Writing Hub
AI governance essays, reasoning systems notes, experiment logs, and technical writing across BioAI and engineering practice.
Project Topics
The Two Problems No One Talks About in AI Agent Coding Pipelines
AI agent coding pipelines fail not because models are weak, but because verification is structurally broken. This article identifies four empirically documented failure mechanisms — agreement bias, latent entanglement, echoing, and right-for-wrong-reasons — and proposes a concrete architecture: hash-chained audit records, hybrid recurrence scoring, dynamic context budgets, and evidence-first review across three independent axes. Covers multi-agent pipeline design, agentic code review, blueprint indexing, and P0–P4 governance gates.
Stanford. Princeton. A bioRxiv Paper. So Why Did Nobody Ask Where the Data Goes?
BioClaw processes EHR data. Its primary showcase channel is WhatsApp. We audited the repository: 60/100, Tier 2 Caution. Here is what the bioRxiv paper says that the README does not.
Your Bio Repo Could Get You Fined. Here Is Why We Check Every Single One.
When a bio AI repository claims HIPAA compliance but the code says otherwise, the legal exposure falls on whoever deploys it. STEM-BIO-AI evaluated yorkeccak/bio — 322 stars, modern stack, one dangerous README line. Score: 48/100. T1 Quarantine. Full audit report with score matrix, regulatory traceability, and raw machine output.
Beyond Repo Scanning: How AIRI Expanded the Risk Vocabulary in STEM BIO-AI 1.7.x
How STEM BIO-AI uses the MIT AI Risk Repository as a governed local risk-vocabulary layer without replacing deterministic repository scanning
When Control Becomes Authority: Calibration Governance in STEM BIO-AI 1.7.x
Why STEM BIO-AI treats calibration as governed policy instead of a free-form score-tuning console for bio and medical AI repository audits.
Role Separation Is Not Verification: The Structural Failures Hidden in Your Multi-Agent Pipeline
A research-backed breakdown of why agent role design alone does not produce reliable audits — and what actually does
Prompt → RAG → MCP → Agent → Harness, and What?
Why the next layer in AI may be governance infrastructure, not just better agents.
The Harness Is the Product: What the Claude Code Leak Actually Revealed About AI Agent Architecture
The Claude Code leak exposed more than source. It revealed that modern AI agent performance depends heavily on the harness around the model.
Prompt, Pray & Push: Why Your AI Agent Keeps Failing You
The one concept that turns expensive spaghetti into great agentic engineering.
Your Agentic Stack Has Two Layers. It Needs Three.
Most agentic stacks cover tools and skills, but miss intent governance. Learn why a third layer is needed to stop AI drift, scope creep, and technically correct systems heading in the wrong direction.
AI Agents Are Poisoning Your Codebase From the Inside
Explore how AI-generated code can silently degrade software quality through weakened tests, rising code churn, and duplication—and how teams can prevent it with better governance.