AI & AI-Assisted Development

About this course

Who this course is for

What you'll learn

• Explain what modern generative AI and large language models can and cannot do.
• Use AI tools to support software planning, requirements, documentation, and development tasks.
• Write clearer prompts for software-related work and evaluate AI-generated output critically.
• Use AI to assist with coding, debugging, testing, and refactoring while maintaining human oversight.
• Understand how AI features can be added to applications through APIs and connected services.
• Identify common risks involving privacy, security, hallucinations, bias, and unreliable output.
• Design a practical AI-assisted development workflow that balances speed, quality, and accountability.

Course details

Level

beginner

Estimated duration

12 lessons · about 2.5 hours

What's included

• 12 lessons
• Progress tracking

Requirements

• No prior AI or programming experience required.
• Basic computer and internet skills recommended.
• Familiarity with the idea of apps/software is helpful but not required.

Curriculum

1. 01

   Lesson 1: What AI Is and How Modern Models Work

   A clear, non-mathematical introduction to artificial intelligence, machine learning, generative AI, and large language models. You will learn how models are trained and used, what tokens and context are, and why AI output can vary.

   12m
2. 02

   Lesson 2: Generative AI, Large Language Models, and Software Work

   Explore the core tasks generative AI performs and the main ways developers access it — copilots, chat interfaces, and APIs. You will see common software-development uses, why context quality matters, what structured outputs are, and when traditional logic is the better tool.

   12m
3. 03

   Lesson 3: Strengths, Limits, Risks, and Human Oversight

   Get a balanced view of what AI does well and where it fails. This lesson covers hallucinations, outdated knowledge, bias, inconsistency, privacy and security concerns, and code-quality risks, and gives you a practical checklist for reviewing AI output.

   12m
4. 04

   Lesson 4: Prompting for Software and App Development

   Learn to write prompts that produce useful, reviewable results for software work. This lesson covers prompt structure, supplying requirements and examples, asking for assumptions, iterating, breaking down complex tasks, and adapting prompts for planning, coding, and review.

   12m
5. 05

   Lesson 5: Planning, Writing, and Refactoring with AI

   See how AI can support the early and middle stages of development: turning ideas into requirements, drafting user stories and data models, brainstorming architecture, generating starter code, refactoring, and explaining unfamiliar code — while people keep ownership of design decisions.

   12m
6. 06

   Lesson 6: Reviewing, Testing, and Debugging AI-Generated Work

   Learn how to check AI-generated code before it reaches users. This lesson covers logic and security problems, missing edge cases, using AI to help create tests, disciplined debugging with logs and reproduction, finding root causes, and verifying fixes.

   12m
7. 07

   Lesson 7: Common AI Features in Modern Applications

   Survey the AI features users now encounter in apps — chat assistants, question answering, summarization, classification, extraction, recommendations, content generation, document analysis, and AI-assisted workflows — and learn how to choose the right feature, or decide rules are better.

   12m
8. 08

   Lesson 8: Connecting Applications to AI Services and APIs

   Understand how an application sends requests to an AI service and safely uses the responses. This lesson covers API keys, prompts sent from your app, structured responses, latency, rate limits, costs, timeouts and retries, logging, provider abstraction, and privacy.

   12m
9. 09

   Lesson 9: Designing Reliable AI User Experiences

   Learn to design AI features users can understand, trust appropriately, and correct. This lesson covers setting expectations, communicating uncertainty, human confirmation, editing before action, feedback, loading and error states, honest interfaces, guardrails, fallbacks, citations, and designing for failure.

   12m
10. 10

    Lesson 10: Data, Privacy, Security, and Governance

    Learn the practical safeguards that responsible AI use requires. This lesson covers sensitive data, data minimization, secrets, access control, prompt injection, data leakage, provider considerations, retention and logging, human review, governance policies, and a risk-based approach to compliance awareness.

    12m
11. 11

    Lesson 11: AI for Productivity, Documentation, and Development Operations

    Discover how AI can reduce routine effort across a development team — documentation, code explanations, release notes, issue summaries, test planning, backlog work, meeting notes, research, checklists, and incident summaries — while keeping proprietary data safe and building repeatable workflows.

    12m
12. 12

    Lesson 12: Planning an AI-Assisted Product from Idea to Improvement

    Bring the course together by planning an AI-enabled product end to end: identifying a real problem, deciding where AI adds value, choosing between AI and deterministic logic, planning integrations and risks, prototyping, testing, monitoring, and improving over time. The lesson closes with a full course recap.

    12m