Customer-obsessed science

We analyze Optical Add/Drop Multiplexing architecture trade-offs for Cloud Content Providers focusing on G-SNR, operations, reliability, and cost/power. We show that as coherent baud-rates increase, directly attaching transponders to the WSS satisfies all key metrics.

Deploying LLMs for enterprise Text-to-SQL is bottlenecked less by the model than by what context reaches it: business logic spans thousands of tables, and no model can ingest a full catalog at once. We argue that the most effective place to intervene is therefore the knowledge-base context the model consumes, and that this context should be constructed from historical usage rather than tuned for as a fixed

Single-metric task-success scores systematically misrank LLM agents in domain-specific deployments: two configurations can achieve identical end-to-end accuracy while exhibiting structurally different production behaviors — silent argument hallucination, infinite tool loops, redundant retries, semantically-equivalent-but-syntactically-divergent queries. We propose a behavioral evaluation protocol that decomposes

Accurate map paths are crucial for routing vehicles, pedestrians, and autonomous systems, yet keeping that data fresh demands continual editing of features and geometry, and labeling of attributes such as surface type and lane count. At scale this is labor-intensive, and each change calls for spatial reasoning and verification that has resisted full automation, keeping a human in the loop. We present MapScout

Last-mile logistics efficiency largely depends on map data being accurate, fresh, and having high geospatial coverage. Operators must preserve these qualities when migrating between heterogeneous map data providers. Existing work in the literature addresses road-geometry conflation; however, the conflation of road network attributes and their transition relations remains under-studied, especially at a production-level