                                                |
| `flagged_categories` | OpenAI-moderation categories (`harassment`, `hate`, `sexual`, `illicit`, and child-safety variants). Only evaluated on chat-completions and messages targets. |
| `redact_pii`         | Boolean. Strips PII patterns from the message text before upstream call.                                                                                      |

## Rollout modes

Rollout is **per policy**, not per rule.

| Mode       | `enabled` | `percentage` | Behavior                                                                                                      |
| ---------- | --------- | ------------ | ------------------------------------------------------------------------------------------------------------- |
| `shadow`   | `false`   | n/a          | Evaluate and log. Never block.                                                                                |
| `canary`   | `true`    | `< 100`      | Each request has (`percentage`/100) chance of being enforced.                                                 |
| `enforced` | `true`    | `100`        | Always enforced.                                                                                              |
| `rollback` | (derived) | n/a          | Auto-rollback fired — policy is temporarily demoted to shadow-like behavior until `cooldown_minutes` elapses. |

## Auto-rollback

Every policy can auto-demote itself if the rate of negative decisions spikes:

| Field                | Purpose                                                   |
| -------------------- | --------------------------------------------------------- |
| `threshold_pct`      | Rate (0–100) of matching decisions that triggers rollback |
| `window_minutes`     | Sliding window for the rate calculation                   |
| `min_requests`       | Minimum sample size before rollback can fire              |
| `cooldown_minutes`   | How long to stay in rollback before resuming              |
| `rollback_decisions` | Which decisions count (e.g. `["refuse", "escalate"]`)     |

## Data classification

Every policy carries a `classification` field: `public | internal | confidential | restricted`. It doesn't change behavior — it's metadata for audit and access reviews.

## Caveats

1. **Shadow mode still runs rules.** Every allowlist / denylist / category check happens even in shadow — it just doesn't block. This is what makes dry-run measurement possible.
2. **No per-rule rollout overrides.** Rollout mode is a single knob at the policy level. Adding a rule doesn't let you ramp that rule independently.
3. **Allowlist exclusivity.** A non-empty allowlist forces `refuse` on any message without an allowlist hit, regardless of denylist/category.
4. **Canary is probabilistic.** Two identical requests at `percentage=50` can have different outcomes.

## Next

<CardGroup cols={2}>
  <Card title="Onboarding" icon="play" href="/policy-gateway/onboarding">
    Create a project, write a policy, attach a key
  </Card>

  <Card title="Policy endpoints" icon="shield" href="/api/policy-endpoints">
    /policy/\* surface and headers
  </Card>

  <Card title="Streaming metadata" icon="rss" href="/capabilities/streaming-policy-metadata">
    The `policy` field on every SSE frame
  </Card>

  <Card title="Connectors" icon="rss" href="/policy-gateway/connectors">
    Stream events to your SIEM, log pipeline, or data lake
  </Card>
</CardGroup>