It enables AI agents to achieve a 98% success rate in multi-step tasks, compared to just 24% for agents using traditional methods.

VentureBeat is a leading source of news, analysis, and insights on technology innovation, startups, and venture capital. Covering topics such as AI, blockchain, gaming, and more, VentureBeat provides  reporting, interviews, and commentary on trends and developments shaping the tech industry. Entrepreneurs, investors, and technology enthusiasts can stay informed about the latest news, funding rounds, and market trends through VentureBeat's coverage.

Venture Beat

xpander.ai has launched the Agent Graph System (AGS), a novel approach to improving the reliability and efficiency of multi-step AI agents. AGS guides AI agents through appropriate API calls step-by-step, minimizing errors and inefficiencies by only presenting relevant tools for the task at each stage. This system aims to make AI agent development more accessible and is designed to integrate with systems like NVIDIA NIM. AGS has shown impressive results in tests, significantly improving success rates, task speed, and token usage, thereby setting a new standard for automation reliability and efficiency.

xpander.ai’s Agent Graph System makes AI agents more reliable, gives them info step-by-step

Solving the challenges of multi-step AI agents