MST 505Mastery · 90 days3 US credit hours·Mastery course · Upper-division / professional elective·v1 · updated 3 Oct 2026

Context Engineering Mastery

University / Board Instructor Student Outcomes & Skills

Course outcomes

CO1

Demonstrate Foundations & Theory competence: complete the Day 1–15 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C2 Understand

Context engineering Foundation model mechanics Token counting & context budgeting Prompt engineering

CO2

Demonstrate Retrieval & Knowledge Context competence: complete the Day 16–30 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C3 Apply

RAG pipeline design Embeddings & vector search Hybrid search, chunking & reranking Query understanding: rewriting, decomposition, adaptive retrieval Metadata design, tenant isolation and clearance-aware filtering Evaluation engineering with golden sets Citations, groundedness and the ten-cause RAG diagnosis

CO3

Demonstrate Conversation State & Memory competence: complete the Day 31–45 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C4 Analyse

Conversation state, summarisation & compaction Agent memory & state

CO4

Demonstrate Agents, Tools & Orchestration competence: complete the Day 46–60 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C4 Analyse

Context engineering Agent memory & state Building an agent loop from primitives (no framework)Tool contract design, descriptions and token-efficient returns Tool calling & MCP integration Multi-agent orchestration Long-running & self-verifying agents Graph orchestration with typed state and conditional control flow Model selection, routing, fallback and provider portability Structured outputs & schema validation

CO5

Demonstrate Evaluation, Caching, Multimodal & Observability competence: complete the Day 61–75 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C5 Evaluate

Evaluation engineering with golden sets Citations, groundedness and the ten-cause RAG diagnosis Structured outputs & schema validation CI regression gates for AI LLMOps observability & SLOs LLM cost & latency estimation Prompt caching & cache-aware context design Multimodal context (images, PDFs, audio, video)

CO6

Demonstrate Production, Security, Governance & Mastery competence: complete the Day 76–90 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C6 Create

Metadata design, tenant isolation and clearance-aware filtering Tool calling & MCP integration LLM cost & latency estimation AI security & prompt-injection defence Agent environments & sandboxing Reference architecture & trust boundaries Portability & open alternatives AI red-teaming Responsible AI & regulatory compliance Team delivery & technical communication

Phases & skills

Phase	Topic	Outcomes	Deliverable	Skills
1	Foundations & Theory Days 1–15 · C2	CO1	CAPSTONE (Phase 1) — Context budgeter & window visualizer	Context engineering Foundation model mechanics Token counting & context budgeting Prompt engineering
2	Retrieval & Knowledge Context Days 16–30 · C3	CO2	CAPSTONE (Phase 2) — Hybrid RAG with citations + eval harness	RAG pipeline design Embeddings & vector search Hybrid search, chunking & reranking Query understanding: rewriting, decomposition, adaptive retrieval Metadata design, tenant isolation and clearance-aware filtering Evaluation engineering with golden sets Citations, groundedness and the ten-cause RAG diagnosis
3	Conversation State & Memory Days 31–45 · C4	CO3	CAPSTONE (Phase 3) — Governed memory service	Conversation state, summarisation & compaction Agent memory & state
4	Agents, Tools & Orchestration Days 46–60 · C4	CO4	CAPSTONE (Phase 4) — Long-running agent: editing + memory + MCP	Context engineering Agent memory & state Building an agent loop from primitives (no framework)Tool contract design, descriptions and token-efficient returns Tool calling & MCP integration Multi-agent orchestration Long-running & self-verifying agents Graph orchestration with typed state and conditional control flow Model selection, routing, fallback and provider portability Structured outputs & schema validation
5	Evaluation, Caching, Multimodal & Observability Days 61–75 · C5	CO5	CAPSTONE (Phase 5) — Eval + observability harness	Evaluation engineering with golden sets Citations, groundedness and the ten-cause RAG diagnosis Structured outputs & schema validation CI regression gates for AI LLMOps observability & SLOs LLM cost & latency estimation Prompt caching & cache-aware context design Multimodal context (images, PDFs, audio, video)
6	Production, Security, Governance & Mastery Days 76–90 · C6	CO6	MASTERY CAPSTONE — Full production context-engineering reference implementation	Metadata design, tenant isolation and clearance-aware filtering Tool calling & MCP integration LLM cost & latency estimation AI security & prompt-injection defence Agent environments & sandboxing Reference architecture & trust boundaries Portability & open alternatives AI red-teaming Responsible AI & regulatory compliance Team delivery & technical communication