Phasis develops platform for agentic orientation using World APIs and reality layers
When the founders at Phasis Inc. sought to develop a platform for orienting AI agents, they turned to graphs as a way to obtain a measurement of culture. The company wanted to better understand relations not just between people, but between a person and their values, beliefs and subcultures. The goal was to map culture […] The post Phasis develops platform for agentic orientation using World APIs…
Phasis Inc., a company developing AI agents, has created a platform that utilizes graphs, culture mapping, and World APIs to enable agents to understand and adapt to changing realities. Co-founder and CEO Brandon Farley explained that Phasis is essentially a representation of reality and the real world, providing a World API that helps agents orient themselves in various domains.
The World API is designed to be integrated into existing systems, offering the necessary primitives to build a reality layer and expertise. Phasis' primary endpoint, "/orient," allows users to send tasks and receive relevant World frames for agents to begin work, encompassing current state, material changes, supporting evidence, and uncertainties.
Farley emphasized that the durable asset is the World model, and companies using it will gain a significant advantage in AI deployment. The company sees a future with smaller, capable models, agent swarms, and auto-research, leading to remarkable advancements in intelligence applications.
Written by urgent.news from SiliconANGLE's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
