# Onboarding, run-trace, and verdict improvements

> 4 updates: Chat-edited tests are tracked in the revisions sheet, Failed network requests show up in the run trace, A smarter onboarding chat, Smarter…

Source: https://qa.tech/changelog/2026-05-08

---
4 updates shipped on May 8, 2026.

In this release

1.  01[Chat-edited tests are tracked in the revisions sheet](#2026-05-08-chat-edited-tests-tracked-in-revisions)
2.  02[Failed network requests show up in the run trace](#2026-05-08-failed-network-requests-in-run-trace)
3.  03[A smarter onboarding chat](#2026-05-08-smarter-onboarding-chat)
4.  04[Smarter verdicts on partial test runs](#2026-05-08-smarter-verdicts-on-partial-runs)

1.  Update 01 of 04
    
    ## Chat-edited tests are tracked in the revisions sheet
    
    See exactly which conversation produced which version of a test.
    
    When the chat agent edits a test case, the resulting revision is now tagged with a "Chat" badge in the test's revisions sheet. Click the badge to jump back to the conversation that produced that change. Useful for understanding why a test looks the way it does, and for telling apart human edits from agent edits at a glance.
    
    [\# Direct link](#2026-05-08-chat-edited-tests-tracked-in-revisions)
    
2.  Update 02 of 04
    
    ## Failed network requests show up in the run trace
    
    If a request never reached the server, you'll see it now instead of having to guess.
    
    When a test triggers a `fetch` or `XMLHttpRequest` that fails before getting a response – DNS error, TLS error, connection refused, abort – the request now shows up in the Network panel of the run trace as a red ERROR entry with the failure reason. Previously these requests were invisible, which made it hard to tell whether your application was actually trying to talk to the API.
    
    [\# Direct link](#2026-05-08-failed-network-requests-in-run-trace)
    
3.  Update 03 of 04
    
    ## A smarter onboarding chat
    
    Onboarding now actively explores your app instead of asking for three tests and stopping.
    
    The default onboarding chat used to ask you for the first three to five tests and stop there. That was rarely enough to get a useful test suite. The new version actively crawls and explores your application, recovers when it hits a login wall or an IP allowlist, builds context recursively, and asks for the domain feedback that makes future test generation reliable. It generates tests in waves rather than in a fixed batch, and stores everything it learns as project knowledge so the agent doesn't ask you the same questions again later.
    
    Tests created during onboarding are now activated automatically instead of left as drafts, so your first run after signup is a real one.
    
    [\# Direct link](#2026-05-08-smarter-onboarding-chat)
    
4.  Update 04 of 04
    
    ## Smarter verdicts on partial test runs
    
    The Assessment Agent now treats "the agent didn't actually try the thing" differently from "the thing failed".
    
    A run where the agent only covered part of the test goal used to sometimes get a confident pass when the parts it did cover happened to work. The Assessment Agent now explicitly checks step coverage and detects when a blocker step was skipped rather than completed, and adjusts the verdict and confidence accordingly. Fewer wrong passes on partial runs, fewer wrong fails on tests that legitimately stopped early.
    
    [\# Direct link](#2026-05-08-smarter-verdicts-on-partial-runs)
    

## Your team moves fast. Can your testing keep up?

QA.tech agents test your product autonomously, so moving fast never means shipping broken. See how it works in a 30-minute demo.

[Get a demo](https://qa.tech/demo)

[QA.tech](https://qa.tech/)

SOC 2 Type 2 compliant

![Sensiba SOC 2 Type 2 compliant](https://qa.tech/assets/soc2-type2-badge-DPb1j9VX.png)

### Product

-   [Platform overview](https://qa.tech/product)
-   [AI QA Testing](https://qa.tech/ai-qa-testing)
-   [Web Testing](https://qa.tech/product/web-testing)
-   [Mobile Testing](https://qa.tech/product/mobile-testing)
-   [PR Testing](https://qa.tech/product/pr-testing)
-   [MCP](https://qa.tech/product/mcp)
-   [Use cases](https://qa.tech/use-cases)
-   [Changelog](https://qa.tech/changelog)

### Compare

-   [QA.tech vs Cypress](https://qa.tech/compare/qa-tech-vs-cypress)
-   [QA.tech vs Playwright](https://qa.tech/compare/qa-tech-vs-playwright)
-   [QA.tech vs Mabl](https://qa.tech/compare/qa-tech-vs-mabl)
-   [QA.tech vs QA Wolf](https://qa.tech/compare/qa-tech-vs-qa-wolf)
-   [AI vs Human QA](https://qa.tech/saas)

### Resources

-   [Docs](https://docs.qa.tech/)
-   [Blog](https://qa.tech/blog)
-   [Events](https://qa.tech/events)
-   [Pricing](https://qa.tech/pricing)
-   [Case Studies](https://qa.tech/case-studies)

### Company

-   [About](https://qa.tech/about-us)
-   [Partnerships](https://qa.tech/partnerships)
-   [Press](https://qa.tech/press)
-   [Contact Us](https://qa.tech/contact)
-   [Privacy Policy](https://qa.tech/privacy-policy)
-   [Terms of Service](https://trust.qa.tech/resources?s=mb9w4yjb03i3t8bjsq4jx3&name=main-agreement.pdf)
-   [Security & Compliance](https://trust.qa.tech/)

### Social

-   [](https://www.linkedin.com/company/qa-tech-ai/)
-   [](https://x.com/getqatech)
-   [](https://www.instagram.com/getqatech/)

© 2025 QA.tech. All rights reserved