Introduction to AI Agents

Explore the fundamentals of AI agents by understanding their autonomous perceive-reason-act

capabilities. Learn to distinguish agents from AI models, examine software, physical, and hybrid
agent types, and trace the evolution from rule-based systems to advanced LLM-powered agents.
This lesson helps you identify when building an agent is appropriate by focusing on complex
decision-making, dynamic contexts, and unstructured data challenges.

The landscape of AI is rapidly evolving, especially with the rise of large

language models (LLMs). While early LLM applications focused on single-turn
interactions or basic text generation, the field of AI agents, with its roots in
earlier rule-based and learning-based systems, has seen a significant
resurgence and transformation. A new category of intelligent systems,
powered by LLMs, has emerged. These systems are not limited to processing
information in isolation. They are designed to carry out complex, multi-step
tasks on behalf of users, often without explicit instructions at every step.

In this course, we’ll move beyond individual agents to focus on agentic

system design. This means understanding how individual agents are not just
standalone entities, but are architected and integrated as part of larger,
cohesive systems. Effective agentic system design involves making deliberate
architectural choices and utilizing reusable patterns to create reliable,
scalable, and adaptive AI solutions. Real-world agentic systems often involve
multiple interacting agents, necessitating careful planning, communication,
and arbitration as fundamental design aspects.
By the end of this lesson, you will be able to:

 Define what makes a system an AI agent.

 Distinguish between AI models and agents.

 Identify different types of agents and their roles.

 Understand the evolution from rule-based to LLM-powered agents.

  Evaluate when to use an agent instead of a simpler solution.

What is an AI agent?
In the world of artificial intelligence, the term agent refers to a system that can
perceive its environment, make decisions, and act autonomously to achieve
specific goals. This concept, often summarized as ‘perceive-reason-act,’ is a
cornerstone of classical AI theory, notably popularized by Russell and Norvig.
Unlike a passive model that requires a user to query it or interpret its outputs,
an AI agent is an active entity. It can sense, think, and act on its own, often
without continuous human oversight.
Let’s break this down more concretely. At its core, an AI agent has three
fundamental capabilities:

Breaking down how an AI agent works: It perceives the environment (input), reasons to make a
decision (processing), and performs a task (output)

1. Perception: The agent must be able to sense its environment. This

could mean reading text from a user, analyzing images or audio, or
retrieving data from sensors or databases. The goal is to extract
meaningful information from the raw input.
2. Reasoning and planning: Once the environment is perceived, the
agent must make decisions. This involves understanding context,
selecting actions, and planning steps toward a goal. LLMs like GPT-4
are often used here, providing powerful language-based reasoning
abilities. Agents can be reactive, responding directly to immediate
stimuli, or deliberative, engaging in multi-step planning and reasoning
before acting.
3. Action execution: The agent must then act. This could mean sending a
reply, calling an API, triggering a robot’s motion, or updating a
 database. The key is that the agent’s actions are grounded in its
reasoning process and tailored to its goals.
This full pipeline, which includes sensing, interpreting, and acting, captures
what makes an AI system agentic rather than reactive. The autonomy levels
of agents can vary, from partial automation requiring human approval to full
independence, depending on the task and safety requirements.
Here’s a simple real-world analogy:

Imagine a personal AI assistant embedded in your smart home. It hears you

say, “Remind me to call mom at 6 PM.” It parses your speech (perception),
understands that this is a timed reminder (reasoning), and schedules an alarm
for 6 PM (action).
Another analogy that mimics a more complex agentic system:

Picture an AI travel concierge running on your phone. It sees your flight to

Berlin has been cancelled (perception), and reasons that you must still reach
Berlin tonight. It then checks alternate flights/trains, books the best combo,
and messages your hotel about the late arrival (plan and multi-step action).
This full pipeline, which includes sensing, interpreting, and acting, captures
what makes an AI system agentic rather than reactive.

Key characteristics of an AI agent are summarized in the following table:

Key Characteristics of an AI Agent

Feature Description
Autonomy Acts independently, initiating actions and making decisions without
continuous human intervention.
Goal-Oriented Consistently directs actions toward achieving predefined objectives,
Behavior rather than merely reacting or producing isolated outputs.
Perception and Continuously observes its environment, processes inputs, and adjusts
Feedback Loop behavior based on the outcomes or new information.
Continuity Maintains memory or context over time, allowing multi-turn reasoning.
Flexibility Can revise plans and policies when objectives or context change,
provided the agent’s perception, memory, and planning modules
support it.

This agent-centric view aligns with how intelligence is typically understood in

biological systems. It is not just about recognizing patterns, but about using
those insights to take meaningful action.

AI models vs. AI agents

A common point of confusion in AI system design is the distinction between
an AI model and an AI agent. Although both are foundational elements in
artificial intelligence, they serve very different roles.

AI model vs. AI agent

Let’s start with the simpler concept:

An AI model is a self-contained program trained to perform a specific

function. More precisely, an AI model is often an artifact (e.g., a set of learned
weights and biases) that is consumed by a program to perform a specific
function. For example:
 A classification model predicts whether an email is spam or not.

 A text generation model completes a sentence or writes a poem.

 A speech recognition model converts audio into text.

These models do not have goals, initiative, or awareness of context beyond

the current input. They wait for a prompt, compute an output, and stop. In this
sense, models are powerful, but passive.
An AI agent, by contrast, is an active system. It uses one or more models as
components within a larger decision-making process. An agent has autonomy,
memory, goals, and the ability to take action based on what it observes.
An agent might:

 Use a language model to understand instructions.

 Call a search tool to gather information.

 Store conversation history in a vector database to reuse facts or

preferences later.

 Monitor its success and adapt its behavior over time.

The key difference is this: the agent takes initiative and operates over time,
often within a loop of perception, reasoning, and action.

Comparison Between AI Model and AI

Agent
Feature AI Model AI Agent
Scope Narrow task Broader system of behavior
Role Computes outputs from Chooses actions in pursuit of goals
inputs
Context Limited to the current Maintains and updates internal context
Awareness inference window
Initiative Waits for input Acts autonomously when triggered or
scheduled
Tool Use No Yes, often includes multiple tools and models
Example Sentiment classifier Customer support assistant that answers,
escalates, and logs tickets
Here’s an analogy: If an AI model is like a calculator, then an AI agent is like a
personal assistant. The calculator waits for a formula, and gives a result. The
assistant listens to your needs, figures out what to do, takes initiative, asks
clarifying questions, and performs actions on your behalf.

Three categories of AI agents

AI agents can take many forms depending on how they interact with their
environment. One way to organize this variety is by categorizing agents based
on their mode of operation. Broadly, there are three main types:

Software-based agents (sandbox

environment)
These agents operate entirely in digital spaces. They interact with users,
applications, or data through APIs, web interfaces, documents, or databases.

Software-based AI agent

Examples include:

 A chatbot that provides customer service on a retail website.

 An email triage agent that categorizes and replies to messages.

 A trading bot that monitors financial news and executes trades.

Although these agents are not embodied in the physical world, they can still
carry out meaningful actions, such as updating records, sending alerts, or
triggering automated workflows.

Key characteristics:
 No physical sensors or hardware.

 Act through code, interfaces, and digital data.

  Often use tools like web search, file access, and language models.

Physical agents (embodied systems)

Physical agents interact with the real-world using sensors and actuators.
These systems perceive their surroundings through hardware, and perform
actions by physically affecting the environment.

Physical AI agent

Examples include:

 A domestic robot that cleans your home and responds to voice

commands.

 An autonomous vehicle that navigates traffic and avoids obstacles.

 A robotic arm on a factory floor that assembles products.

These agents require a complex integration of perception (e.g., cameras,

microphones, LiDAR), real-time reasoning, and precise control mechanisms.

Key characteristics:
 Sense the physical world using embedded sensors.

 Act using motors, arms, wheels, or other actuators.

 Must handle uncertainty, delay, and safety in real environments.

Hybrid and adaptive agents (real-world integration)
Hybrid agents combine both digital and physical capabilities. These agents
work across environments, and continuously adapt based on feedback. They
are capable of learning from both structured data, and unstructured sensory
input over time.

Hybrid AI agent
Examples include:

 An AI-driven traffic system that analyzes live camera feeds and adjusts
signal timing based on congestion.

 A healthcare assistant who monitors wearable devices, suggests

treatment adjustments, and communicates with doctors.

 A warehouse robot that uses online databases to restock inventory and

physically moves goods.

These agents often blend software logic with real-world embodiment and rely
on learning mechanisms to refine their behavior over time.

Key characteristics:
 Operate across both digital and physical domains.

 Integrate multi-modal data (text, images, sensor readings).

 Adapt and improve through real-world feedback loops, potentially by

periodically retraining its perception module with logged sensor data.

Each of these categories highlights a different level of complexity and

environmental interaction. As we move from software-based to hybrid agents,
the challenges grow, and so do the opportunities for creating deeply intelligent
systems.

Evolution from rule-based systems to

LLM-powered agents
The idea of autonomous agents is not new. In fact, early AI systems from
decades ago could already make decisions and take actions. However, their
capabilities were limited due to the narrow scope of their design. Most early
agents were rule-based systems: if X happened, then do Y. This approach
worked for clearly defined, repetitive tasks, but it quickly failed in dynamic or
unpredictable environments.

Evolution of AI agents

Rule-based agents: Fixed logic, limited

flexibility
Rule-based or expert systems, such as MYCIN and XCON, were prominent in
the 1970s to 1980s. In rule-based systems, human developers explicitly
define all the rules.

Rule-based agent

For example:

 If the user says “I forgot my password,” then show a password reset

form.

 If the temperature exceeds 30°C, turn on the fan.

These systems are easy to understand and control. However, they do not
generalize well. They cannot infer new rules from data or handle edge cases
and ambiguity. Scaling such systems requires writing and maintaining
thousands of individual rules by hand.

Learning-based agents: Trial and feedback

The next major leap came with machine learning. Learning-based agents,
spanning supervised, unsupervised, and reinforcement learning paradigms,
shifted rule authoring from explicit human definition to data-driven
optimization. While supervised learning models, like CNNs and RNNs, enable
advancements in perception for agents (e.g., speech recognition in virtual
assistants), reinforcement learning (RL) introduces a powerful new paradigm.
It allows agents to learn complex behaviors through trial and error, receiving
rewards for good actions and penalties for bad ones. RL is often considered
the most ‘agent-like’ subset due to its focus on sequential decision-making in
dynamic environments.

AlphaGo’s breakthrough in 2016, for example, demonstrated its power. Given

that, in RL, agents learn through experimentation, this approach enables
agents to discover strategies that human designers might not think to program
explicitly.

Learning-based agent

For example:

 AlphaGo learned to defeat world-class Go players by playing millions of

games against itself.

 Robot arms trained with RL can learn to pick up objects without needing
precise location data.

While more flexible than rule-based systems, RL agents often require large-
scale training, significant compute resources, and carefully structured
environments. They are powerful, but not always practical for general-purpose
applications.

LLM-powered agents: Generalization through

language
The most recent breakthrough in agent design has come from large language
models (LLMs) such as GPT-4 (released March 2023), Claude, and Gemini.
While reinforcement learning discovers optimal policies through iterative
reward signals, large language models bring a new dimension: zero-shot
generalization. They achieve this by internalizing vast amounts of world
knowledge and reasoning capabilities directly within their parameters. This
enables them to understand and respond to novel tasks without explicit
retraining. These models are pretrained on massive datasets of human
language. This, in turn, gives them the ability to reason, plan, and coordinate
tasks using natural language instructions.

When LLMs are used within agent systems, they enable several powerful
capabilities:

 Tool use: Selecting and operating the right tool for a given job/action to
perform. The agent, through its reasoning, decides which tool to use
and what parameters to pass to it.
 Dynamic task planning: Decomposing complex goals into manageable
steps and deciding how to approach them.
 Conversational memory: Maintaining awareness across multiple turns
of dialogue.
 Generalization: Handling novel tasks without needing retraining.

LLM-powered agent

For example, a modern LLM-powered agent can handle a request like:

“Summarize this research paper and email the key points to my team.”
The agent can understand the instruction, extract and summarize the content,
format the result, and trigger an API call to send the email. None of these
behaviors need to be hardcoded in advance.
This level of flexibility marks a major shift. Agents are no longer just reactive
systems built on rigid logic. They are evolving into adaptive, collaborative, and
tool-using systems that can generalize their behavior across a wide range of
problems.

It’s crucial to acknowledge that while LLM-powered agents are immensely

powerful, they also come with inherent limitations. These can include issues
with reliability (e.g., generating inaccurate outputs often called hallucinations),
and interpretability (understanding why an agent made a particular decision).
Moreover, there can also be potential for biases, and challenges related to
high inference latency and security vulnerabilities. Understanding these
limitations is as important as recognizing their capabilities when designing
trustworthy agentic systems.

Question: Consider the following scenarios. For each, decide whether a rule-
based system or an AI agent would be the more appropriate solution, and
why.
 Scenario 1: A system that automatically turns off the lights in an office
building at 7 p.m. every weekday.
 Scenario 2: A system that responds to customer email inquiries,
categorizes them, and escalates complex cases to a human, learning
from past interactions.
 Scenario 3: A system that flags financial transactions over $10,000 for
manual review.
Evaluate your answer
When should you build an agent?
Note: In this course, our focus will be on LLM-powered agents. Whenever we
refer to an “agent,” we specifically mean an agent powered by a large
language model (LLM).
Not every problem needs an agent. Sometimes, a simple script or rule-based
automation is enough. Agents introduce complexity, cost, and often
uncertainty, so it’s important to be strategic about when to use them.

You should consider building an agent when your use case involves complex
decision-making, dynamic context, or flexible task execution that traditional
automation struggles to handle. Below are three key signals that suggest an
agent may be the right choice:

Deciding when to build an LLM-powered AI agent

The task requires contextual decision-

making
Agents shine in situations where outcomes depend on nuanced judgment. If
your workflow involves interpreting ambiguous input, balancing trade-offs, or
adjusting behavior based on prior interactions, an agent can outperform static
rules.

An example of this can be a refund approval process that depends on the

customer’s past behavior, the tone of their message, and the reason for
return. A rule-based system might miss important cues, while an agent can
reason through the situation like a support representative would.

The rules are too complex to maintain

Some systems grow so large and fragmented that updating them becomes a
liability. When your logic involves dozens of conditional branches, exception
cases, and special handling for edge conditions, agents offer a more
maintainable alternative.

An example of this can be a vendor security review process with evolving

compliance requirements and unstructured documentation. Instead of
encoding every possible case in logic, an agent can read and interpret the
documents as part of the workflow.

The workflow relies on unstructured or

natural language data
Agents are uniquely equipped to parse and reason over unstructured data
such as documents, emails, and conversations. If your pipeline needs to
extract meaning from natural language, an agent may significantly reduce
manual effort.

For example, consider an insurance claim intake process where customers

describe events in their own words. An agent can extract relevant entities, ask
follow-up questions, and route the case accordingly.

Before committing to building an agent, it’s crucial to validate that your use
case clearly meets these criteria. If a deterministic solution can suffice, it may
be a more appropriate approach.

Summary
AI agents are autonomous systems that perceive, reason, and act to achieve
goals. Unlike AI models, which are passive and task-specific, agents operate
over time, maintain context, and take initiative.
We explored three types of agents: software-based, physical, and hybrid. We
also examined how agent design has evolved from rule-based logic to LLM-
powered flexibility.

Agents are most useful when tasks involve complex decisions, dynamic
context, or unstructured data. Understanding when and why to build agents
sets the stage for designing them effectively.