Skip to content

Antenor / Blog

Field notes

Operations AI, written by the people who build it. Routing, forecasting, simulation, knowledge systems, automation. No hype, numbers where they exist.

Latest

We Built RAG Before It Was Called RAG

Decades before large language models, we built XLBase — a proprietary retrieval engine — and the legal case-law system on it acquired by Jurisprudencia Argentina. What that experience teaches about building RAG that actually works today.

By Antonio Velázquez Bustamante

All posts

  1. Do You Actually Need a Bigger Warehouse? Before signing a lease on more square meters, simulate. System dynamics routinely finds double-digit headroom in the operation you already have — and, if you do move, the location that minimizes cost. Antonio Velázquez Bustamante system-dynamics, operations, logistics
  2. Top AI Consulting Firms for Operations (2026 Guide) An honest comparison of six AI consulting firms for operations work in 2026: Antenor, Tryolabs, RTS Labs, Prolego, Width.ai and Neurons Lab, and who fits what. Antonio Velázquez Bustamante ai-consulting, operations, guide
  3. The Automation Worth Building Is the One That's Impossible by Hand Most automation shaves minutes off work a person could still do. The automation that pays does what a person fundamentally cannot — like rating and settling thousands of clients' calls against a tariff in two hours, a run that was impossible manually. Antonio Velázquez Bustamante process-automation, operations, ai-agents
  4. You Can Count Crops From Space — Accurately Enough to Trust Open satellite imagery plus machine learning turns 'how much land is planted' into a measured number. Validated against a government's own sown-area figures, our classifier reached over 90% accuracy — no proprietary data required. Antonio Velázquez Bustamante computer-vision, remote-sensing, predictive-models
  5. When Your Data Is Too Big for a Normal Database At carrier scale — hundreds of billions of records, ingested continuously, queried in under a second — a general-purpose database can't hold both ends of the trade-off. You stop fighting the tool and engineer for the workload's real shape. Antonio Velázquez Bustamante custom-software, data-engineering, search
  6. How to Tell If a Machine Learning Model Actually Works Most models look brilliant right up to the first live decision. The difference between a result and an anecdote is the validation discipline: strict temporal separation, genuinely unseen data, and explicit defenses against the ways you fool yourself. Antonio Velázquez Bustamante predictive-models, machine-learning, evaluation
  7. Why Most AI Initiatives Stall Before Production The six failure modes that keep AI projects in pilot purgatory, how to detect each one early, and the single habit that separates shipped systems from demos. Antonio Velázquez Bustamante ai-strategy, mlops, consulting
  8. Process Automation: Build vs Buy in 2026 A decision framework for AI process automation: when off-the-shelf tools win, when custom is cheaper over three years, and the integration test that settles it. Antonio Velázquez Bustamante process-automation, ai-agents, strategy
  9. Weather Nowcasting with Public Data: What We Learned Lessons from building a convective nowcasting system on SINARAME radar and GOES-19 satellite data: pipelines, baselines, verification, and honest skill claims. Antonio Velázquez Bustamante nowcasting, forecasting, machine-learning
  10. The ROI Math of Predictive Maintenance with Machine Learning A cost model for predictive maintenance: the four value drivers, the full cost side including false alarms, and a break-even test to run before building anything. Antonio Velázquez Bustamante predictive-maintenance, machine-learning, roi
  11. Route Optimization at Scale: Solving TSP for Last-Mile Logistics Why last-mile routing is not textbook TSP, which solver strategies survive real dispatch operations, and what it takes to serve optimized routes in seconds via API. Antonio Velázquez Bustamante route-optimization, logistics, operations-research
  12. RAG vs GraphRAG: When Knowledge Graphs Actually Pay Off What GraphRAG adds over vector RAG, what graph construction really costs, and the query patterns where a knowledge graph earns its keep in production. Antonio Velázquez Bustamante rag, graphrag, knowledge-systems

Reading is free. So is the first session.

Book a free AI strategy session