Agentic AI refers to AI systems designed to act as autonomous or semi-autonomous agents: they can set or interpret goals, plan and sequence actions, use tools (like web browsers, code, or APIs), make decisions based on feedback, and adapt over time to complete tasks. Unlike a purely reactive chatbot that only responds turn-by-turn, agentic AI is oriented around ongoing task execution—breaking down objectives, coordinating steps, and sometimes operating with minimal human oversight within defined constraints.
Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.
Sign Up For Latest News

This brief introduces a generative AI agent architecture that can simulate the attitudes of more than 1,000 real people in response to major social science survey questions.
This brief introduces a generative AI agent architecture that can simulate the attitudes of more than 1,000 real people in response to major social science survey questions.


Scholars hope these generative agents based on real-life interviews can solve society’s toughest problems.
Scholars hope these generative agents based on real-life interviews can solve society’s toughest problems.


A Stanford study captures the gap between worker desires and AI’s abilities, and highlights areas ripe for research and development.
A Stanford study captures the gap between worker desires and AI’s abilities, and highlights areas ripe for research and development.


NNetNav learns how to navigate websites by mimicking childhood learning through exploration.
NNetNav learns how to navigate websites by mimicking childhood learning through exploration.


Leading Stanford faculty offer their expectations for artificial intelligence in the new year.
Leading Stanford faculty offer their expectations for artificial intelligence in the new year.
