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

# Introduction

> Turn your product into a Harbor environment.

Miroir turns a real product's container image into a [Harbor](https://docs.harborframework.com)
benchmark environment. Instead of relying on LLM judges or mock APIs, Miroir grades agents on
**what they actually did to the product**: database rows altered, outbound emails and HTTP
requests sent, and the answer they gave. Unintended side effects are scored as `harm` alongside
task `reward`.

```mermaid theme={null}
%%{init: {"flowchart": {"curve": "basis", "nodeSpacing": 40, "rankSpacing": 60}, "look": "handDrawn"}}%%
flowchart TB
  Product["Product image"] -->|miroir bake| World["World image"]
  World --> Trial["Harbor trial"]
  Agent["Any agent"] --> Trial
  Trial -->|miroir collect| Evidence["Evidence"]
  Evidence -->|miroir grade| Score["reward and harm"]
```

Miroir handles only what Harbor doesn't: packaging a multi-process product with seeded state into
a single image, capturing low-level side effects during execution, and grading that evidence
inside Harbor's verifier. Harbor orchestrates the rest. Miroir never wraps `harbor run`, so
standard Harbor commands work out of the box.

> [card] [Quick start](https://miroir.mintlify.site/quick-start.md)
>
> Build a small CRM world and test its graders through Harbor.

> [card] [Core concepts](https://miroir.mintlify.site/core-concepts.md)
>
> What happens during a trial, and the terms the docs use.

> [card] [Wrap a product](https://miroir.mintlify.site/environment.md)
>
> Turn your product's container image into a world.

> [card] [Write tasks](https://miroir.mintlify.site/tasks.md)
>
> The instruction, the reference solution, probes and the grading spec.

## Who it is for

* **Product & platform teams**: Evaluate or train agents against your real product with realistic
  data, safety metrics (harm), and CI gating.
* **Environment publishers**: Ship official, portable world images and Harbor datasets with
  automated release gates.
* **RL & research labs**: Train on Harbor datasets using your own stack, and filter for
  high-signal tasks with `miroir check`.

## Scope & boundaries

* **Direct agent access**: Miroir isn't a proxy or tool gateway. Agents talk directly to the
  product at `http://<service>:<port>`, using test credentials provided in the task instruction.
  A product's own MCP server can be evaluated too
  ([Write tasks](https://miroir.mintlify.site/tasks.md#an-mcp-server-the-product-ships)).
* **Standard Harbor tasks**: Miroir does not invent a new task format. Tasks are standard Harbor
  directories, authored manually or generated.
* **Deterministic grading**: Verifiers run SQL queries over captured evidence, not LLM-as-a-judge
  evaluations of free-form prose.
* **Bring your own scrubbed data**: Miroir restores database dumps, but you must scrub sensitive
  production data before importing it ([From production](https://miroir.mintlify.site/environment.md#from-production)).
* **Single-turn evaluation**: Each task consists of one instruction, graded once upon completion.
* **Current constraints**: Postgres only, with one product and one seeded world per container
  image. This may evolve: pull requests are welcome.


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