AI Agents with Model Context Protocol & Typescript

ChatGPT and other large language models are going to be more important in your life and business than your smartphone, if you use them right. ChatGPT can tutor your child in math, generate a meal plan and recipes, write software applications for your business, help you improve your personal cybersecurity, and that is just in the first hour that you use it. This course will teach you how to be an expert user of these generative AI tools. The course will show amazing examples of how you can tap into these generative AI tools' emergent intelligence and reasoning, how you can use them to be more productive day to day, and give you insight into how they work. Large language models respond to instructions and questions posed by users in natural language statements, known as “prompts”. Although large language models will disrupt many fields, most users lack the skills to write effective prompts. Expert users, who understand how to write good prompts, are orders of magnitude more productive and can unlock significantly more creative uses for these tools. This course introduces students to the patterns and approaches for writing effective prompts for large language models. Anyone can take the course and the only required knowledge is basic computer usage skills, such as using a browser and accessing ChatGPT. Students will start with basic prompts and build towards writing sophisticated prompts to solve problems in any domain. By the end of the course, students will have strong prompt engineering skills and be capable of using large language models for a wide range of tasks in their job, business, personal life, and education, such as writing, summarization, game play, planning, simulation, and programming.

We see lots of news reports of Generative AI tools, such as ChatGPT, making mistakes and producing inaccurate information. Many of these mistakes happen because humans use the tools in the wrong way - trying to solve unsuitable problems and not thinking about risk. Hallucination isn't a bug, it's a feature when you approach problems correctly. This course teaches techniques for determining if a problem fits Generative AI's capabilities, framing problems to reduce risk, prompt engineering for trust, and appropriate human engagement in the process. Students learn concrete prompt designs, how to check outputs, how to use Generative AI for ideation and creation, ways to augment human skills, and more ethical, beneficial applications. The course will show how you can: - Leverage prompt engineering techniques to generate more reliable outputs - Master methods to verify and validate outputs - Frame problems in alternative ways to reduce risk - Apply generative AI for creative ideation - Use Generative AI in ways that augment rather than replace human reasoning and creativity

Master AI-Assisted Development with Claude Code: From Fear to 1000X Productivity Transform your software engineering practice by learning to work effectively with AI as your development partner. This comprehensive course takes you from initial skepticism about AI coding tools to confidently leveraging Claude Code for dramatic productivity gains. In just the first few lessons, you'll learn to have Claude Code build entire applications in minutes - complete with user interfaces, databases, and business logic. By the end of this course, you'll know how to orchestrate Claude Code working concurrently across multiple git branches, with parallel AI agents developing different features simultaneously and automatically integrating their work. This isn't about getting better autocomplete - it's about fundamentally changing how software gets built. You'll discover how to treat AI as scalable development labor, implement the "Best of N" pattern to generate multiple solution approaches, and establish robust quality assurance processes that ensure AI-generated code meets professional standards. The course covers essential skills like writing effective CLAUDE.md files for project context, creating reusable commands for common workflows, and managing parallel development streams with git worktrees and AI subagents. Through hands-on exercises and real-world examples, you'll learn to overcome the common fears engineers have about AI tools while building practical systems for code evaluation, documentation generation, and feature development. By the end, you'll have a complete toolkit for scaling your development capabilities and a personalized process that fits your workflow. What You'll Learn: - Break free from micromanaging Claude Code and start delegating like a tech lead managing a team of senior developers - Write "big prompts" that get Claude Code building entire features instead of generating single functions you copy-paste - Use the "Best of N" pattern with Claude Code to generate 3-5 versions of every feature and cherry-pick the best parts or versions - Teach Claude Code to critique its own code using contextual rubrics that catch bugs before you ever see them - Master CLAUDE.md files that turn onboarding into autopilot - give Claude Code perfect project context so it writes code that fits your architecture from day one - Build Claude Code command libraries that compress complex development workflows into single prompts (code reviews, feature builds, testing suites) - Train Claude Code through examples so it writes code that matches your team's style without 100-page style guides - Orchestrate parallel feature development with Claude Code working multiple git branches simultaneously while you focus on architecture - Design codebases that scale with AI labor - understand token limits and architect projects for maximum Claude Code efficiency - Deploy Claude Code subagents that work independently on different features in parallel and then have Claude Code perform the merging and integration when they are done - Build your personal AI-first development process that multiplies your output while maintaining code quality - Use multimodal prompting to turn cocktail napkin sketches and whiteboard sessions into complete UI components, architectures, and processes in minutes Real Impact for Developers: - Cut feature development time from days to minutes - Never write boilerplate code again - Get comprehensive test suites written automatically - Have Claude Code handle code reviews and refactoring - Build multiple prototypes before committing to an approach - Scale your personal productivity like you hired a team Who This Is For: Software engineers, tech leads, and development teams ready to embrace AI-assisted coding while maintaining code quality and engineering best practices. Prerequisites: Basic software development experience and familiarity with version control (Git). This course requires a paid subscription that includes Claude Code.