ProductJanuary 14, 2026

Automating Splice Diagrams with TIA-598 Compliance

By Ariel Aviv

Splice documentation is one of the most error-prone steps in fiber deployment.

We built an AI-driven splice engine that generates fully compliant TIA-598 diagrams, tracks every fiber from OLT to ONT, and validates optical loss budgets before a single cable is pulled. This post covers the architecture of the splice automation system, the challenges of maintaining fiber continuity through cascaded splitters, and how we handle the combinatorial complexity of multi-tube cable assignments.

Full article coming soon.

Why Geospatial AI Agents Are Uniquely Hard to Build

Over two years of building AI agents that design fiber networks on real maps, we learned something most LLM-agent literature ignores: the physical world doesn't tolerate hallucination. This post breaks down the five fundamental constraints and the design principles that survived production.

Read post

Engineering

January 28, 2026

Agentic FTTH Design: How AI Agents Plan Fiber Networks End-to-End

Traditional FTTH planning requires weeks of manual work across GIS, CAD, and spreadsheet tools. Nexma's agentic approach compresses this into minutes — a single AI agent reasons about topology, optical budgets, and real-world street geometry to produce deployment-ready designs.

Read post

Research

December 19, 2025

Why MIP Alone Isn't Enough for Real-World Network Optimization

Mixed-Integer Programming finds mathematically optimal solutions — but it doesn't know about building footprints, street access, or pole-mounted closures. We combine MIP with geography-aware heuristics to get the best of both: optimality where it matters, practicality everywhere else.

Read post