Skip to content
Search Engineering

From search foundations to governed search

Course

Part I develops the search pipeline and the evidence needed to evaluate it. Part II adds agents that can plan, act, recover, and be evaluated as complete trajectories. Part III carries identity and policy through retrieval, memory, and external systems.

The fifteen constraints →

Part 1

Search Foundations

Build and evaluate the search pipeline.

  1. 1What Is Relevance?What makes a result right for this user and this task?
  2. 2Corpus and IndexingWhat can the system find, and how is it represented?
  3. 3Query UnderstandingWhat is the user asking the system to do?
  4. 4RetrievalWhere do lexical and vector retrieval fail?
  5. 5Ranking and FusionWhich candidates should appear first?
  6. 6GenerationHow should retrieved evidence constrain an answer?
  7. 7Evaluation and FeedbackHow do we measure quality and improve it safely?

Part 2

Agentic Search

Turn the pipeline into a controlled, observable loop.

  1. 8Agentic OrchestrationWhen should a system inspect results and search again?
  2. 9Plan and Route Complex SearchesHow should a complex request become coordinated search work?
  3. 10Maintain State and RecoverHow should an agent preserve progress across turns and failures?
  4. 11Authorize Agent ActionsWhat may an agent trust, access, and do without approval?
  5. 12Evaluate Agentic SearchHow do we judge the quality and cost of an entire trajectory?

Part 3

Governed Search

Keep evidence and action inside attributable authority across system boundaries.

  1. 13Permissioned RetrievalWhich evidence may this principal retrieve?
  2. 14Policy Through the TrajectoryHow does authorization remain intact through every search, retry, memory read, and handoff?
  3. 15Connectors and Trust BoundariesWhich external claims and capabilities can the system rely on?