Writing & research
Writing, open source & research
I write about AI-assisted engineering, build open-source reliability tooling, and publish peer-reviewed research on observability and LLM systems.
Writing & open source
Spec-Driven Development Is the New Developer Superpower
How spec-first workflows and agentic tooling turn written specifications directly into shipped features.
Featured in the editors’ “CEO’s Highlighted Reads of the Week.”
Open source · assevra.aiAssevra AI — open-source reliability scorecard for LLM agents
Co-founder and contributor. Evaluates LLM agents across grounding, safety, PII leakage, and task completion, producing signed, offline-runnable reports with statistical confidence intervals and mapping to governance frameworks (EU AI Act, NIST AI RMF, ISO/IEC 42001).
Peer-reviewed publications
Telemetry Quality Indexing for AI-Ready Observability in Multi-Node Cloud Systems: A Multi-Dimensional Framework for Distributed Infrastructure Diagnosis
International Journal of Engineering Development and Research (IJEDR)
A multi-dimensional framework for scoring telemetry quality to enable AI-ready observability and automated diagnosis across distributed infrastructure.
CostAgent: Self-Improving Autonomous LLM-Based Orchestration for Cost-Optimal Cloud Data Processing at Scale
IEEE (IEEE Xplore)
A self-improving, LLM-based orchestration approach for cost-optimal cloud data processing at scale.
Learning to Filter Documents for Information Extraction using Rapid Annotation
IEEE
Machine-learning approach to filtering documents for information extraction, from federally funded materials-informatics research.