Complete index

Work

The homepage is curated. Nothing is hidden here.

Flagship case studies

• The SystemArchitecture, interfaces, asynchronous delivery, and a broken contract seam
• Defense News ClassifierHuman-labeled evaluation, reversals, and evidence-gated model decisions
• Faithfulness JudgeWhether an LLM judge can reliably identify unsupported claims
• Product & ProgramRoadmap, dependencies, risks, metrics, and the limits of a solo simulation

Evaluation and reliability

• Classifier baseline and live demo — run the TF-IDF logistic-regression baseline in the browser.
• False Green — six checks that passed when the required work never ran.
• Retrieval, Measured — a 27-query gold set and three paired retrieval experiments.
• The Autonomy Ladder — four levels of agent autonomy, with two shipped and two rejected.
• Loop Replay — interactive playback of two autonomous improvement runs.
• Context Architecture — an audit of relevance, sufficiency, isolation, economy, and provenance.

Systems and infrastructure

• One Note, End to End — one payload traced across the real service contracts.
• Zero-Touch Provisioning — a factory-blank router configured after one power cycle.

Looking for terminology used across the projects? Open the glossary →