mabl Adds Testing Harness for Code Produced by AI Agents
mabl announced in a press release new testing capabilities that independently verify software produced by coding agents. The tools let engineering and quality teams define testing objectives and guardrails, then review the effect of a code change from the terminal before opening a pull request.
The mabl knowledge graph assesses each change, identifies relevant tests and highlights gaps in test coverage. Integrations with Xray, Zephyr, TestRail and Azure DevOps connect existing test cases with agent activity and return results to those services.
The release also adds tools for coordinating test maintenance across workspaces. Desktop application testing will be available later for enterprise customers.
Mabl says its agents analyzed 1.58 million unique failures across 3.3 million agent sessions during the past 90 days. Coding agents made 3 million MCP tool calls to mabl and created more than 4,200 tests during that period.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.
Also, consider following us on social media:
AI Programming Weekly
Weekly news about AI tools for software engineers, AI enabled IDE's and much more.
Market report
2025 Generative AI in Professional Services Report
Thomson Reuters
This report by Thomson Reuters explores the integration and impact of generative AI technologies, such as ChatGPT and Microsoft Copilot, within the professional services sector. It highlights the growing adoption of GenAI tools across industries like legal, tax, accounting, and government, and discusses the challenges and opportunities these technologies present. The report also examines professionals' perceptions of GenAI and the need for strategic integration to maximize its value.
Read moreYou may also like
TestMu AI Named a Leader in Gartner's Agentic Software Testing Quadrant
Abstracta Introduces Quality Intelligence Framework for Software Releases
SandboxAQ Adds Agent Security and ROI Tools to Switch AI
Boost.ai Adds Model Testing and No Code Integrations
Meticulous Raises $15 Million for Automated Software Testing
Daily AI Brief: the AI news that matters, in your inbox.