I Built the Same Agent Twice to Find Out If the Harness Matters
A controlled comparison of a hand-rolled Python harness and Google ADK - and what happened when I audited my own headline
professional
Professional
Technical reports. Each one accompanies a repository - the write-up explains the work, the code is the proof.
The Life and Lies of Data Contextualization for Agentic AI
Does your AI agent actually know what it doesn't know? 3,800 controlled experiments across three frontier models, measuring whether the metadata around your data changes how reliable the agent is.
When the Data Refuses to Behave: Building an Agentic Demand Forecasting System
How classical time series, deep learning, and Generative AI come together to tackle one of supply chain's oldest problems — built on the M5 competition data, where 68% of item-level observations are zero.
Project VIGIL - Agentic Pharmacovigilance
Agentic Pharmacovigilance - automating adverse-event case processing and safety signal detection
VERDICT: Validation and Explainability framework for Reproducible, Deterministic, Inspectable Compliance Testing
Can You Trust an LLM to Grade Pharmaceutical Compliance? I Built a Framework to Find Out.