# Course

Search Engineering · Course

Interactive edition: https://mutapa.dev/search-engineering/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.

[Read the fifteen constraints](https://mutapa.dev/search-engineering/course/constraints.md)

## Part 1: Search Foundations

Build and evaluate the search pipeline.

1. [What Is Relevance?](https://mutapa.dev/search-engineering/course/what-is-relevance.md): What makes a result right for this user and this task?
2. [Corpus and Indexing](https://mutapa.dev/search-engineering/course/corpus-and-indexing.md): What can the system find, and how is it represented?
3. [Query Understanding](https://mutapa.dev/search-engineering/course/query-understanding.md): What is the user asking the system to do?
4. [Retrieval](https://mutapa.dev/search-engineering/course/retrieval.md): Where do lexical and vector retrieval fail?
5. [Ranking and Fusion](https://mutapa.dev/search-engineering/course/ranking-and-fusion.md): Which candidates should appear first?
6. [Generation](https://mutapa.dev/search-engineering/course/generation.md): How should retrieved evidence constrain an answer?
7. [Evaluation and Feedback](https://mutapa.dev/search-engineering/course/evaluation-and-feedback.md): How do we measure quality and improve it safely?

## Part 2: Agentic Search

Turn the pipeline into a controlled, observable loop.

8. [Agentic Orchestration](https://mutapa.dev/search-engineering/course/agentic-orchestration.md): When should a system inspect results and search again?
9. [Plan and Route Complex Searches](https://mutapa.dev/search-engineering/course/plan-and-route-complex-searches.md): How should a complex request become coordinated search work?
10. [Maintain State and Recover](https://mutapa.dev/search-engineering/course/maintain-state-and-recover.md): How should an agent preserve progress across turns and failures?
11. [Authorize Agent Actions](https://mutapa.dev/search-engineering/course/authorize-agent-actions.md): What may an agent trust, access, and do without approval?
12. [Evaluate Agentic Search](https://mutapa.dev/search-engineering/course/evaluate-agentic-search.md): How 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.

13. [Permissioned Retrieval](https://mutapa.dev/search-engineering/course/permissioned-retrieval.md): Which evidence may this principal retrieve?
14. [Policy Through the Trajectory](https://mutapa.dev/search-engineering/course/policy-through-the-trajectory.md): How does authorization remain intact through every search, retry, memory read, and handoff?
15. [Connectors and Trust Boundaries](https://mutapa.dev/search-engineering/course/connectors-and-trust-boundaries.md): Which external claims and capabilities can the system rely on?