AIYING | PRACTICAL AI LEARNING
Learn as You Do
One Doing. One Learning. Cumulative Accomplishment.
A progressive learning series covering AI concepts, tools, technologies, and practical applications—one useful accomplishment at a time.
What If Learning AI Began with Doing?
Imagine learning artificial intelligence without beginning with a long course, a textbook, or a complicated technical explanation.
Instead, you begin by doing something useful.
You ask AI to improve a message. It works.
You discover that the instruction you provided is called a prompt.
You then improve the prompt by adding information about the audience, purpose, and desired result.
You discover another concept: context.
Next, you combine both concepts to create a reusable workflow.
Before long, you are not merely learning about AI. You are developing the ability to use AI to accomplish increasingly meaningful tasks.
That is the idea behind Learn as You Do.
The Central Proposition
Don't wait to finish learning AI before using it.
Start doing something useful. Discover the concept behind it. Apply that learning to accomplish something more.
One Doing → One Learning → One New Capability → Cumulative Accomplishment.
Why Another AI Learning Series?
There is already an enormous amount of AI learning content available.
Courses explain concepts. Tutorials demonstrate tools. Videos introduce technologies. Documentation describes features.
All of these have value.
But learners often face a different challenge:
How do I turn what I have learned into something I can actually do?
Many learners understand terms such as prompts, tokens, embeddings, RAG, agents, and APIs without having built anything meaningful using them.
Others use AI tools every day without understanding the concepts that would help them use those tools more effectively.
Learn as You Do connects practical accomplishment with conceptual understanding.
The objective is not to accumulate terminology. It is to accumulate capability.
The Learning Model
DO #001
Complete one small, useful task.
↓
LEARN #001
Discover one underlying AI concept.
↓
DO #002
Use the previous learning and add a new capability.
↓
LEARN #002
Understand the next concept through experience.
↓
DO MORE → LEARN MORE → ACCOMPLISH MORE
Every episode builds on earlier accomplishments.
The learner does not repeatedly start from zero. Each new concept becomes part of a growing practical toolkit.
From Literacy to Operacy
Edward de Bono introduced the concept of operacy to emphasise the importance of thinking as a practical operating skill—the ability to make things happen.
Literacy concerns reading and writing. Numeracy concerns working with numbers. Operacy concerns effective action.
This provides a useful foundation for rethinking AI education.
AI literacy helps people understand artificial intelligence.
AI operacy helps people use artificial intelligence to accomplish things.
Learn as You Do applies this distinction to modern AI learning.
The aim is to develop people who can recognise opportunities, choose suitable tools, construct useful workflows, evaluate results, and turn possibilities into accomplishments.
AI operacy is the proposed educational extension used in this series, not a term attributed to de Bono himself.
How Every Episode Works
Each episode is designed as a short practical learning experience, typically requiring 10–20 minutes.
| Stage | What Happens |
|---|---|
| 1. DO | Complete one useful AI task. |
| 2. SEE | Observe and inspect the result. |
| 3. LEARN | Understand one underlying concept. |
| 4. EXTEND | Connect the new learning to previous skills. |
| 5. APPLY | Use the capability in a practical situation. |
| 6. ACCOMPLISH | Save a tangible result and identify the next step. |
Every episode introduces one primary new concept, demonstrates its practical use, and produces an output the learner can retain.
The First 30 Learning Experiences
The initial pathway moves from everyday AI use to increasingly sophisticated AI applications.
Phase 1: Start Using AI
- Improve a rough message — Prompts
- Adapt a message for an audience — Context
- Generate alternative versions — Output variation
- Specify an exact output structure — Structured outputs
- Create reusable instructions — Prompt templates
Phase 2: Work with Information
- Summarise a long document — Context windows
- Ask questions about a document — Grounding
- Check an AI-generated answer — Hallucinations
- Create a source-backed briefing — Retrieval
- Organise reference material — Knowledge bases
Phase 3: Build Knowledge-Based AI
- Find related information — Embeddings
- Build a document assistant — RAG
- Compare AI-generated answers — Model evaluation
- Build a quality checklist — Evaluation rubrics
- Create a reusable AI assistant — Custom assistants
Phase 4: Explore Multimodal AI
- Create an infographic — Image generation
- Extract information from an image — Multimodal AI
- Transcribe a recording — Speech-to-text
- Generate narration — Text-to-speech
- Produce an educational video — Multimodal workflows
Phase 5: Build AI Workflows
- Automate a repeated task — Workflow automation
- Connect applications — APIs
- Enable an assistant to use tools — Tool calling
- Connect external capabilities — MCP
- Build a multi-step assistant — AI agents
Phase 6: Make AI Reliable
- Review and approve AI actions — Human-in-the-loop
- Monitor AI behaviour — Observability
- Test difficult scenarios — Evals
- Protect sensitive information — AI security
- Publish a tested assistant — Deployment
This is only the beginning. Future learning pathways will extend into machine learning, neural networks, transformers, fine-tuning, vector databases, agent orchestration, AI engineering, responsible AI, governance, and emerging technologies.
The Power of Cumulative Learning
Consider how a learner might gradually build a personal AI work assistant.
- Episode 001: Write a professional message.
- Episode 002: Adapt the message for different audiences.
- Episode 005: Save reusable instructions.
- Episode 007: Use reference documents to improve accuracy.
- Episode 014: Add quality checks.
- Episode 015: Turn the workflow into an assistant.
- Episode 025: Extend it into a multi-step AI agent.
What began as a simple writing task gradually becomes a useful AI application.
That is the difference between collecting lessons and building capability.
Every tenth episode will also introduce a Milestone Challenge, inviting learners to combine earlier skills into an independent accomplishment.
Let's Try Episode #001
DO: Turn a Rough Thought into a Professional Message
Open an AI assistant such as ChatGPT and enter this prompt:
Task: Rewrite the following rough message into a clear, professional message.
Audience: College principal
Purpose: Invite consideration of an AI course
Tone: Respectful and concise
Length: Under 100 words
Rough message: "We have AI course. Students can learn new AI things. Please consider for your college."
Provide the improved version and explain three changes you made.
SEE: Examine the Result
Observe how AI improves the language, organisation, tone, and clarity.
Does the message communicate the intended purpose? Has the AI introduced any claims that were not supplied? Would you actually send it?
LEARN: What Is a Prompt?
A prompt is the input or instruction provided to an AI model to guide its response.
A useful prompt may specify the task, audience, relevant context, constraints, and desired output.
Prompting is not simply asking a question. It is a practical way of directing AI toward a particular result.
EXTEND: Change the Audience
Repeat the exercise, but change the audience from a college principal to a prospective student.
Compare the two outputs. What changed? Why?
ACCOMPLISH: Save Your Work
Save both messages and the reusable prompt in a personal learning portfolio.
You have now completed your first AI task and learned your first AI concept.
Next episode: Why does the same AI produce different responses for different audiences? Discover the role of context.
Who Is This Series For?
Students: Develop practical AI skills through small, achievable tasks.
Freshers and job seekers: Build a portfolio demonstrating real AI capabilities.
Working professionals: Discover ways to improve everyday work.
Educators: Use short practical activities to introduce AI concepts in classrooms.
Developers and engineers: Progress from everyday AI usage to building and evaluating AI systems.
Institutions and learning communities: Adopt individual episodes as microlearning exercises, workshops, or team-learning activities.
No programming experience is required to begin. More technical episodes will introduce additional prerequisites when needed.
A Living Learning Series
Artificial intelligence is changing rapidly. New tools, models, capabilities, architectures, and practices continue to emerge.
A fixed curriculum can become outdated.
Learn as You Do is therefore designed as a living learning series.
New episodes will introduce relevant concepts and tools through practical tasks. Existing lessons can be updated as technologies evolve.
The series will remain guided by one principle:
Every learning experience must lead to something the learner can actually do.
The Learn as You Do Challenge
Start with one small task today.
Use AI to accomplish it.
Identify one concept that explains how it worked.
Save the result.
Tomorrow, use what you learned to do something more.
Thirty episodes. Thirty practical experiences. A growing portfolio of AI accomplishments.
Not thirty disconnected tutorials, but thirty connected steps toward greater AI capability.
