<ul><li>Israeli startup xpander.ai has introduced the Agent Graph System (AGS), which is a new approach to building reliable and efficient multi-step AI agents.</li><li>AGS uses a graph-based workflow to guide agents through appropriate API calls step by step, reducing errors and inefficiencies.</li><li>In benchmarking tests, AGS demonstrated a 98% success rate in multi-step tasks, completing workflows 38% faster and with 31.5% fewer tokens.</li><li>xpander.ai's AGS sets a new standard for reliability and efficiency in automation, empowering businesses to harness the potential of AI-driven workflows.</li></ul>

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

Discover more