Tagged articles
risk-driven testing
10 articles · Page 1 of 1
The article outlines four 2026 trends in test coverage optimization: risk-driven coverage models binding metrics to business risk, AI-native test generation using LLMs and symbolic execution, real-time coverage observability embedded in CI/CD pipelines, and cross-stack coverage graphs unifying frontend, backend, and infrastructure layers.
AI TestingCI/CDcoverage observability
0 likes · 9 min read

This article explores intelligent regression testing (IRT), a risk-driven paradigm that uses code semantic analysis, change impact modeling, and AI-powered test selection to reduce regression suite execution by 63% while improving defect detection by 9.2%, detailing key techniques like AST-based change awareness, LLM-assisted test generation, and engineering practices for overcoming cold-start and environment heterogeneity challenges.
ASTDevOpsIntelligent Regression Testing
0 likes · 9 min read

The article examines how test coverage in 2026 shifts from simple percentage goals to risk‑driven, AI‑enhanced, and visualized approaches, highlighting the RDC model, LLM‑assisted gap analysis, causal graph visualizations, and left‑right coverage governance across CI/CD and production environments.
AI-assisted testingCI/CD governanceObservability
0 likes · 7 min read

Facing a multi‑year, multi‑billion‑dollar core banking migration, the quality‑assurance team compressed a 3‑month testing window to two weeks by deploying risk‑driven test prioritisation, contract‑based end‑to‑end testing, layered automation, AI‑powered defect diagnosis and production‑traffic replay, delivering a dramatic efficiency leap while maintaining zero‑tolerance data accuracy.
AIautomationfinancial systems
0 likes · 22 min read

This article describes Baidu's risk‑driven delivery approach, detailing the three current testing challenges, the design of a quality‑assessment system that uses machine‑learning (logistic regression) for risk identification, control and decision, and the resulting improvements in testing efficiency and quality.
AIautomationmachine learning
0 likes · 14 min read

This article analyzes Baidu's risk‑driven delivery approach, detailing how machine‑learning models identify, control, and decide on testing risks, replace manual judgments, improve test efficiency and quality, and deliver measurable savings and bug interceptions across large‑scale software projects.
automated deliverylogistic regressionmachine learning
0 likes · 13 min read

Baidu’s risk‑driven delivery system applies a machine‑learning quality‑assessment model that automatically identifies, controls, and decides testing risks across over 50 features, enabling precise test selection, intercepting hundreds of bugs, cutting test waiting time from 50 to 2 hours, and paving the way toward fully automated intelligent testing.
AIquality assessmentrisk management
0 likes · 15 min read

This article examines Baidu's risk‑driven delivery approach and AI‑powered intelligent testing, explaining how automated risk assessment, task allocation, test‑scope analysis, and quality‑score models can dramatically lower reliance on human judgment, improve testing efficiency, and accelerate project release cycles.
AI in software testingIntelligent TestingProject Delivery
0 likes · 14 min read

Baidu’s AI‑driven, risk‑based testing framework automatically identifies high‑risk projects, allocates tasks, defines precise test scopes, and localizes defects using white‑box analysis and quality‑score models, cutting test‑case volume by up to 90 % and reducing release‑gate time from 50 hours to two, dramatically improving efficiency and defect recall.
AI in software testingContinuous Integrationintelligent decision system
0 likes · 15 min read

This article examines Baidu's risk‑driven, AI‑enhanced approach to unmanned software delivery, detailing the evolution of testing automation, the three human dependencies it eliminates, and the essential capabilities—comprehensive testing, stable builds, and precise risk evaluation—required to free testers from manual intervention.
AI automationContinuous Integrationquality assessment
0 likes · 12 min read
