adrian tame adrian tame

about me

I am building Plicara Labs, my independent AI research lab: reproducible studies, benchmarks, and tools for understanding and improving AI systems. Its projects include labloop, an agent-driven experiment loop, and regexbench, an evaluator for LLM-generated regular expressions.

At S&P Global, I am a Lead II Data Scientist working on document extraction and internal benchmarking for model evaluation. Previously, I worked on experimentation and customer segmentation at Zillow and held data-science leadership roles at Coca-Cola FEMSA. More about my experience.

I studied applied mathematics at ITAM, where I completed my MSc in Data Science coursework in 2022; my thesis is expected in September 2026.

Underneath the agent work is a decade+ of statistical practice: Bayesian optimization (my MSc thesis develops Bayesian Adaptive Spline Surfaces as a surrogate model and an alternative to Gaussian processes), agentic systems and benchmarks for them, causal inference, and large-scale experimentation and A/B testing. The through-line in both halves is the same: I care about systems whose conclusions can be trusted, with honest uncertainty, tiered evidence, and results that survive contact with production.

Right now I am learning econometric theory, systems design, and Rust. I am always happy to collaborate on agentic systems, benchmarking, novel AI research, and anomaly detection.