Night-before cheat sheet

Part XI: Building Agents and Agent Infrastructure

11 chapters (131–141). 0 key facts to review.

Chapters at a glance

131 Agent SDKs and frameworks: from primitives to production
132 Agent memory systems: context, retrieval, and persistence
133 Code-executing agents: sandboxes, REPLs, and the code-as-tool pattern
134 Computer use and browser agents: vision, interaction, and the GUI-as-API pattern
135 Agent evaluation and testing: benchmarks, traces, and the eval flywheel
136 Agent security and permissions: sandboxing, delegation, and defense in depth
137 Agent observability and debugging: traces, cost attribution, and the non-determinism problem
138 -- Agent-to-agent communication: A2A, agent cards, and the interoperability problem
139 -- Long-running and background agents: daemons, checkpoints, and async execution
140 Designing an agent product: UX, streaming, and the human-in-the-loop contract
141 Agent SWE interview preparation: the questions they actually ask

Key facts (from quizzes)

Other parts
Part I Part II Part III Part IV Part V Part VI Part VII Part VIII Part IX Part X Part XI