AI 102FoundationL1 + L2 Certificates
Context Engineering: What Should AI Know?
Move from prompts to context: learn what information an AI task needs, which sources to trust, what to retrieve on demand and what never to provide, and complete your own Context Canvas.
Your next step
AI 102 · Module 1: From Prompt to Context
0 / 48 items done0%
Curriculum
- Module 1From Prompt to ContextWhy an excellent prompt can still produce a wrong answer.
- Module 2What Is Context Made Of?The seven kinds of information an AI task may need: instructions, user, task, reference knowledge, history, state and memory, tool results.
- Module 3Context Selection: What Is Worth Letting the AI Know?Use RAFS (Relevance, Authority, Freshness, Sensitivity) to decide what belongs in the context.
- Module 4Include / Retrieve / Remember / ExcludeNot all context belongs in the prompt: learn the four context strategies.
- Module 5Context FailureMissing, overloaded, stale, conflicting, poisoned and lost-in-the-middle: how AI fails when context is designed wrongly.
- Module 6Context Canvas: from case to work applicationDesign the context for a real AI use case and complete a Context Canvas you can take back to work.
Progress is stored in this browser and does not identify you. It is uploaded only if you join progress sync below.
Sync my progressJoin a session to keep progress across devices and share it with your instructor
Practice and assessment
- Activity 1: Prompt or Context?Decide whether the problem is the prompt, the context, both, or needs human judgment.Not done yet
- Activity 2: Context ClassificationSort information into the seven context types.Not done yet
- Activity 3: Context Quality (RAFS)Assess sources by relevance, authority, freshness and sensitivity.Not done yet
- Activity 4: Context DecisionDecide whether information should be included, retrieved, remembered or excluded.Not done yet
- Activity 5: Failure DiagnosisDiagnose whether an AI failure is a prompt, context, tool, model or human-judgment problem.Not done yet
- AI 102 assessmentTwo levels: knowledge quiz and scenario judgment.Not done yet
- Context CanvasTurn what you learned into a Context Canvas you can take back to work.Not done yet
About this course
Outcomes
- Tell a Prompt problem from a Context problem
- Judge what information an AI task really needs
- Assess information for relevance, authority, freshness and sensitivity
- Decide whether information should be included, retrieved, remembered or excluded
- Recognize common context failures
- Complete a Context Canvas you can take back to work
Prerequisites
- AI 101 is recommended, or a basic grasp of prompting and task definition
- You know AI output needs human review and sensitive data must not be handed to AI casually
- No programming background required
Who it is for
- Staff and faculty who finished AI 101 and want more reliable AI output
- Coordinators and managers who plan AI workflows and must judge data sources and sensitivity
- Students and researchers who want to know why AI still errs after a good prompt
We suggest finishing AI 101 first. This is a suggestion only and never blocks you from starting.
Certificate
Earns a course completion certificate (L1); a capability certificate (L2) is also available through additional artifact review.
Requirements to earn it
- Complete all 6 course modules
- Pass the post-test assessment at 80% or higher
- Submit a project artifact and pass review
Course feedback
It takes 2 to 3 minutes and is used to improve the course.