Introduction to AI

Introduction

Artificial Intelligence (AI) is the field of building software that performs tasks normally requiring human intelligence — understanding language, recognising images, making decisions. Modern AI learns patterns from huge datasets instead of being hand-coded with rules.

Beginner analogy: traditional software is a strict recipe; AI is teaching a child by example — show enough cats and dogs and the child generalises. Agentic AI takes this one step further: the AI doesn't only recognise, it acts in the world.

Understanding the topic

Core concepts:

• AI = software that learns from data instead of hard-coded rules.
• Narrow AI: great at one task (translation, image recognition, chat).
• General AI: human-level reasoning across any domain (still future).
• Generative AI: a subset of deep learning that creates new content.
• Agentic AI: generative AI + planning + tools + autonomy.

Syntax reference

Visual workflow / architecture:

┌──────────────────┐
│   Artificial     │
│   Intelligence   │
└────────┬─────────┘
         ▼
┌──────────────────┐
│ Machine Learning │
└────────┬─────────┘
         ▼
┌──────────────────┐
│  Deep Learning   │
└────────┬─────────┘
         ▼
┌──────────────────┐
│  Generative AI   │  ← LLMs
└────────┬─────────┘
         ▼
┌──────────────────┐
│   Agentic AI     │  ← LLMs that act
└──────────────────┘

Real-world use

AI runs Google Search ranking, Netflix recommendations, Tesla Autopilot, Gmail spam filters, Apple Face ID and now ChatGPT-style assistants embedded in nearly every SaaS product.

Best practices

• Pick the simplest model that solves the problem — don't reach for an LLM if regex works.
• Always measure: accuracy, latency, cost, hallucination rate.
• Treat AI output as a suggestion in regulated domains.

Common mistakes

• Assuming AI is magic — it's statistics on huge datasets.
• Confusing AI hype with capability.

Hands-on exercise

Interview preparation — practice these questions:

• Q1. Define AI in one sentence.
• Q2. Difference between narrow and general AI?
• Q3. Where does Agentic AI sit in the AI hierarchy?
• Q4. Why is Agentic AI different from Generative AI?