Create and review a synthetic campaign brief, script and storyboard while preserving facts, access, rights and provenance.
Level
Basic
Study time
12 hours
Lessons
18 in 6 modules
Exam
20 questions
About this course
Eighteen lessons connect image generation/editing, speech and music workflows, video continuity, evaluation, provenance and US-first permission/claim checks through the fictional Cedar Lantern Science Center. All required artifacts are textual source records, descriptions, metadata and seeded outputs supplied inline. No paid generator, real likeness or voice, media upload or live model is required. The core assesses planning and evidence reasoning; it does not claim to establish perceptual deepfake-detection ability or hands-on tool proficiency without actual media.
The planned twelve hours are an author estimate, not measured learner timing. Six module Decision Labs and a longer capstone combine reusable records into one recommendation. Optional live creative work adds time and uses only authorized inputs and appropriate service terms. AI feedback is fallible advisory practice, not a certificate gate. Completion follows lessons, listed labs played to any ending and the exam; it does not confer copyright ownership, legal clearance, accreditation, vendor endorsement or independent professional competence. The pre-lesson blueprint received independent parent design acceptance before lessons were written. This completed author packet awaits separate factual, instructional and assessment reviews; author checks are not those approvals.
What you will be able to do
Apply a simple generation/conditioning/editing model to write a checkable image brief without treating prompts as guaranteed factual control
Choose an audio production route and verify script, transcript, timing and voice-use scope from supplied records
Diagnose temporal and format defects in a supplied shot log and revise a storyboard without inventing observed footage
Compare manual editing, approved-source assembly and generation on task fit, review burden and an explicit baseline
Evaluate supplied image/audio/video review observations using fixed acceptance criteria, denominators and version dependencies
Interpret provenance and watermark results within their actual coverage and separate file history from depicted truth
Apply US copyright, likeness, testimonial and permission distinctions to a bounded proposed use with unresolved applicability explicit
Construct a feasible media-release recommendation with accessible alternatives, real evidence states and a revised scope after new facts
Syllabus
6 modules · 18 lessons · about 12 hours
1
Module 1: Create images from a controlled brief
Produce a fact-controlled image/edit record.3 lessons
From Noise to Picture: A Useful Mental Model for Image Generation
Condition a Prompt Without Delegating Event Facts
Repair a Poster with a Mask, a Reference and an Edit Log
Decision Lab · 10 minThe cropped reservation conditionDev must recommend a usable poster repair, not claim a final export was produced.
2
Module 2: Produce understandable audio without borrowing a persona
Prepare a script, timing and permission record.3 lessons
Text-to-Speech and Voice Imitation Are Different Production Choices
Transcribe, Translate and Time the Actual Script
Choose Music and Sound with a Usable Rights Record
Decision Lab · 10 minThe website recording meets a paid requestMaya chooses an audio proposal with actual script and use boundaries.
3
Module 3: Plan video across time and formats
Create a versioned storyboard with usable access alternatives.3 lessons
A Shot Can Look Right While Its Object Changes
Choose Text-to-Video, Image-to-Video or an Avatar for the Actual Job
Deliver Captions, Descriptions and a Sound-Off Route
Decision Lab · 10 minSix shots and a missing conditionDev selects a coherent moving or illustrated sequence from the supplied log.
4
Module 4: Compare media workflows and evaluate revisions
Compare methods against explicit quality criteria.3 lessons
Choose a Tool Category by Input, Control and Review Cost
Write a Media Prompt and a Checkable Acceptance Sheet
Evaluate Counting, Copy and Continuity Errors on a Frozen Set
Decision Lab · 10 minThe result improves when a miss disappearsChen recommends a fair small evaluation and its review effort.
5
Module 5: Preserve provenance and apply US rights boundaries
Carry source, provenance and US use boundaries into the release record.3 lessons
Read Content Credentials and Watermark Results Without Overclaiming
Check Voice, Likeness and Testimonial Scope Before a New Use
Separate Human Authorship, Input Permission and Output Use
Decision Lab · 10 minA signed record for the wrong useMaya prepares a source-linked use recommendation without acting as a rights court.
6
Module 6: Verify suspicious media and defend a release package
Verify a disputed claim and recommend a feasible revised portfolio.3 lessons
Verify a Suspicious Recording Through an Independent Channel
Write a Media H andoff with Actual Scope, Cost and Release State
Revise the Cedar Lantern Portfolio After a Paid-Vertical Request
Decision Lab · 10 minA familiar-sounding exception requestChen verifies request authority and keeps the campaign source current.
Capstone simulation · 25 minThe Cedar Lantern portfolio committeeChoose creative scope, then revise channel, checking and resources after F2 and a mismatched receipt.
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 Google. Product and company names are trademarks of their respective owners.
A free, plain-English introduction taught through one realistic company getting ready for its busiest season. Sort the kinds of AI, see why a chat assistant can sound right and be wrong, decide which tasks it fits and how to measure them, catch its three predictable failures, ask well, and decide what never goes into an AI tool.
A plain-language grounding in artificial intelligence: what AI, machine learning and generative AI actually are, how chat assistants produce text, why they sometimes get things confidently wrong, and how to use them safely for real work.
A guided tour of the machinery inside a large language model, told in plain-language analogies, tables and small runnable examples rather than equations: tokenizers, embeddings, attention, pretraining, instruction tuning, reasoning models, context windows and sampling. You leave able to explain why models behave the way they do.