Writing

On the decisions that shape enterprise AI, data platforms, and technology organizations.


Multi-Agent AI

The Agent Identity Gap: Why MCP and A2A Need Verifiable Delegation

2026

A scan of ~2,000 MCP servers found all lacked authentication. OAuth 2.1 covers single-hop auth, but multi-agent delegation chains need more. How verifiable identity connects to routing, provenance, and reasoning.

Read

When Smarter AI Isn't Worth It

2026

Most teams over-engineer simple tasks and under-engineer complex ones. A framework for matching AI architecture complexity to task complexity — with data on when 62x more compute is the right call.

Read

The Missing Agent Stack: Identity + Durable Execution with LDP and JamJet

2026

Code-first walkthrough: build identity-aware agent routing with LDP identity cards and JamJet's Coordinator. Difficulty-based scoring, provenance-weighted synthesis, runnable example.

Read

From Debate to Deliberation: When Multi-Agent Reasoning Needs Structure

2026

Multi-agent debate is unstructured and lossy. DCI introduces typed reasoning moves, preserved disagreements, and guaranteed convergence — with honest results on when the 62x token cost is justified.

Read

Why Multi-Agent AI Systems Need Identity-Aware Routing

2026

Current agent protocols treat all models as interchangeable black boxes. LDP introduces identity-aware delegation — and the results show where it matters and where it doesn't.

Read

From NER Pipelines to LLM Agents: How Production NLP Changed in Seven Years

March 2025

Seven years from BiLSTM-CRF at a startup to multi-agent protocols — what changed in production NLP, what stayed the same, and what the arc tells us about where we are going.

Read

Enterprise AI & Governance

Your ML Risk Framework Wasn't Built for GenAI. Here's What's Missing.

2026

Why traditional model risk management fails for LLMs — hallucination policy, GenAI risk dimensions, deployment gates, prompt audit trails, and what a complete governance framework looks like.

Read

The Year LLMs Met Compliance — And Compliance Wasn't Ready

October 2023

GPT-4 is genuinely capable. Enterprise wants to use it. But the governance frameworks built for classical ML — model validation, risk management, audit trails — were not designed for non-deterministic models with emergent capabilities.

Read

GPT-3 Changed the Game — Is Enterprise Ready?

November 2020

175 billion parameters, few-shot learning, and an API. GPT-3 shows where language models are going. But cost, latency, data privacy, and governance stand between the demo and production.

Read

AI Leadership & Strategy

Most Companies Know Their AI Spend. Almost None Know Their AI Readiness.

2026

Most organizations know their AI spend. Almost none can answer basic questions about whether they’re ready to absorb what they’re buying. A diagnostic across five readiness dimensions, and a 10-minute assessment tool to find the gaps.

Read

The Middle Management AI Gap

2026

Boards are excited about AI. Engineers are building it. But the layer between the boardroom and the engineering floor is where most enterprise AI programs quietly die — and nobody talks about it.

Read

Why Most Enterprise AI Programs Fail Before They Start

2026

The failure mode isn't technical. It's organizational. Most enterprises skip the operating model and jump straight to tooling — then wonder why nothing scales past the pilot.

Read

The AI Center of Excellence Is Dead. Long Live the AI Operating Model.

November 2025

Centers of Excellence centralize capability. Operating models distribute it. The difference determines whether AI scales or stalls at the enterprise level.

Read

Why I Chose Regulated AI Over Startup Speed

August 2021

After three years building AI at a startup, I moved to a global bank. Not despite the constraints — because of them. Regulated environments are where AI gets hardest and most valuable.

Read

Data Architecture

Why We Chose dbt Over BigQuery Dataform

2026

JavaScript supply chain risk, SQL-first philosophy, multi-warehouse portability, and what actually matters when choosing a transformation framework in a regulated enterprise.

Read

Data Vault 2.0 in Banking: Architecture for the Audit That Hasn't Happened Yet

2026

Why insert-only modeling, hash keys, and full lineage aren't academic exercises — they're survival patterns in regulated environments where every record must be defensible.

Read

Building Data Foundations While Everyone Chased Models

March 2022

The industry is obsessed with models. Meanwhile, the actual bottleneck for enterprise AI is data infrastructure — Data Vault 2.0, BCBS 239, lineage, and the unsexy work that makes everything else possible.

Read

NLP & Machine Learning

We Switched to PyTorch in 2020. Was It the Right Call?

October 2024

Four years after switching from TensorFlow to PyTorch during the pandemic — what happened to TF, why PyTorch won, and why inference engines like vLLM matter more than training frameworks now.

Read

RAG in Production: What Breaks When You Move Past the Tutorial

June 2024

Every RAG tutorial works. Then you move to production and discover that chunking strategy matters more than embedding models, retrieval quality matters more than generation, and evaluation is the hardest problem.

Read

Switching from TensorFlow to PyTorch — A Practical Assessment

June 2020

We switched our NLP projects from TensorFlow 1.x to PyTorch mid-pandemic. Eager execution, HuggingFace, debugging, and what we gave up. A practical framework comparison for a small team.

Read

Building NLP Pipelines Before Transformers Were Easy

June 2019

What production NER actually looks like: BiLSTM-CRF, character embeddings, gazetteers, and the pipeline engineering that matters more than the model. Lessons from building NLP systems at a startup.

Read

Attention Is All You Need — A Practitioner's Guide to the Transformer

September 2018

Breaking down the paper that replaced RNNs, LSTMs, and sequence-to-sequence models with a single mechanism: attention. What the Transformer does, why it works, and why it matters.

Read

Classifying 7,000 Product Codes from Four Words of Text

August 2018

Comparing LSTM, BiLSTM, GRU, CNN, and hybrid architectures for HS code classification from short product descriptions. What worked, what didn't, and why CNNs beat RNNs on short text.

Read