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

# Real app testing and simulation testing

> Understand what each test runs and when to use it.

**Real app testing** runs your application and its tools to check the outcome.
**Simulation testing** tests prompts and models using simulated tool replies.

|                    | Real app testing                                                      | Simulation testing                                                 |
| ------------------ | --------------------------------------------------------------------- | ------------------------------------------------------------------ |
| What runs?         | Your app's entry point, model calls and instrumented tools.           | The prompt and model, with simulated tool replies where needed.    |
| What can it check? | The answer, tool calls and recorded effects in your test environment. | The model's decisions, answer quality and model-call cost.         |
| What do I need?    | The SDK, a test request, expected results and test dependencies.      | A complete prompt, example requests and criteria for good answers. |
| Where do I start?  | **AI Systems → your system → Real app testing**.                      | **AI Systems → your system → Start benching**.                     |

## Real app testing

Use this when you need to know whether the app actually did the right thing.
For a Weather Agent, check that its weather tool ran, returned a result and that
the answer used it correctly. For a refund assistant, check the recorded refund,
not only an answer saying “refunded.”

1. Open **Real app testing** and choose **Set up SDK**.
2. Connect the function that handles a request. Record its model and tool calls.
3. Add example requests and expected results. Run in a test environment with test
   services or isolated fixtures for external actions.
4. Publish the report to Bench and review it under **Real app testing**.

The [real app testing setup guide](/sdk/system-evaluation) includes the code and
report-publishing steps. Installing the SDK or connecting GitHub alone does not
run these tests. SDK reports cover the behavior you instrument and are labeled
**SDK test report**.

## Simulation testing

Use this to compare prompts and models before connecting the full app. Bench
runs model conversations and supplies simulated replies for declared tools.
For a Weather Agent, it can test how the model responds to an example weather
tool result. It does not check whether your weather service actually works.

1. Connect a repository or upload a complete prompt. If your app fills in parts
   of the prompt at runtime, provide a representative full prompt first.
2. Add rules in **Understanding** and example inputs and expected answers in
   **Test library**.
3. Choose **Start benching**. Review the cases, failed checks and proposed changes
   in **Results**. Runs using simulated tools are labeled **Simulation mode**.

See [test cases](/guides/test-library) and [evaluation results](/guides/evaluations).
Simulation results do not verify real tool execution or changes to a database.

## How a scan fits in

A [quick scan](/guides/quick-scan) reads code and identifies things to investigate.
It does not run either kind of test. Open a finding's right sidebar to see its
source evidence and next step. A missing prompt or an untested tool is a coverage
gap until tested.

<Note>
  The SDK also has scripted conversation helpers such as `simulateSystem`. These
  can drive your real app with isolated test dependencies across several turns.
  Their evidence depends on the app and tools you connect; they are different from
  the simulated tool replies in a prompt bench. See
  [scripted app conversations](/sdk/system-evaluation#simulate-a-customer-conversation).
</Note>