← Tech Station
05 — Advanced

Agentic AI

Planning loops, tool use, memory, and multi-agent coordination.

14 guides in this track·1.7h reading·Advanced
What you'll learn

Build agents that plan, use tools, remember, and coordinate — with clear eyes about where they fail and how to keep them under control.

Who this is for

Engineers past RAG and prompt-chaining who need models to do multi-step work, and leaders sizing up what agents can realistically ship today.

How to use it

The guides are numbered — read in order for the curriculum path, or jump straight to the one you need. Each card is self-contained.

The guides

Ordered by recommended reading path
01
What Is Agentic AI?

What actually makes an agent an agent, five defining capabilities, and why 2026 is when the pattern lands.

9 minRead →
02
Agents vs Workflows vs Chatbots: Choosing the Right Level of Autonomy

Chatbots, workflows, and agents each solve different classes of problem. How to honestly choose.

8 minRead →
03
Inside the Agent Loop

Think to act to observe, and ReAct.

6 minRead →
04
Tool Use & Function Calling

How agents act on the world.

8 minRead →
05
Memory in AI Agents

Short- and long-term memory design.

8 minRead →
06
Planning & Reasoning in Agents

Decomposition and re-planning.

9 minRead →
07
Agent Design Patterns

Reflection, planning, tool use, collaboration.

9 minRead →
08
Building Your First Agent

A working agent from scratch, no framework.

6 minRead →
09
Multi-Agent Systems

When many agents beat one, and when they do not.

6 minRead →
10
Agentic RAG

Reasoning-driven retrieval inside agents.

5 minRead →
11
Model Context Protocol (MCP)

Standardised ways to connect agents to systems.

6 minRead →
12
Choosing an Agent Framework

Comparing the main build options and trade-offs.

7 minRead →
13
Evaluating & Observing Agents in Production

Measuring trajectories, not just outcomes.

6 minRead →
14
Securing AI Agents

The new attack surface and layered defence.

7 minRead →

Related tracks

Continue in the same group
01 — Start hereAI PrimerThe concepts every LLM practitioner needs before writing a single prompt.02 — Core skillPrompt EngineeringZero-shot to few-shot, chain-of-thought, and structured output patterns.03 — ArchitectureRAGChunking, embeddings, vector search, and fixing hallucinations in production.04 — LLMOpsLLM Fine-Tuning & LLMOpsWhen to fine-tune vs. prompt, LoRA, QLoRA, evaluation, and deployment.