← MindForgeAI homeJanuary 2027 proposed cohort · Admissions not openConnected campus
LaunchpointBY MINDFORGEAI
← Course catalogue

LANGUAGE & GENERATIVE AI / SPECIALIST

AI340Production RAG, search & evaluation

24 h productive allocation9 h 36 m learning + 14 h 24 m training4 units · 1 assessed practical brief

Detailed course plan and training brief. A complete taught course pack is in preparation. The linked foundation module, where shown, is a smaller available resource.

BEFORE YOU BEGIN

A clear starting point.

Prerequisites: AI320

Specialist studio; environment and faculty must be confirmed before scheduling

WHAT YOU SHOULD BE ABLE TO DEMONSTRATE

  1. Explain the assumptions and failure modes in information retrieval.
  2. Complete the practical: build and evaluate a hybrid retrieval prototype with document-level permission tests.
  3. Defend the resulting retrieval dataset with reproducible evidence.

THE SUBJECTS / FOUR CONNECTED UNITS

What you will study.

UNIT 016 h allocated

Information retrieval

  • Lexical search
  • dense retrieval
  • hybrid ranking
  • query formulation
UNIT 026 h allocated

Index engineering

  • Chunk strategies
  • metadata
  • refresh
  • access-aware retrieval
UNIT 036 h allocated

Evidence quality

  • Reranking
  • citations
  • answerability
  • abstention
UNIT 046 h allocated

Service evaluation

  • Retrieval test sets
  • support checks
  • latency
  • cost and traceability

THE TRAINING STUDIO

Make the subject
visible in your work.

Build and evaluate a hybrid retrieval prototype with document-level permission tests.

Evidence to produce

  • Retrieval dataset
  • index contract
  • support and abstention report

Training brief for supervised delivery. Code, datasets, answer keys and environment acceptance must be completed in the full course pack before delivery is confirmed.

ASSESS THE REASONING

A question you
should be able to answer.

Why must access control happen before a document becomes model context?

Review dimensions

Technical correctness · reproducibility · interpretation of results · failure analysis · individual explanation. Course-level rubric and faculty moderation form part of the final adopted teaching pack.

External reference access, hardware, cloud accounts and paid services are separate. No third-party certification is included by implication.

Search by topic or purpose. Press Escape to close.