Field notes · page 3 of 3
AI Engineering Articles, Page 3
From the review desk
Production AI systems: inference and serving, retrieval, agents, evaluation and AI security, multimodal and edge pipelines, and AI-native product architecture.
Articles, page 3
-
Structured Outputs Beyond Valid JSON
Designing schemas, constrained decoding, semantic validators, repairs, and safe evolution for dependable model integrations.
-
Model Context Protocol in Production
Designing MCP servers, capability discovery, authorization, transport, schemas, and observability for real agent ecosystems.
-
Edge LLM Inference: Designing for the Device
Quantization, memory, thermal budgets, runtimes, privacy, and hybrid execution for useful models on constrained hardware.
-
AI Data Flywheels Without Feedback Pollution
Turning product use into better data through instrumentation, review, provenance, counterfactuals, and controlled training loops.
-
AI Product UX for Systems That Can Be Wrong
Designing intent, progress, evidence, editing, confirmation, and recovery so capability becomes trustworthy product behavior.
-
Production AI Architecture in Laravel and PHP
Queues, streaming, typed provider boundaries, retrieval, tool execution, and observability for durable AI features in Laravel.