AI curriculum
Course outline for Context Engineering and Context Graphs
An agent needs relevant situation-specific information, not every available fact. Model context with provenance and time, then retrieve the evidence needed for a task.
About Context Engineering and Context Graphs
An agent needs relevant situation-specific information, not every available fact. Model context with provenance and time, then retrieve the evidence needed for a task.
Context Engineering and Context Graphs Course Objectives
- Distinguish reusable knowledge from task context.
- Model activity, provenance, and temporal relationships.
- Assemble a bounded context package for an agent.
Pre-requisites
- Familiarity with graphs and agent inputs.
- Basic data modelling or application design skills.
Lab Setup
- Computer with a graph editor or local graph library.
- Use synthetic activity records and user profiles; no personal or confidential records are necessary.
Detailed Course Outline
Proposed modulesModule 1: Context models
- Context vs knowledge
- Context graphs
- Activity graphs
Practical outcome: Model task context separately from stable domain facts.
Module 2: Context provenance
- Provenance
- Temporal context
- User context
Practical outcome: Record source, time, and access constraints for context.
Module 3: Context assembly
- Workflow context
- Context retrieval
- Context construction for agents
Practical outcome: Select context for a specific workflow decision.
Practical exercise
- Build a context graph and assemble an agent input with traceable evidence and excluded irrelevant facts.
How we train
Contact us for full course details, including duration, delivery options and lab requirements.
Ask about exercises, instructor feedback and the prior knowledge you need. Tool-specific courses marked provisional may become modules in a broader course.
Discuss your learning goals