What is AI

Many real-world problems are too complex for hand-coded rules: understanding language, recognizing images, making recommendations. AI automates these cognitive tasks at scale, powering everything from search engines to coding assistants.

AI is like teaching a very fast intern — instead of programming every rule, you show examples and the system learns patterns. The intern gets better with more training data and feedback.

Visual Workflows

Start here — study each diagram, then use + / − to zoom if needed.

100%

Loading diagram...

Scroll inside the frame · use + / − to zoom

Key Takeaways

1.Artificial Intelligence (AI) is the field of building systems that perform tasks requiring human-like intelligence — perception, reasoning, language understanding, and decision-making.
2.AI spans multiple paradigms: rule-based systems (expert systems), machine learning (learn from data), deep learning (neural networks), and generative AI (create new content).
3.Modern AI engineering focuses on applying pre-trained models via APIs, building RAG pipelines, and orchestrating agents.
4.You don't need to train foundation models — you integrate, prompt, retrieve, and evaluate them in production systems.

Real Example

Scenario

A customer support bot receives 'Where is my order #12345?', retrieves order status from a database via a tool, and generates a natural language response using an LLM.

What you would do

In Generative AI Foundations, apply What is AI to this scenario: A customer support bot receives 'Where is my order #12345?', retrieves order status from a database via a tool, and generates a natural language response using an LLM. Identify the inputs, run the technique, validate the output, and note one thing you would monitor in production.

Practice Task

Open the Code Walkthrough below and run it locally. Change one parameter related to What is AI (e.g. model, temperature, top_k, or tool name), observe the difference in output, and write 2–3 sentences explaining what changed.

Code Walkthrough

Highlighted lines show where What is AI happens in the code.

What is AI

1# Minimal AI application pattern2from openai import OpenAI  # import dependencies3
4client = OpenAI()  # create API client5
6def handle_user_query(query: str) -> str:  # define a reusable function7    response = client.chat.completions.create(  # core API call for What is AI8        model="gpt-4o-mini",9        messages=[  # key line for What is AI10            {"role": "system", "content": "You are a helpful assistant."},11            {"role": "user", "content": query},12        ],13    )14    return response.choices[0].message.content  # return the result

Cheat Sheet

Quick recap

quick ref

•AI > ML > DL > GenAI
•Engineers integrate, researchers train
•LLM API = OpenAI/Anthropic
•RAG = retrieval + generation
•Agents = LLM + tools
•Eval = measure quality

Common Mistakes

✕Thinking you need to train models from scratch for most applications
✕Confusing AI hype with practical engineering requirements
✕Ignoring cost and latency when designing AI features
✕Building without evaluation — no way to measure if it works