Sauce Labs has announced that bring-your-own-model capabilities are available now to Sauce Labs enterprise customers within AURA, the company’s code verification and release assurance platform. The new capabilities allow enterprises to build software with any open source, open weight or proprietary LLM, the company said in its announcement, even being able to change them as technology, regulations or standards evolve while keeping it all governed in one platform.
While code velocity has risen dramatically, release velocity has been unable to keep pace, and AURA uses autonomous agents for test authoring, execution and diagnosis to close the gap between code generation and validation. “Because AURA is framework-agnostic, CI/CD-native, and designed for existing development environments, organizations can modernize the model layer without a rip-and-replace migration or fragmented release controls,” the company wrote.
“Enterprise AI should expand choice, not create a new layer of lock-in,” said Dr. Prince Kohli, CEO of Sauce Labs. “AURA lets customers choose the intelligence layer that fits their business while keeping one consistent, governed system for release assurance. Models can change; the foundation for production confidence should not.”
According to Sauce Labs, enterprises running AURA achieve independently validated results: 90%+ fewer production incidents and 47% faster release cycles, with 38% of engineering capacity reclaimed.
In its announcement, Sauce Labs said AURA gives customers the flexibility to:
● Choose supported models that align with internal security, privacy, governance, and architecture standards.
● Evaluate and change models based on accuracy, latency, cost, and policy without replacing the release assurance platform.
● Maintain one human-governed process across business intent, test authoring, execution, failure analysis, and production learning.
