Prepare source-checked prompts, diagnose output errors and maintain reusable workflows using complete supplied cases.
Level
Basic
Study time
10 hours
Lessons
18 in 6 modules
Exam
20 questions
About this course
Use a fictional Columbus supply cooperative to build and inspect internal quote drafts. Work from actual supplied catalog rows, requests and fallible outputs, preserving product identity, units, versions and genuinely missing inputs. Compare manual and generative workflow specifications without treating a fluent answer or valid JSON as evidence of correctness.
Across eighteen lessons, maintain six cumulative records covering task definition, context, examples and format, revision, matched comparison and reusable templates. Complete six module Decision Labs and a capstone about feasible preparation scope. Vendor guidance is attributed and bounded; the core work uses supplied text, calculations and authored outputs rather than a commercial account. The certificate uses lesson completion, Decision Labs and the automated exam; optional written practice provides formative feedback.
What you will be able to do
Write a task contract with audience, artifact, deciding inputs, constraints and observable acceptance checks
Select and delimit relevant context while preserving identity, units, source versions and instruction/data boundaries
Design representative examples and inspect structured outputs against an explicit local schema
Revise a specific failed output through targeted feedback and staged work while retaining supported fields
Interpret supplied documents, tables and image-description records without assuming unavailable source access
Compare matched candidate outputs for content, format, appropriate clarification and whole-task effort
Maintain reusable templates with placeholders, source versions, tool assumptions and refresh checks
Choose a feasible preparation strategy and revise it using actual supplied feedback and resource limits
Syllabus
6 modules · 18 lessons · about 10 hours
1
Module 1: Define the Task
Specify the requested artifact and check its observable fields.3 lessons
Specify the Artifact from the Request
Separate Goals, Audience and Constraints
Build Observable Acceptance Checks
Decision Lab · 11 minSpecify the unit before finishing the quoteUse the supplied Riverton records to choose actual preparation scope, then revise it when a deciding dependency changes.
2
Module 2: Choose the Deciding Context
Preserve source identity, units and versions.3 lessons
Supply the Actual Deciding Sources
Separate Task Instructions from Source Data
Reconcile Identity, Units and Source Version
Decision Lab · 11 minJoin the changed row to the right sourceUse the supplied Riverton records to choose actual preparation scope, then revise it when a deciding dependency changes.
3
Module 3: Show Examples and Specify Format
Teach the intended pattern without copying obsolete facts.3 lessons
Choose Representative Examples
Specify and Inspect Structured Output
Prevent Example Leakage and Stale Facts
Decision Lab · 11 minKeep the example shape without its old priceUse the supplied Riverton records to choose actual preparation scope, then revise it when a deciding dependency changes.
4
Module 4: Revise the Workflow
Repair a concrete defect and check its dependencies.3 lessons
Give Targeted Feedback
Extract, Calculate, Draft and Check
Transfer Context to a Fresh Conversation
Decision Lab · 11 minCarry correct fields into a different source contextUse the supplied Riverton records to choose actual preparation scope, then revise it when a deciding dependency changes.
5
Module 5: Evaluate the Result
Compare the same cases and the complete work boundary.3 lessons
Freeze a Matched Reference Set
Separate Correctness, Format and Clarification
Compare Whole-Task Effort
Decision Lab · 11 minKeep an exposed correction out of the unseen columnUse the supplied Riverton records to choose actual preparation scope, then revise it when a deciding dependency changes.
6
Module 6: Maintain and Decide
Build reusable templates and choose feasible scope.3 lessons
Write Reusable Placeholders
Refresh Sources and Templates
Choose a Feasible Prompt Workflow
Decision Lab · 11 minRefresh the fields and the preparation boundaryUse the supplied Riverton records to choose actual preparation scope, then revise it when a deciding dependency changes.
Capstone simulation · 25 minDefend the actual preparation portfolio after R2Choose and revise a six-record preparation plan when the received source and aggregate staffing allowance both change.
Exam and certificate
The exam unlocks once you have completed every lesson and played each Decision Lab to an ending. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 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.
A free one-hour course built around one realistic case: a resident services coordinator clearing a 412-message backlog with her company's approved AI tool, who nearly mails 63 letters with a legal deadline the assistant got wrong. You learn to write a four-part brief, steer drafts with examples, check what matters and keep restricted data out of the chat box.
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.