> 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?

See the latest QApilot releases, including CoWork, PII exposure detection, and other recent product changes that affect testing workflows today.

### 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.

***

### Automate Dual Sessions Journeys - Two Devices, One Test Scenario

QApilot now supports dual session test plans - letting you automate test scenarios that involve two users interacting within the same app simultaneously. Think of flows like a user raising a support ticket while an admin approves it, two users exchanging messages, or a sender and recipient completing a payment.

Each session runs independently on its own device. You configure dependencies between steps across the two sessions to control when one side waits for the other before proceeding.

1. Dependency Map - a side-by-side view of both test cases and all configured dependencies, for review and bulk editing.
2. Start time sync - Session B holds at its start until the designated trigger step in Session A is reached, so both sides are always in sync at dependency points.
3. Auto-populate dependencies - when configuring a dual session plan, dependencies already set up during recording are pulled in automatically.
4. Scheduler support - dual session plans can now be scheduled for recurring or one-time automated runs.

***

### Private Device Farm

Teams can now connect their own physical device infrastructure to QApilot and run test plans against it - no cloud device farm required. A private device farm is ideal for clients who need to test on specific hardware, operate in environments where cloud devices aren't an option, or want tighter control over device availability for scheduled runs.

QApilot manages Appium session routing and a lightweight remote agent on your device host (Mac mini or equivalent). Once connected, your private devices appear alongside your existing cloud farm devices in plan configuration and the Scheduler - no change to your authoring workflow.

How it works

· A remote agent (listener) runs on your device host machine and registers your connected devices with QApilot.

· QApilot's routing layer directs Appium sessions to the correct device when a plan or scheduled run targets it.

· Private devices are available for both on-demand runs and scheduled executions — particularly useful for teams with predictable device availability windows.

Private device farm setup requires coordination with the QApilot team. Reach out to configure the remote agent on your device host and register your devices.