Agentic AI

An agentic AI system is one that acts - not just responds. Rather than producing a single output for a single input, an agent receives a goal, breaks it into steps, uses available tools to execute those steps, and iterates based on intermediate results until the goal is achieved or it determines it cannot proceed.

What makes a system "agentic"

Three properties distinguish agents from standard LLM prompting:

• Planning: The model decomposes a goal into subtasks and sequences them.
• Tool use: The model calls external functions (search, code execution, APIs, file I/O) based on what it needs.
• Feedback loops: The model observes the results of its actions and adjusts behavior accordingly.

Agent patterns

Common architectures include:

• ReAct (Reason + Act): Interleave reasoning steps with tool calls. The model "thinks out loud" before choosing an action.
• Plan-and-execute: Generate a full plan first, then execute steps with individual calls.
• Multi-agent: Orchestrator assigns tasks to specialized sub-agents (researcher, coder, reviewer).

Real-world examples

Agentic AI powers: Claude Code (reads your repo, writes code, runs tests, fixes failures), Devin (autonomous software engineering), and browser-use agents (navigates the web to complete tasks). In production, agents typically include a human-in-the-loop approval step before irreversible actions.

What limits current agents

Long-horizon reliability is the main challenge. Models accumulate errors over many steps - a mistake at step 3 may only surface at step 15. Context windows, cost per step, and latency add up. Most production agents work best on well-scoped, bounded tasks with clear success criteria.