MST 509Mastery · 90 days3 US credit hours·Mastery course · Upper-division / professional elective·v1 · updated 3 Oct 2026

AI-Ready Enterprise Knowledge Fabric 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

Containerisation, secrets management and CI/CD for agents Python, Git, CLI & APIs Data readiness & SQL with AI assistants Lakehouse storage, table formats & reproducibility (Iceberg, DuckDB)Architecture review, framework selection and teaching the discipline

CO2

Demonstrate Ingestion & Document Intelligence competence: complete the Day 16–30 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C3 Apply

Containerisation, secrets management and CI/CD for agents Orchestration & pipeline engineering (Airflow, Dagster, dbt, dlt)Streaming ingestion & CDC (Kafka, Debezium, freshness SLAs)Document parsing & layout-aware extraction (Docling, tables, OCR)Chunking strategy design & measurement (semantic, late, contextual)Multi-level data quality scoring and gates PII redaction, retention & LLM data governance Architecture review, framework selection and teaching the discipline

CO3

Demonstrate Trusted Data & Knowledge Graph competence: complete the Day 31–45 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C4 Analyse

Multi-level data quality scoring and gates Entity resolution & record linkage (Splink, blocking, Fellegi–Sunter)Provenance (W3C PROV) and claim-to-cell traceability Bi-temporal modelling and point-in-time queries Ontologies & semantic standards (RDF, OWL, SKOS, SPARQL, SHACL)Knowledge-graph traversal (Neo4j)Metadata cataloguing and lineage (OpenMetadata, OpenLineage)Architecture review, framework selection and teaching the discipline

CO4

Demonstrate Semantic Access & Context Engine competence: complete the Day 46–60 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C4 Analyse

Python, Git, CLI & APIs Knowledge-graph traversal (Neo4j)Embeddings & vector search Hybrid search, chunking & reranking Context engineering Metadata design, tenant isolation and clearance-aware filtering Token counting & context budgeting Architecture review, framework selection and teaching the discipline

CO5

Demonstrate AI Control Plane competence: complete the Day 61–75 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C5 Evaluate

Bi-temporal modelling and point-in-time queries Model selection, routing, fallback and provider portability RAG pipeline design LangChain & LangGraph integration Agent memory & state MCP authorization, scoping and enterprise hardening Agent memory, budgets & guardrails CI regression gates for AI

CO6

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

C6 Create

PII redaction, retention & LLM data governance Provenance (W3C PROV) and claim-to-cell traceability Metadata design, tenant isolation and clearance-aware filtering Token counting & context budgeting CI regression gates for AI LLMOps observability & SLOs Probability, calibration, Brier & ECE Explainability and lineage drill-down UI Structured retrieval: text-to-SQL & semantic layers Scale, HA, disaster recovery and FinOps Kubernetes, IaC and supply-chain security Architecture review, framework selection and teaching the discipline AI governance (NIST AI RMF & ISO/IEC 42001)

Phases & skills

Phase	Topic	Outcomes	Deliverable	Skills
1	Foundations & Theory Days 1–15 · C2	CO1	CAPSTONE (Phase 1) — the local platform skeleton	Containerisation, secrets management and CI/CD for agents Python, Git, CLI & APIs Data readiness & SQL with AI assistants Lakehouse storage, table formats & reproducibility (Iceberg, DuckDB)Architecture review, framework selection and teaching the discipline
2	Ingestion & Document Intelligence Days 16–30 · C3	CO2	CAPSTONE (Phase 2) — the ingestion & extraction pipeline	Containerisation, secrets management and CI/CD for agents Orchestration & pipeline engineering (Airflow, Dagster, dbt, dlt)Streaming ingestion & CDC (Kafka, Debezium, freshness SLAs)Document parsing & layout-aware extraction (Docling, tables, OCR)Chunking strategy design & measurement (semantic, late, contextual)Multi-level data quality scoring and gates PII redaction, retention & LLM data governance Architecture review, framework selection and teaching the discipline
3	Trusted Data & Knowledge Graph Days 31–45 · C4	CO3	CAPSTONE (Phase 3) — the trusted knowledge fabric	Multi-level data quality scoring and gates Entity resolution & record linkage (Splink, blocking, Fellegi–Sunter)Provenance (W3C PROV) and claim-to-cell traceability Bi-temporal modelling and point-in-time queries Ontologies & semantic standards (RDF, OWL, SKOS, SPARQL, SHACL)Knowledge-graph traversal (Neo4j)Metadata cataloguing and lineage (OpenMetadata, OpenLineage)Architecture review, framework selection and teaching the discipline
4	Semantic Access & Context Engine Days 46–60 · C4	CO4	CAPSTONE (Phase 4) — the Context Engine	Python, Git, CLI & APIs Knowledge-graph traversal (Neo4j)Embeddings & vector search Hybrid search, chunking & reranking Context engineering Metadata design, tenant isolation and clearance-aware filtering Token counting & context budgeting Architecture review, framework selection and teaching the discipline
5	AI Control Plane Days 61–75 · C5	CO5	CAPSTONE (Phase 5) — the AI control plane	Bi-temporal modelling and point-in-time queries Model selection, routing, fallback and provider portability RAG pipeline design LangChain & LangGraph integration Agent memory & state MCP authorization, scoping and enterprise hardening Agent memory, budgets & guardrails CI regression gates for AI
6	Production, Governance & Mastery Days 76–90 · C6	CO6	MASTERY CAPSTONE — end-to-end customer intelligence	PII redaction, retention & LLM data governance Provenance (W3C PROV) and claim-to-cell traceability Metadata design, tenant isolation and clearance-aware filtering Token counting & context budgeting CI regression gates for AI LLMOps observability & SLOs Probability, calibration, Brier & ECE Explainability and lineage drill-down UI Structured retrieval: text-to-SQL & semantic layers Scale, HA, disaster recovery and FinOps Kubernetes, IaC and supply-chain security Architecture review, framework selection and teaching the discipline AI governance (NIST AI RMF & ISO/IEC 42001)