Prompting Fundamentals
Practice task contracts, relevant context, examples, structured output and targeted revision. Compare complete authored outputs against source references and whole-task effort; no paid AI account is required.
For anyone new to Copilot Chat, ChatGPT, Claude or Gemini at work: get usable drafts on the first or second try, and know which answers to check before they leave your desk.
Most disappointing AI answers are not the tool's fault: the assistant filled in what the prompt left out. This course shows you exactly how that happens, and what to do about it, through one case told in three acts. Harborline Residential Management (a fictional composite) manages 2,950 Milwaukee apartments. Its shared inbox is 412 messages behind, its largest client's contract review is weeks away, and the only approved AI tool is Copilot Chat. You follow coordinator Dana Reyes as she triages the emergencies first, as her one-line prompts promise 24-hour visits that Harborline's own heating standard does not allow, as she rebuilds them into four-part briefs with the policy pasted in, as a colleague's 900-word mega-prompt and week-long chat thread go wrong, and as she catches a move-out template that misstates Wisconsin's deposit deadline the evening before a 63-letter mail merge, the same evening she learns that a rental application went into a personal ChatGPT account.
Each lesson shows the real prompt, the output, a line-by-line critique, a failure and its fix, and a short exercise with a model answer. Three five-minute Decision Labs put you in Dana's chair with a dashboard of consequences: backlog, wrong promises, legal exposure, owner confidence and data exposure. You finish the course by building a one-page prompt kit for your own job, scored against a rubric with a worked strong and weak example, and you leave with a two-minute check-and-data routine you can use on Monday. It follows the prompting guidance OpenAI, Anthropic and Google publish and Microsoft's Copilot Chat privacy documentation as of October 2026, and it works in any mainstream assistant. The course does not claim any tool is approved for patient, financial or other regulated data; it teaches you how to find out.
3 modules · 7 lessons · about 1 hours
The exam unlocks once you have completed every lesson and played each Decision Lab to an ending. It draws 10 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 20 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.
Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.
The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by OpenAI, Anthropic, Google, or Microsoft. Product and company names are trademarks of their respective owners.
Practice task contracts, relevant context, examples, structured output and targeted revision. Compare complete authored outputs against source references and whole-task effort; no paid AI account is required.
Go beyond chat tricks: learn how production prompts are structured, how to decide what goes into the context window, how to get schema-valid JSON, and how to test, version and protect prompts. Every technique comes with before-and-after examples and is checked against the official OpenAI, Anthropic and Google prompting guidance as of October 2026.
Design schemas models can fill reliably, use the native structured-output features of the OpenAI, Anthropic and Gemini APIs, extract fields from PDFs, scans and email, and measure field-level accuracy with gold sets. Parameter names and features are checked against vendor documentation as of October 2026.