Home/AI/ML Notes/Basics of Agents/Agentic AI: Distinctions & Special Topics
⌂ Main Page
Basics of Agents

Agentic AI: Distinctions & Special Topics

Decision agents, agentic AI vs. AI agents, agents vs. MoE and assistants, degrees of automation, Google Antigravity.

On this page

Decision Agents

Make transparent, consistent, and reviewable decisions formalized using structured logic, sub-decisions, data dependencies for them, and predictive models with choices that are auditable, explainable, and reproducible LLMs are unreliable decision-makers, but help with analysis playing a supporting role to extract business rules from documents, summarize policy changes, or compare model versions to detect differences:

LLMs still play a supporting role: they can extract business rules from documents, summarize policy changes, or compare model versions to detect differences.

Source: https://www.youtube.com/watch?v=Wtpwva8t1vs&t=1031s

Agentic AI versus AI agents

AI Agents vs. MoE

Source: https://www.youtube.com/watch?v=4-FH09AMsp0

Agents vs. Assistants

Degrees of Automation

Google Antigravity

AI-powered "agent-first" IDE for software development: antigravity.google.

Google’s response to agentic coding tools like Cursor and Windsurf (fork of VS Code powered by Gemini, Claude Sonnet 4.6, GPT-OSS-120B). Antigravity treats AI agents as autonomous actors capable of planning, executing, validating, and iterating on complex engineering tasks with minimal human intervention:

Antigravity 2.0 (May 19, 2026):

IDE vs. CLI: