Join top executives in San Francisco on July 11-12, to hear how leaders are integrating and optimizing AI investments for success. Learn More
Software delivery platform Harness has announced the launch of AIDA (AI Development Assistant), a generative AI assistant to streamline software development lifecycle (SDLC) workflows. According to the company, unlike traditional AI applications that primarily focus on code development, AIDA addresses the entire SDLC, encompassing code error resolution, security vulnerabilities and cloud cost governance.
“Our approach ensures that developers have AI-powered assistance at every stage of the SDLC, which we think is a necessary approach to AI in software delivery to get full potential benefits,” Harish Doddala, VP of product management at Harness, told VentureBeat.
Harness claims its generative AI tool can enhance software engineering teams’ productivity by 30-50%.
AIDA also offers automated identification and explanation of security vulnerabilities, drawing on extensive training with publicly available data like common vulnerabilities and exposures (CVEs) and common weakness enumerations (CWEs).
Event
Transform 2023
Join us in San Francisco on July 11-12, where top executives will share how they have integrated and optimized AI investments for success and avoided common pitfalls.
Using models trained on security best practices and expert knowledge, the AI can generate explanations for security vulnerabilities and suggests remedies, thereby minimizing the time and effort needed for remediation.
Harness emphasized that this feature will assist developers in enhancing application security and maintaining code integrity throughout the SDLC. Any further customization based on specific code requirements will align with the company’s privacy and security policies.
The company said the AI solution can be integrated with all Harness platform workflows and capabilities, including continuous integration (CI), continuous deployment (CD), cloud cost management and feature flags.
Streamlining software development through generative AI
Doddala stated that offering developers automatic pinpointing and insights into root causes enables them to swiftly troubleshoot and resolve issues. This eliminates the need for manual log analysis.
AIDA analyzes log files, correlates error messages with known issues, and suggests fixes to troubleshoot and resolve deployment failures. Additionally, it uses generative AI to automatically identify security vulnerabilities and generate code fixes.
>>Follow VentureBeat’s ongoing generative AI coverage<<
“What sets our solution apart is its extensive training on known vulnerabilities and weaknesses, allowing it to offer targeted and accurate remediation suggestions,” said Doddala. “This distinguishes AIDA from traditional security testing tools by providing developers with actionable recommendations specific to their codebase and enhancing the overall security of the software.”
The AI tool, the company claims, also aids developers in managing cloud assets using natural language, allowing them to define policies for governing asset management and cost control without resorting to manual programming.
Doddala said the company employs a hybrid approach to ensure data privacy and security and is exploring using domain-specific data to train the models.
“We don’t send proprietary customer data without customers’ explicit consent, and we ensure appropriate safety protocols and security encryption standards are followed. As for the LLMs themselves, we are looking at using data trained by permissive licenses pre-trained with domain-specific data,” he added. “Harness leverages a combination of cloud APIs and our own LLMs.”
What’s next for Harness?
Doddala said that the initial release of AIDA marks only the beginning of its capabilities. In the coming months, AIDA will introduce additional AI functionalities, such as automated code reviews, AI-assisted authoring of CI/CD pipelines, and AI-supported chaos engineering experiments.
Harness’s long-term vision for AI involves continued innovation in generative AI and its integration into the fabric of software delivery.
“As generative AI evolves, it will continue to reshape the software development landscape, enabling faster, more efficient and higher-quality software delivery,” said Doddala. “We forecast that offerings like AIDA [will] play a key role in shaping the future of AI-driven software development and empowering developers with these transformative capabilities.”
>>Don’t miss our special issue: Building the foundation for customer data quality.<<
VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.
