PRACTICAL AI. ONE IDEA AT A TIME.
AI makes more sense when you work through it. Join Justin Thompson for clear explanations, short lessons, and exercises that turn new ideas into useful skills.
Independent teaching · Free audio · Ideas to practice with
Independent Exam Prep
LEARN → CHOOSE → BUILD
Explore free project ideas, choose a small exercise, and work toward a build of your own. Explore original GitHub project source alongside the ideas. Guided learning starters will follow as they are created.
Find a practice idea ↗THE FIRST SERIES
Learn the concepts. Make the connections. Practice building.
This first series works through Claude development foundations in short audio lessons. Justin connects the technical ideas to decisions you will make while building an application.
24 episodes are planned. The first 21 are published. Listen free on Spotify and Apple Podcasts using the links below. Choose an episode below or follow the series in your podcast app. Future beginner building tutorials will have their own place here as they are created.
Official exam guide PDF ↗
Version 1.0, effective July 2026. Check Anthropic’s latest guide before scheduling an exam.
START WITH THE FOUNDATIONS
Published episodes 01–21
Free on Spotify and Apple Podcasts.
Start with the ideas behind a model response: how text is represented, how responses vary, and what fits in context.
Try explaining the difference between a token and a word. Then consider what happens when a conversation outgrows its context window.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Understand how an application talks to an AI model, and where an SDK fits alongside a direct API request.
Sketch a request traveling from your application to an API and back. Label the request, response, SDK, and error handling.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Begin with the problem, define what success looks like, and follow an AI application from idea to maintenance.
Choose a small AI project. Write one user need, one measurable acceptance criterion, and one condition that requires human review.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Follow a structured Messages request through images, a read-only tool call, and a continuation that preserves the evidence.
Sketch a tool request and its matching result. Mark where the application validates inputs, checks access, and decides what action is allowed.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Separate streamed fragments from completed responses, compare interactive work with batches, and plan recovery across provider boundaries.
Describe a stream that stops before the final event. What can you display, what can you commit to history, and what must you check before retrying?
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Trace request contracts, JSON validation, and asynchronous work from an application request to a reviewed result.
Sketch two independent reads followed by a draft that depends on both. Identify which work may overlap and which steps must wait.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Follow a patch from edited files through staging, commits, merge conflicts and review. Distinguish a refactor from a deliberate behavior change.
A formatter extraction also changes who may read a repair record. Identify what must remain stable, what behavior changed, and which checks and approval the change needs.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Trace instruction sources across Claude chat, projects, Claude Code and API applications. Keep reference evidence separate from guidance and enforced permissions.
Move one assistant task between two Claude interfaces. Record which instructions and evidence actually loaded, then explain which controls enforce approval before an action.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Design schema contracts, keep repair-case sessions separate, and choose a maintainable plugin boundary. Includes three original retrieval questions.
Design a fictional assistant. Name one structural check, one evidence check, and one session boundary. Explain when its reusable procedure needs a standalone skill or a plugin.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Trace effective configuration across model identifiers, API and SDK versions, prompts, settings, and resolved dependencies. Includes three original decision questions.
A teammate says the prompt is unchanged, so the system is unchanged. Name three other configuration details you would inspect and one observed check that would support your conclusion.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Improve a failing prompt through observable requirements, correct placement, diverse examples, usable constraints, and separate evaluation cases. Includes three original questions.
Rewrite “summarize professionally” for a fictional workflow. Add a rule and example for missing information, a separate evaluation case, and one requirement enforced outside the prompt.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Preserve decisive evidence and valid state while using targeted retrieval, pruning, compaction, and isolated investigations. Includes three original questions.
Choose a long-running task. Explain what you would prune, what a summary must retain, and what you would delegate. Write a continuation question that would reveal a lost fact.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Follow an invented delivery record through completion, parsing, structural checks, evidence validation, and authorization. Practice three original decisions about missing fields, truncation, and permission checks.
Walk an invented delivery record through completion, parsing, structure, and evidence checks. Explain which failures need correction, a bounded retry, or human review.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Compare model configurations by acceptable-result quality, end-to-end latency, compatibility, and total cost. Use fictional token prices to calculate retries and cache reuse, then connect configuration, prompting, context, and output handling in a cumulative checkpoint.
Compare two fictional workloads. Define acceptable results, a latency measure, and a token budget. Explain when cache reuse would save money and what evidence would change your model choice.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Design a predictable packing workflow and an adaptive investigation for a fictional museum. Choose routing, parallel checks, single-agent investigation, or supervised delegation, and define concrete completion, limits, and human handoffs.
Sketch a predictable workflow and an evidence-dependent investigator. Identify who chooses each step, what can run independently, who reconciles findings, and two stopping conditions.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Trace a tool-use loop, distinguish active context, checkpoints, and long-term memory, and compare framework abstractions. Use original scenarios to reason about denied tools, scoped preferences, durable review pauses, and recovery evidence.
Design the smallest useful assistant for a fictional workshop. Distinguish active context, a checkpoint, and long-term memory, then name one framework capability you would verify.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Compare a custom Messages API loop, a process-operated Claude Agent SDK harness, and Claude Managed Agents. Follow Maple Room through execution ownership, conversation and working state, self-hosted tool sandboxes, hooks, and recovery after an uncertain write. Includes original retrieval questions and an ownership teach-back.
Compare a custom API worker, an Agent SDK worker, and a hosted harness with self-hosted tools. Name who runs the loop, executes tools, stores state, and verifies recovery, including which data travels.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Follow a proposed repair-note operation through schema design, registered dispatch, business validation, access checks, approval, execution, and matched results. Original questions cover forbidden but well-formed inputs, parallel lookup results, and recovery after a write timeout.
Trace a proposed repair note through dispatch, validation, access, approval, execution, and its matched result. Explain how you would handle an unauthorized record, refused approval, and lost acknowledgment.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
A compact MCP lesson: identify host, client, and server; distinguish resources, prompts, and tools; select compatible protocol and transport behavior; and test clear errors and denied access. Current2026-07-28 request semantics are explicitly separated from older initialization-based revisions.
Sketch an MCP host, client, and server for a fictional repair workflow. Distinguish a manual resource from a lookup tool, then identify the transport and compatible protocol revision.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Build Maple Room's handover workflow by matching existing operations, a custom repair integration, reusable Skill guidance, an MCP connection, and optional plugin packaging. Learn why these components can compose, how execution and permissions differ by surface, and which maintenance responsibilities each introduces.
Separate a workflow’s existing capabilities, missing business operation, and reusable procedure. Justify whether MCP or a plugin adds enough value, and name one component you would leave out.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
Choose Claude Code components, inspect loaded project guidance, resume sessions carefully, and distinguish output modes from permission and isolation controls.
Resume a fictional coding task with a missing tool connection and an interrupted ticket request. Name the evidence needed to continue, and distinguish conversation state, permissions, and isolation.
Original preview exercise. Episode notes and teaching coverage require review against the recordings.
The rest of the path is ahead. 3 more episodes are planned. Get new episode updates with the study companion.
Keep me in the loop ↗Follow the series on Spotify ↗ or Apple Podcasts ↗ for the next release.
Apple and Apple Podcasts are trademarks of Apple Inc., registered in the U.S. and other countries.
LISTEN. THEN PUT IT TO WORK.
Get the free Claude Certified Developer – Foundations study companion, plus new episode updates.
First edition scope: episodes 1–3, with a full 25-skill checklist distinguishing covered and future topics. The first-edition checklist remains a snapshot of episodes 1–3. A separate listening companion for episodes 4–6 has also been prepared, with notes, original questions and proposed offline exercises. Both companions are free. Verify your email through the training signup to open the written notes. No real exam questions or copied gated-course material.
Your next step, after you listen.
Choose the training list for the free companions and new episode updates. Verify your email before companion access opens.
Get the free companions ↗Two separate signups. Choose either or both. Each requires its own consent. The Age of Imagineering essay newsletter stays separate.
YOUR GUIDE
Microsoft Certified AI Engineer · U.S. Marine veteran
I believe understanding grows when you have something to try.
AI with JT is my practical teaching space. I break ideas into manageable pieces, explain how they connect, and give you a next step you can work through yourself.
Start with the Claude foundations series. As this library grows, you will find beginner building tutorials here too.
A personal education project. Views are my own; not consulting, employer-affiliated, or an offer of professional services.
Connect on LinkedIn ↗A DIFFERENT KIND OF QUESTION
For essays about technological possibility, human potential, and what we choose to do with AI, visit my separate publication.
Explore Age of Imagineering ↗A separate essay brand and newsletter. Subscribing to AI with JT training will not subscribe you to its essays.
