Beginnercourse · Free
Jëfandikukat IA bu am responsabilite
Jëfandikool IA ci anam wu am njariñ boole ci aar sa bopp, saytu li ñuy génne, ba noppi baña bàyyi xel ci nit ñi.
Loading your course evidence…
Outcomes
What you will be able to do
- Design clear prompts with useful context and constraints.
- Review outputs for factual, privacy, bias, and copyright risks.
- Build a repeatable human-in-the-loop workflow.
Recommended first: Fondation IA
Curriculum
Course modules
Prompting with context
Outcome: Turn vague requests into testable instructions.
Practice: Rewrite a weak prompt with audience, context, constraints, examples, and success criteria.
Prompt and context designLanguage-model mechanicsReviewing outputs
Outcome: Detect unsupported claims and decide what requires verification.
Practice: Annotate an AI answer as verified, attributed, uncertain, or unsupported.
Output review and error detectionBias and fairnessSource and claim verificationPrivacy and ownership
Outcome: Choose safe inputs and understand content rights.
Practice: Create a red/yellow/green data policy for an AI workflow.
Privacy and data handlingCopyright and content provenanceA dependable workflow
Outcome: Combine AI assistance with checkpoints and human ownership.
Practice: Map an existing task and mark where AI may draft, check, or never decide.
AI-assisted workflow designTool selection and comparisonAutomation boundaries and safeguards
Applied capstone
Human-in-the-loop workflow
Design and test an AI-assisted workflow for a real recurring task.
- Before-and-after process
- Prompt or configuration
- Verification checklist
- Privacy and failure safeguards