> For the complete documentation index, see [llms.txt](https://docs.qapilot.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.qapilot.io/whats-new.md).

# What's New?

### CoWork: Agentic Human-in-the-loop Test Authoring

CoWork is a new agentic test authoring mode on QApilot that converts natural language or BDD test cases into automated recordings - with the user remaining in control throughout.

Previously, automating a test case required either fully manual recording through the RPA module or utilising Crawler to generate tests autonomously. There was no middle path for teams that already had test cases written and wanted to automate them directly.

With CoWork, users can import or upload their existing test cases, review the auto-generated BDD steps, and trigger an AI planner that reads the screen at each step, takes the appropriate action, and automatically replans when it encounters unexpected UI states - without interrupting the user. Once the run completes, the user can accept the recorded steps or refine them in the RPA module before finalising!

CoWork covers 30–50% of test cases with an estimated 50% cost savings, and works alongside our Crawler and Record & Playback as the third mode of test authoring on QApilot.

***

### PII Exposure Detection In Network Logs

QApilot now automatically scans network logs during test execution to detect exposed PII data, flagging leakage across 8 sensitive data categories before it reaches production.

Previously, identifying personal data leaking through API calls or network requests required manual inspection of logs - a slow and error-prone process with no visibility during test runs.

With this capability, every test execution includes a scan of network traffic for 8 PII categories including email addresses, phone numbers, and financial identifiers. Any detected exposure is surfaced in the test report, giving teams a clear signal of data leakage risks without requiring additional configuration or tooling.

It is now possible to catch sensitive data exposure at the testing stage, before it reaches end users or auditors.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.qapilot.io/whats-new.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.