RAG & AGENTS
AI Agents
Understand how AI agents combine language models with tools, memory, reasoning and feedback to complete multi-step tasks.
AI Agents Learning Path
Follow the modules in order, from the evolution of agentic systems through architecture, safety, evaluation and operations.
The Story Before AI Agents
The real evolution from traditional software through automation, workflows, and LLM applications to AI Agents — and why each step, one at a time, became insufficient for what came next.
What Is an AI Agent?
The precise definition Module 1's evolution story built toward — why an Agent is a real SYSTEM, not just a model, and sharp distinctions from an LLM, a chatbot, an LLM application, automation, and a workflow.
The Agent Mental Model
Mapping Module 2's precise definition onto a complete set of concepts — goal, environment, state, observation, action, decision, tool, context, feedback — anchored by a human-employee analogy used throughout this course.
The Agent Loop Deep Dive
The mechanics of how the reason-act-observe loop actually runs — why it's necessary, how it terminates, and what happens when a decision is wrong, a tool fails, or the agent gets stuck.
The LLM as the Agent's Brain
Closing Level 2: precisely what role the LLM plays within the agent loop, and why — despite being central — the LLM alone is never the entire agent.
Tools and Actions
The complete mechanics of what a tool actually is, how an agent selects and executes one, and everything that can go wrong — schema, validation, errors, permissions — starting Level 3.
Function Calling Deep Dive
Closing Level 3: the precise mechanics of how an LLM's structured decision becomes an executable function call — and the critical clarification that the LLM never literally executes anything itself.
Reasoning and Planning
Level 4 begins here: why agents sometimes need to plan ahead across multiple steps before acting — task decomposition, dependencies, and static vs. dynamic planning, using a complex trip-planning example.
ReAct: Reasoning + Acting
A historically influential agent pattern that interleaves a generated action rationale, an action, and an observation — making the recorded decision trace visible without claiming to reveal hidden model reasoning.
Reflection and Self-Correction
Closing Level 4: how an agent can evaluate its own output and revise it before finishing — the generate-evaluate-revise-retry loop, and the real risks of relying on self-evaluation.
Agent Memory
Level 5 begins here: why memory is needed, and the critical distinction between state, context, conversation history, and memory — four different concepts this course keeps carefully separate.
Agent State
Closing Level 5: state transitions, persistence, and precisely how an agent's understanding evolves through a multi-step execution — building directly on Module 11's memory/state distinction.
Single-Agent Architectures
Level 6 begins here: assembling everything from Modules 1-12 into complete, recognizable architectural patterns, each suited to different real task requirements.
Agentic RAG
Connecting directly to the RAG course: how a real agent decides whether retrieval is needed at all, evaluates retrieval quality, and searches again when the first attempt falls short.
Multi-Agent Systems
Closing Level 6: when a single agent isn't enough, and the architectural patterns — sequential, parallel, supervisor, hierarchical, and more — for coordinating multiple specialized agents together.
Human-in-the-Loop
Level 7 begins here: why humans may need to remain in control for high-risk actions, and how approval, confirmation, and escalation fit structurally into an agent's loop.
Guardrails
Input, output, and tool guardrails that constrain what an agent is allowed to do — extending Module 16's control principle from just high-risk actions to every layer of the agent's operation.
Agent Security
real security risks — prompt injection, tool misuse, excessive permissions, memory poisoning, agent hijacking — and concrete defense strategies for each, using realistic enterprise scenarios.
Agent Failure Modes
Closing Level 7: a complete, systematic taxonomy of what can go wrong across an agent's entire operation, beyond just security — hallucination, wrong tools, infinite loops, cost explosion, and more.
Agent Evaluation
Level 8 begins here: why evaluating an agent is harder than evaluating a single LLM response, and the multiple, distinct dimensions — completion, tool accuracy, planning quality, cost, safety — that actually matter.
Observability
Why ordinary application logging isn't enough for agents, and what a real agent trace needs to capture — logging, metrics, tracing, trajectories, and tool calls — to make diagnosis actually possible in production.
Agent Frameworks
LangChain and LangGraph, introduced only now — after understanding the manual orchestration problems they exist to solve — mapping every framework concept back to something you've already built from scratch.
MCP and Agents
The standardization problem for tool integration specifically, and how MCP addresses it — directly extending Module 6-7's tool-calling foundation to work consistently across many external capabilities.
Production Agent Architecture
Closing Level 8: the complete, consolidated system diagram bringing together every concept from this entire course — orchestration, tools, memory, guardrails, human approval, observability — into one production-grade design.
Real-World Agent Applications
Level 9 begins here: how the complete architecture from Module 24 applies across different real-world domains — customer support, research, coding, DevOps, and more.
Agent System Design
Worked design exercises applying everything from this course to complete, from-scratch system designs — customer support, research, enterprise RAG, coding, and multi-agent systems.
Common Misconceptions
A dedicated, corrected list of common misunderstandings about AI Agents, consolidating warnings raised throughout this entire course into one focused, final reference.
Interview Masterclass & Final Learning Journey
The final module of this course: comprehensive interview preparation across every topic, a capstone agent combining the entire course, and the complete learning journey from NLP through AI Agents.
WHY AI AGENTS?
Move from answering questions to completing tasks
Agents use a model to decide what to do next, call tools to act on the world and maintain state across a task. Learning the underlying loop helps you design systems that are capable, observable and safe to operate.