> ## Documentation Index
> Fetch the complete documentation index at: https://docs.roserx.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Batch Testing
> Validate your agent's responses with batch tests before deploying to production.
Batch Testing is the RoseRx Platform's quality assurance system for validating agent responses. It lets you define sets of test questions, run them against your agent, and review the results — ensuring your agent provides accurate, compliant responses before (and after) going live.
Regular testing is one of the most effective ways to maintain response quality. Run batch tests after every significant change to your agent's configuration or knowledge base.
## Accessing batch tests
Navigate to **Testing** in the left sidebar. You'll see a list of all existing tests and their current status.
## Creating a test
Click **Testing** in the left sidebar to open the batch testing page.
Click the **Create Test** button in the top-right corner.
Give your test a descriptive name and select the **agent** you want to test. The name should reflect the purpose of the test — for example, "Post-KB Update — \[Medicine Name]" or "Guardrail Compliance Check".
Add the questions you want your agent to answer. You can use any of the three methods below — or combine them.
Click **Run Test** to begin. The RoseRx Platform sends each question to your agent sequentially and captures the response — an estimated runtime is shown based on the number of questions.
Each test can contain up to **100 questions**. Questions run one at a time against the live model, so larger tests take longer — the estimated runtime is displayed before you start.
## Adding questions
The RoseRx Platform provides three ways to add questions to a batch test:
Let RoseRx's AI generate questions automatically based on your agent's configuration, knowledge base, and guardrails. This is the fastest way to create comprehensive test coverage.
Simply click **Generate** and RoseRx will create a set of relevant questions tailored to your agent. You can review, edit, or remove any generated question before running the test.
AI-generated questions are a great starting point, but always review them to ensure they cover the specific scenarios you care about.
Import questions in bulk from a CSV file. This is ideal if you have an existing set of test questions from a previous testing cycle or another system.
Your CSV should contain one question per row. Upload the file and the platform will parse each row into an individual test question.
Type questions one by one using the manual entry field. This is best for targeted testing — for example, adding specific edge cases or compliance-critical questions that you want to verify.
Enter each question and click **Add** to include it in the test.
You can add more questions to an existing test at any time — even after the test has been run. This makes it easy to expand your test coverage iteratively.
## Test statuses
Each batch test moves through the following statuses:
| Status | Description |
| ------------- | ------------------------------------------------------------------------------- |
| **Draft** | The test has been created but not yet run. You can still add or edit questions. |
| **Scheduled** | The test is queued and will begin shortly. |
| **Running** | The test is actively in progress. A progress bar shows completion status. |
| **Completed** | All questions have been processed and results are available for review. |
| **Failed** | The test encountered an error and could not complete. |
While a test is running, the progress bar updates every few seconds. You can navigate away and return — the test will continue running in the background.
## Reviewing results
Once a test completes, click into it to review the results. You can filter the results by:
* **Answer status** — Success, Failed, Timeout, or Pending.
* **Rating** — Good, Acceptable, Poor, or Unrated.
### Rating system
Each answer can be rated to track quality over time:
| Rating | Meaning |
| -------------- | -------------------------------------------------------- |
| **Good** | The response is accurate, compliant, and well-written. |
| **Acceptable** | The response is adequate but could be improved. |
| **Poor** | The response is inaccurate, non-compliant, or unhelpful. |
| **Unrated** | The response has not yet been reviewed. |
Each test also records a **pass rate**, giving you a quick quality benchmark across runs.
### Question detail
Click any question in the results to see the full detail view:
* **Question** — The full text of the test question.
* **Answer** — The complete agent response, along with the model used and response latency.
* **Rating** — Set or change the rating.
* **Notes** — Add internal notes about the response quality or any issues identified.
* **Re-run** — Run the question again, for example after fixing a knowledge base gap.
You can also select multiple questions to **re-run or delete them in bulk**.
## Test actions
From the test list or within a test, you can perform the following actions:
* **Rename** — Change the test name.
* **Duplicate** — Create a copy of the test with all its questions (useful for re-running after changes).
* **Export CSV** — Download the test results as a CSV file for offline review or reporting.
* **Generate report** — Produce a printable report of the test results, ready to share with stakeholders.
* **Delete** — Permanently remove the test and its results.
* **Add questions** — Add additional questions to an existing test at any time.
## Best practices
Run batch tests after updating your Knowledge Base to ensure the agent still provides accurate responses with the new content.
After modifying guardrails or compliance settings, run tests that specifically probe the boundaries you've configured.
Create a standard set of test questions that you run regularly. Duplicate tests to quickly re-run them after making changes.
Use AI-generated questions for broad coverage and manual questions for targeted edge cases. This gives you the best of both worlds.