AI Systems Engineering
Engineering AI systems across model behavior, runtime, evaluation, infrastructure, interfaces, and cost.
Topics
The topic layer is the archive's semantic spine: definitions, related fields, linked papers, systems, and future notes.
Archive summary: The topic layer defines the vocabulary of the archive for humans and retrieval systems. Topics currently active in the published field notes are inference economics and verification economics; the broader topic graph is below.
AI Systems Engineering
Agent Infrastructure
Voice AI Systems
Inference Economics
Verification Economics
Distributed Systems
Embedded Autonomy
The cost, latency, quality, and verification structure of running AI systems after training.
Verification EconomicsDistributed SystemsAI Systems Engineering
Disaggregated or Colocated? The Cost-Frontier of LLM Serving Under SLO Contracts.The Inference-Time Compute Frontier. A Cost-Correct Threshold for Training Versus Test-Time Allocation.
Engineering AI systems across model behavior, runtime, evaluation, infrastructure, interfaces, and cost.
Runtime, memory, tooling, verification, and operating layers for long-running agent systems.
AI Systems EngineeringVoice AI SystemsVerification Economics
Real-time speech and agent systems where latency, turn-taking, reliability, and interface behavior are binding constraints.
The cost, latency, quality, and verification structure of running AI systems after training.
Verification EconomicsDistributed SystemsAI Systems Engineering
A cost model centered on correct answers, verifier accept rates, and the economics of deciding whether outputs are usable.
Systems for research workflows, market structure, execution, risk, and financial automation.
The mechanisms, incentives, venues, and infrastructure that shape how markets route, price, and settle activity.
The coordination, reliability, state, and runtime behavior of systems spread across machines or services.
Autonomous behavior under compute, power, sensing, latency, and deployment constraints.
Systems that combine perception, control, navigation, autonomy, embedded compute, and operational constraints.
The interaction layer between humans and AI systems, especially where trust, handoff, memory, and control matter.
Personal, organizational, and technical systems for decision-making, automation, instrumentation, and execution.
Results are local, static, and index the same public surfaces exposed to crawlers.