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

# Blindsight Platform

> Three coordinated surfaces for AI safety: dataset integrity, an LLM‑traffic firewall, and endpoint DLP. One managed cloud workspace.

## What Blindsight does

Blindsight is a three‑part safety platform for AI systems, delivered as
a managed cloud service. Use whichever surfaces (or all of them) fit
your stack.

<Columns cols={3}>
  <Card title="Data Integrity" icon="shield-check" href="/data-integrity/overview">
    Scan training datasets for label errors, outliers, poisoning, bias, leaked
    secrets, and prompt‑injection payloads. Triage, heal, and audit the results.
  </Card>

  <Card title="Runtime Security" icon="bolt-lightning" href="/runtime-security/overview">
    A drop‑in firewall for LLM traffic. Scan prompts before they reach the model
    and responses before they reach the user.
  </Card>

  <Card title="DLP (endpoint)" icon="laptop" href="/dlp/overview">
    A signed desktop agent that intercepts LLM traffic at the OS network layer
    on every managed laptop. No application code changes.
  </Card>
</Columns>

All three surfaces share the same scanners, the same Apps, the same
event store, and the same admin console. They ship independently so
you can adopt one (or two) without committing to the rest.

## Pick a starting point

<Columns cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Sign in, scan your first dataset, and make your first Runtime Security call
    in about ten minutes.
  </Card>

  <Card title="Data Integrity overview" icon="book-open" href="/data-integrity/overview">
    Core concepts, severity scale, and the map of every feature.
  </Card>

  <Card title="Runtime Security overview" icon="code" href="/runtime-security/overview">
    Three ways to integrate the LLM‑traffic firewall, plus authentication.
  </Card>

  <Card title="DLP overview" icon="laptop" href="/dlp/overview">
    Endpoint coverage for shadow‑IT AI traffic across the whole workforce.
  </Card>
</Columns>

## How the surfaces relate

|                      | Data Integrity                                    | Runtime Security                                            | DLP (endpoint)                                                  |
| -------------------- | ------------------------------------------------- | ----------------------------------------------------------- | --------------------------------------------------------------- |
| **What it inspects** | Datasets at rest (images, text, NIfTI, detection) | Live LLM prompts and responses from instrumented apps       | Live LLM prompts and responses from any app on a managed device |
| **When it runs**     | On upload, on schedule, on demand                 | On every request, inline                                    | On every request, on the device                                 |
| **Who deploys it**   | The data / ML team                                | The application team                                        | IT, via MDM                                                     |
| **Integration**      | Web UI, REST API, scheduled scans                 | Reverse proxy (swap `base_url`) or REST scan endpoints      | Push the signed agent through Jamf, Kandji, Intune, GPO, SCCM   |
| **Output**           | Issue lists, healed datasets, compliance reports  | `allow` / `redact` / `block` verdicts, events, drift charts | Same verdicts, attributed to a device and a directory user      |

If you only need one surface today, start there. Wiring up the rest
later is additive: workspaces, Apps, API keys, observability, and
audit already know about all three.