Systems where AI agents execute multi-step tasks autonomously, raising interconnected questions about harness architecture, state management, reliability engineering, human oversight, and the organizational context those agents operate within.

LLM agents are software systems that pair a language model with tools, memory, and control flow to accomplish multi-step tasks autonomously; the emerging consensus is that reliability requires engineering constraints, not better prompts.

LLM engineering spans the full stack of building with large language models: training, inference optimization, agent architecture, harness design, and the operational tradeoffs that determine whether model capability translates into reliable software.

Observability spans infrastructure, distributed systems, and AI agents — the practice of making system internals legible through traces, events, and feedback signals so engineers can understand, debug, and improve what they've built.

The engineering decisions that determine how software behaves under real load, covering durability, observability, testing discipline, performance constraints, and the operational costs of failure.