Writing for people
building real AI systems.
Practical guidance on the engineering choices, evaluation methods, and observability patterns that help teams build AI with confidence.
Articles from the field.
Notes and longer-form pieces shaped by building production ML and AI systems with engineering teams.
The AI FDE Dilemma: Overpriced Engineers or Catalysts of Industry Change?
Why effective forward deployed AI engineers need business judgment, agentic-system expertise, and accountability for client outcomes—not just conventional software engineering skills.
New Control Paradigms with Agentic Components
A practical taxonomy for deciding when agentic systems should use deterministic or model-driven execution and control flow to remain capable, efficient, and auditable.
How to measure AI productivity: From LLM token costs to business value with Arize AX
A framework for moving beyond activity metrics by connecting AI cost and quality signals to validated downstream outcomes and measurable business value.
Coding agent tracing and evaluation: An open source tool to improve AI coding workflows
An introduction to open-source tracing for inspecting, evaluating, and improving coding-agent workflows across Claude Code, Cursor, Codex, Copilot, and Gemini CLI.
Adaptive Guardrails for Agentic Applications
A vector-based approach to AI safety that replaces rigid rule sets with adaptive semantic boundaries, continuous improvement, and observability.
Great Books for AI Engineering
A reading list for engineers who want to understand and build dependable production AI systems.
Achieving Self-Service Onboarding for MLOps Tooling
How we built infrastructure that enabled teams to adopt ML observability through a scalable self-service experience at Wayfair.
Great Books for Data Science 2
A follow-up collection of useful reading for practicing and aspiring data scientists.
The Generated World
Reflections on AI-generated content and what it could mean for the way people create and consume information.
Great Books for Data Science
The original collection of must-read books for developing a strong foundation in data science.