Tricentis Unveils AI-Powered Software Quality Tool Suite

Tricentis GmbH, a provider of automated software testing platforms, has unveiled its latest innovation: the AI Workspace. This new feature coordinates a team of intelligent agents aimed at assisting developers and enterprise teams in creating high-quality code efficiently.

The Agentic Quality Engineering Platform from Tricentis employs advanced artificial intelligence agents designed to enhance software development and quality assurance through autonomous actions while allowing human employees to maintain oversight, judgement, and accountability.

Tricentis describes the AI Workspace as a centralized command hub for a network of AI agents operating within a unified context. This setup facilitates collaboration among agents and serves as a comprehensive record system, managing testing, automation, performance, and software quality intelligence.

The company notes that while many generic AI coding tools may seem impressive and swift, developers face potential downtime risks if they lack a complete understanding of their projects or specific application requirements. This includes details regarding dependencies, application connections, and the overall context of enterprise workflows.

“AI can dramatically accelerate code creation, but concerns about the quality of the output are causing difficulty for CIOs,” said Kevin Thompson, Chief Executive Officer. “Enterprises demand speed but cannot afford the risks associated with insecure or low-quality AI-generated code.”

The AI Coding Tool Speed Paradox

Developers are currently navigating a wide array of AI tools that offer extensive coding functionality for delivery, migration, generation, and more. The expectations of time-to-value have shifted significantly over the past year, leaving many developers grappling with how these tools can either help or hinder their work.

A report from METR states that developers using AI tools might take up to 19% longer to resolve issues, a surprising delay, even though the engineers surveyed felt it sped them up by 20%. This paradox partially stems from the time spent debugging outputs generated by AI.

To address this challenge, both startups and established enterprises are focusing on creating improved tools that enhance the quality of AI-generated code and testing processes, rather than simply accelerating them for software engineering tasks.

“At Tricentis, we are already utilizing agentic testing and witnessing tangible benefits in our transformation endeavors,” stated David Cowell, Vice President of AI and Machine Learning. “A cloud migration that usually takes several months was completed in just a week with agentic AI.”

The company claims that employing multiple AI agents, each assigned specific roles within the software development lifecycle, helps maintain boundaries and refine the quality of AI-generated code.

The new AI Workspace includes Agentic Quality Intelligence, which continuously monitors changes, assesses risks, and evaluates quality signals throughout the development lifecycle to determine readiness for release. It automatically directs testing while escalating to human judgment only when necessary, significantly reducing false positives and alert fatigue.

Test automation enhances productivity by intelligently reusing test modules, minimizing duplication, improving maintenance, and managing risk. Agentic performance testing provides robust, AI-driven validation of performance by analyzing code design and execution, including APIs and system interactions.

Integrated into the company’s qTest product, Agentic Test Creation collaborates with test engineers to develop in-context tests. This feature enables them to author tests in natural language, resulting in reusable test cases that operate more swiftly and consistently while reducing redundancy and reliance on specialized expertise.

Image: SiliconANGLE/Microsoft Designer