What is agentic AI today?

What changed. MIT's Phillip Isola framed agents as models wrapped with tools, memory, and an action loop, emphasizing that real agents interact with digital or physical environments.

Technique / discovery. Tool and memory wrappers around foundation models; environment interaction and trial-and-error learning.

Why it matters. Much of practical differentiation sits in the harness, environment, feedback loop, and permissions rather than in a unique foundation model.

Application. Enterprise automation and human-computer interaction

Evidence maturity. Commentary (source tier B)

Identified bottleneck. Open environments are hard to model and actions create safety and evaluation challenges.

Caveat / evidence note. Expert interview, not a new empirical study.

Review status. Reviewed. User requested: Yes.

• MIT (opens in a new tab)

A reproduction tutorial is not yet available for this entry. The closest reviewed material is Agent planning and cognitive architectures and AI paradigms and knowledge representation.