AI 103CoreL1 + L2 Certificates
Agentic AI Memory, Knowledge & Skills
Move from context engineering to agentic AI: design an agent's memory, knowledge and skills, understand memory systems, RAG, semantic chunking, metadata, knowledge architecture and context optimization, and complete your own Agent Memory, Knowledge & Skills Canvas.
Your next step
AI 103 · Module 1: From Context to Agent Memory
0 / 43 items done0%
Curriculum
- Module 1From Context to Agent MemoryIf an AI no longer finishes a single task but keeps working, what does it need to remember?
- Module 2Designing Agent Memory SystemsHow should an agent's memory be organized, instead of remembering everything?
- Module 3RAG & Knowledge RetrievalWhen an agent does not know the answer, should it guess or go and look?
- Module 4Semantic Chunking & MetadataHelping the agent find the right small piece of knowledge
- Module 5Knowledge Architecture & Agent SkillsFrom "having data" to "the agent knows how to use it"
- Module 6Context OptimizationHanding the right information to the agent at the right time
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: Memory DecisionClassify information as current context, temporary memory, long-term memory, external knowledge or do not store.Not done yet
- Activity 2: Memory, RAG or Tool?Decide whether information belongs in memory, should be retrieved through RAG, or needs a tool or API call.Not done yet
- Activity 3: Chunk & Metadata DesignIdentify chunk boundaries and define metadata and retrieval filters.Not done yet
- Activity 4: Agent Skill CardDecide what belongs in each field of an Agent Skill Card.Not done yet
- Activity 5: Context Optimization ChallengeGiven an overloaded context, decide what to remove, keep, retrieve later, summarize or store as memory.Not done yet
- AI 103 assessmentTwo levels: knowledge checks and scenario decisions.Not done yet
- Agent Memory, Knowledge & Skills CanvasTurn what you learned into an Agent Memory, Knowledge & Skills Canvas you can take back to work.Not done yet
About this course
Outcomes
- Distinguish Prompt, Context, Memory, Knowledge and Skills
- Explain why persistent agents need memory beyond a single context window
- Decide whether information goes in context, memory, RAG or a tool
- Explain how chunking and metadata affect retrieval quality
- Design a basic knowledge architecture and define reusable agent skills
- Recognize context failure modes and complete an Agent Memory, Knowledge & Skills Canvas
Prerequisites
- AI 102 is recommended, or a basic grasp of context and context strategy
- You know AI output needs human review and sensitive data must not be handed to AI or remembered by an agent casually
- No programming background required
Who it is for
- Staff and faculty who finished AI 102 and want to plan an AI agent that keeps working over time
- Coordinators and managers who design knowledge bases, RAG or AI workflows
- Students and researchers who want to understand how agents remember, obtain knowledge and gain reusable skills
We suggest finishing AI 102 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.