In benchmarking tests, AGS, along with xpander.ai's Agentic Interfaces, enabled AI agents to achieve a 98% success rate in multi-step tasks, a significant improvement over the 24% success rate achieved by agents using traditional methods. The company aims to democratize AI agent development, making it accessible to a broader audience, and to transform how AI agents handle error management and context continuity.
Key takeaways:
- Israeli startup xpander.ai has introduced the Agent Graph System (AGS), a new approach to building more reliable and efficient multi-step AI agents based on underlying AI models such as OpenAI’s GPT-4o series.
- AGS uses a graph-based workflow that guides agents through appropriate API calls step by step, reducing out-of-sequence or conflicting function calls.
- xpander.ai aims to democratize AI agent development, offering AI-ready connectors that integrate easily with NVIDIA NIM (Nvidia Inference Microservices) and other systems.
- In benchmarking tests, AGS, paired with xpander.ai's Agentic Interfaces, enabled AI agents to achieve a 98% success rate in multi-step tasks, compared to just 24% for agents using traditional methods.