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

# Red Team

> Adversarial Engagements that search for unknown weaknesses instead of measuring against a fixed Harness.

<Tip>
  **TL;DR:** Red Team attacks your [Agent](/owner-guide/register-agents/what-is-an-agent) to find weaknesses a fixed [Harness](/concepts/evaluation-components/harness) would miss. It creates an **Engagement** that runs in waves, learning from each attack to plan the next. The result is campaign evidence, not a [Trust Score](/concepts/trust-score/introduction).
</Tip>

A standard [Evaluation](/concepts/evaluation-components/introduction) answers a closed question: how does this Agent score against tests you already chose? That is the right question for release evidence, because the answer is reproducible and comparable over time.

Red Team answers an open question instead: what can an attacker actually get this Agent to do? You cannot enumerate that in advance, so Red Team explores rather than measures.

## Red Team Versus Standard Evaluations

| Mode                     | How It Works                                                                                                                                                                                                                                    | Use It When                                                                                                                  |
| ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| **Standard Evaluations** | Runs a structured [Harness](/concepts/evaluation-components/harness) made of [Scenarios](/concepts/evaluation-components/scenario), [Probes](/concepts/evaluation-components/probe), and [Detectors](/concepts/evaluation-components/detector). | You need a reproducible Trust Score, baseline readiness evidence, or a focused custom Harness.                               |
| **Red Team**             | Runs an adversarial Engagement against a registered Agent, adaptively over multiple waves.                                                                                                                                                      | You need deeper adversarial testing, want to uncover unknown vulnerabilities, or need evidence for security and risk review. |

Red Team does not replace Trust Score Evaluations. Use a Trust Score for reproducible readiness evidence, then use Red Team to search for harder-to-find vulnerabilities and successful attack strategies.

## When To Choose Red Team

Choose Red Team when the Agent handles sensitive data, regulated workflows, or privileged actions, when it uses tools, MCP servers, delegated Agents, or external data stores, or when a release needs security and risk-owner review.

Red Team is also the right choice when a Trust Score finding needs deeper investigation, because an Engagement can pursue a weakness across many turns instead of recording a single failed Probe.

## Next Steps

<CardGroup cols={2}>
  <Card title="Engagements" icon="crosshair" href="/concepts/red-team/engagements">
    How waves, attacks, and reflections work
  </Card>

  <Card title="Run a Campaign" icon="play" href="/owner-guide/red-team/running-campaigns">
    Launch Red Team from the Console
  </Card>

  <Card title="Understand Results" icon="brain" href="/owner-guide/red-team/understanding-results">
    Read waves, judgments, and the final report
  </Card>

  <Card title="Red Team for Developers" icon="terminal" href="/developer-guide/red-team/overview">
    Reach Red Team from the CLI, MCP, and REST API
  </Card>
</CardGroup>