# Preview-environment search and sharper PR review targeting

> 4 updates: PR review targets the right path and rejects tests that don't cover the change, Chat agent can now list and search preview environments,…

Source: https://qa.tech/changelog/2026-06-26

---
4 updates shipped on June 26, 2026.

In this release

1.  01[PR review targets the right path and rejects tests that don't cover the change](#2026-06-26-pr-review-targets-right-path)Highlight
2.  02[Chat agent can now list and search preview environments](#2026-06-26-chat-agent-lists-preview-environments)
3.  03[Follow a PR review live as it runs](#2026-06-26-follow-pr-review-live)
4.  04[PR review now reads the full PR conversation](#2026-06-26-pr-review-reads-full-conversation)

1.  Highlight
    
    Featured this release
    
    ## PR review targets the right path and rejects tests that don't cover the change
    
    Three behavioural improvements make PR review tests more accurate and harder to game.
    
    **High-risk path focus:** if the PR body, linked issue, or commits name a specific path as highest-risk, the agent tests it directly – not a substitute scenario that's easier to reach.
    
    **Coverage integrity:** tests that complete without actually exercising the changed code are rejected before the [review](https://qa.tech/product/pr-testing) is written.
    
    **Test data search:** before marking a scenario untestable, the agent searches your available projects and can create what it needs (for example, a second workspace) rather than skipping the coverage.
    
    [\# Direct link](#2026-06-26-pr-review-targets-right-path)
    
2.  Update 02 of 04
    
    ## Chat agent can now list and search preview environments
    
    Agents can browse your preview environments directly instead of asking for IDs.
    
    A new `list-preview-environments` capability lets the chat agent page through and search all preview environments for any application. Previously the agent could only see non-preview environments and had to ask you for IDs or URLs. Application details now also report a preview environment count so the agent knows when to go look. Search supports substring matching on name and description, and results are paginated so the agent handles large sets.
    
    [\# Direct link](#2026-06-26-chat-agent-lists-preview-environments)
    
3.  Update 03 of 04
    
    ## Follow a PR review live as it runs
    
    A "Follow the conversation live" link appears in the PR detail panel the moment a review starts.
    
    The in-progress review panel on the PR detail page now shows a direct link to the running chat. It's available from the moment a review triggers – before the review row exists – so you can jump in and watch without waiting for the page to update.
    
    [\# Direct link](#2026-06-26-follow-pr-review-live)
    
4.  Update 04 of 04
    
    ## PR review now reads the full PR conversation
    
    The agent now sees general discussion threads alongside line-level code review comments.
    
    When reviewing a GitHub or GitLab PR, the agent now also reads the PR's general conversation – questions, context, and decisions made in the thread – in a separate "Conversation" section before the line-level code [review](https://qa.tech/product/pr-testing) comments. For GitLab, all MR notes are included in both sections.
    
    [\# Direct link](#2026-06-26-pr-review-reads-full-conversation)
    

## 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