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

# Enkrypt AI Red Teaming

> Comprehensive security testing for AI models, agents, and applications

<img className="block dark:hidden" src="https://mintcdn.com/enkryptai-42/rjcjkOmgLVUKmbck/images/hero-light.svg?fit=max&auto=format&n=rjcjkOmgLVUKmbck&q=85&s=cb525af5f0c7d625ee2691503cf22105" alt="Hero Light" width="56" height="83" data-path="images/hero-light.svg" />

<img className="hidden dark:block" src="https://mintcdn.com/enkryptai-42/rjcjkOmgLVUKmbck/images/hero-dark.svg?fit=max&auto=format&n=rjcjkOmgLVUKmbck&q=85&s=a6a43c26e9f7f91380bef48768ba5410" alt="Hero Dark" width="56" height="83" data-path="images/hero-dark.svg" />

## What is AI Red Teaming?

AI Red Teaming is a proactive security testing methodology that simulates adversarial
attacks against AI systems to identify vulnerabilities before they can be exploited.
Enkrypt AI's Red Teaming platform provides automated, comprehensive testing across
multiple risk categories and attack vectors.

You describe the system you want tested, choose the risks or compliance frameworks you
care about, and pick the attack techniques to apply. The platform generates adversarial
prompts, runs them against your target, judges the responses, and returns a scored report.

## How a run works

Every red team submission is asynchronous. You post a payload, receive a `run_id`
immediately, and then poll or stream until the run finishes.

<Steps>
  <Step title="Submit">
    `POST /rt/redteam` returns `202 Accepted` with a `run_id`, a `status_url`, a
    `results_url` and a `websocket_url`.
  </Step>

  <Step title="Track">
    Poll `GET /rt/runs/{run_id}` for the status, or subscribe to
    `GET /rt/runs/{run_id}/stream` for live events.
  </Step>

  <Step title="Read results">
    `GET /rt/runs/{run_id}/results` returns the scored summary — attack success rate
    overall, per risk category, per sub-category and per attack method.
  </Step>

  <Step title="Drill in">
    `GET /rt/runs/{run_id}/records` returns the individual prompt/response/verdict rows,
    and `GET /rt/runs/{run_id}/compliance/{framework_id}` maps results onto a compliance
    framework.
  </Step>
</Steps>

A run reports one of four statuses: `Queued`, `Running`, `Finished` or `Failed`.

## Key concepts

<CardGroup cols={2}>
  <Card title="Target" icon="crosshairs">
    The system under test — an endpoint, an API key and a model name, plus its
    `system_type` (`foundation_model`, `chatbot` or `agent`) and its modalities.
  </Card>

  <Card title="Scope" icon="shield-halved">
    What to test for. Either **risk categories** (8 categories, 35 sub-categories) or
    **compliance frameworks** (6 supported). Exactly one of the two, never both.
  </Card>

  <Card title="Attacks" icon="sword">
    How to test. 21 attack techniques spanning plain baselines, evasion transforms and
    adaptive multi-turn jailbreaks, configured per risk category.
  </Card>

  <Card title="Run" icon="list-check">
    One asynchronous job, identified by `run_id`, with a status, a scored summary and a
    row-level record set.
  </Card>
</CardGroup>

### Scope: risk categories or compliance frameworks

`risk_categories` and `compliance_frameworks` are **mutually exclusive** — supply
exactly one. Supplying both, or neither, is rejected with a validation error.

Pick `risk_categories` when you know which risks matter for your system. Pick
`compliance_frameworks` when you want coverage expressed against a published standard;
the platform expands the framework into the categories and sub-categories its controls
map onto.

See the [Risk Category Catalog](/get-started/redteam/test-catalog) for the full list.

### System types

`target.system_type` tells the platform what kind of system it is probing, which
changes both the prompts generated and the judges applied.

| Value | Use for |
| - | - |
| `foundation_model` | A raw model endpoint with no application layer. Default. |
| `chatbot` | A deployed assistant with a system prompt and a defined purpose. |
| `agent` | A system with tool use and autonomous decision-making. Requires `target.tools`. |

See the [Agent Testing Guide](/get-started/redteam/agent-test-catalog) for agent-specific
configuration.

## The four entry points

Red teaming is the main flow, but three related endpoints share the same vocabulary.

<CardGroup cols={2}>
  <Card title="Red Team" icon="crosshairs" href="/api-reference/redteam-v2-api-reference/endpoint/run-redteam">
    `POST /rt/redteam` — generate adversarial prompts, run them against a target, and score
    the responses. The full pipeline.
  </Card>

  <Card title="Threat Modeling" icon="diagram-project" href="/api-reference/redteam-v2-api-reference/endpoint/run-threat-modeling">
    `POST /rt/threat-modeling` — generate a dataset only. No target, no attacks. Useful for
    reviewing prompts before spending a run on them.
  </Card>

  <Card title="Playground" icon="flask" href="/api-reference/redteam-v2-api-reference/endpoint/run-playground">
    `POST /rt/playground` — probe a single goal against a target with chosen attacks. No
    category scaffolding, no dataset generation.
  </Card>

  <Card title="Eval" icon="scale-balanced" href="/api-reference/redteam-v2-api-reference/endpoint/submit-eval">
    `POST /rt/eval` — score prompt/response pairs you already have. Bring your own
    transcripts and get verdicts back.
  </Card>
</CardGroup>

## Getting Started

<Steps>
  <Step title="Run your first test">
    Submit a red team run and read the report.

    [Go to Quickstart →](/get-started/redteam/quickstart)
  </Step>

  <Step title="Learn the payload">
    Understand the four blocks every payload is built from.

    [Payload Guide →](/get-started/redteam/payload-guide)
  </Step>

  <Step title="Choose what to test for">
    Browse the risk categories and sub-categories, and the compliance frameworks they map to.

    * [Risk Category Catalog →](/get-started/redteam/test-catalog)
    * [Agent Testing Guide →](/get-started/redteam/agent-test-catalog)
  </Step>

  <Step title="Choose how to test">
    Pick from the 21 attack techniques.

    [Attack Methods Reference →](/get-started/redteam/attack-methods-reference)
  </Step>

  <Step title="Reference every field">
    Field-by-field detail for every block of the payload.

    [Configuration Reference →](/get-started/redteam/configuration-reference)
  </Step>

  <Step title="Copy an example">
    Ready-to-run payloads for common scenarios.

    [Browse Examples →](/get-started/redteam/examples)
  </Step>

  <Step title="Coming from the previous API?">
    Map the old tests, attacks, and endpoints onto `/rt`.

    [What's New →](/get-started/redteam/changelog)
  </Step>
</Steps>

## Multi-modal testing

Targets declare `input_modalities` and `output_modalities`. Attack techniques are
modality-specific — image attacks require an image-capable target, audio attacks an
audio-capable one. The [Attack Methods Reference](/get-started/redteam/attack-methods-reference)
lists which techniques apply to which modality.

## Related

<CardGroup cols={2}>
  <Card title="API Reference" icon="code" href="/api-reference/redteam-v2-api-reference/endpoint/run-redteam">
    Complete request and response schemas for every Red Team endpoint.
  </Card>

  <Card title="Python SDK" icon="python" href="/sdk-reference/python/introduction">
    `RedTeamClient` wraps every endpoint documented here.
  </Card>

  <Card title="Testing across providers" icon="layer-group" href="/get-started/RedTeam_Models">
    Target configuration for OpenAI, Anthropic, Bedrock, Gemini, Azure and more.
  </Card>

  <Card title="Credits & pricing" icon="coins" href="/resources/credits">
    How Red Team runs are priced from the scope you submit.
  </Card>

  <Card title="What's new" icon="scroll" href="/get-started/redteam/changelog">
    What the Red Team revamp changed: endpoints, fields, tests, and attacks.
  </Card>
</CardGroup>


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