Blog

Deep dives into data governance, AI, architecture, and engineering.

AI Products & Strategy April 19, 2026 · 17 min read

Gemma 4, Decoded: Why Google Released It Free and How It Actually Works

Google released Gemma 4 under Apache 2.0 on April 2, 2026. The license change is the real story, not the benchmarks. This is the three-tier framework for 'open' AI (closed, open-weight, open-source), a technical breakdown of how Gemma 4's MoE and multimodal pipeline work, and a practitioner decision flow for picking the right tier.

#gemma-4#open-weight#open-source#ai-strategy

AI Governance & Safety April 11, 2026 · 10 min read

Part 8 of 10 · Data Privacy Guide

Mathematical Privacy Guarantees: Differential Privacy and Synthetic Data

Part 6 showed Meridian adopting differential privacy for query analytics. This article explains why: what epsilon means, how noise is calibrated, what Apple and the Census Bureau chose, and when to use synthetic data instead.

#data-governance#data-privacy#data-protection#privacy-engineering

AI Governance & Safety April 11, 2026 · 12 min read

Part 9 of 10 · Data Privacy Guide

Privacy-Preserving Computation: Encrypted Processing, Federated Learning, and the Explainability Paradox

Part 6 showed Meridian rejecting federated learning (single-tenant architecture) and deferring homomorphic encryption (47x latency). This article explains the mechanics behind those decisions, introduces secure multi-party computation, and reveals the tension between GDPR's explainability mandate and privacy protection. Concludes with a capstone PET decision framework spanning Parts 7 through 9.

#data-governance#data-privacy#data-protection#privacy-engineering

AI Governance & Safety April 11, 2026 · 9 min read

Part 7 of 10 · Data Privacy Guide

Privacy-Enhancing Technologies: Masking, Tokenization, and De-identification

Part 3 introduced PETs as governance decisions. Part 6 showed Meridian evaluating them. This article explains how each technique actually works: static and dynamic masking, vault-based and format-preserving tokenization, and the k-anonymity family of de-identification methods.

#data-governance#data-privacy#data-protection#privacy-engineering

AI Governance & Safety April 11, 2026 · 7 min read

The Benchmark Illusion: Why Passing Safety Tests Means Almost Nothing

A study of 32 models across 56 jailbreak techniques found attack success rates jumping from 0.6% to 96.3% depending on the attack type. The Safety Tax costs 7-31% accuracy. Ten alignment techniques are competing to solve this. None covers the full attack surface.

#ai-governance#ai-safety#llm-alignment#model-risk

AI Governance & Safety April 11, 2026 · 7 min read

The $0.20 Jailbreak: Why LLM Safety Alignment Is Shallow

Fine-tuning GPT-3.5 on 10 examples for $0.20 strips its safety guardrails. Removing safety from Llama 3 takes 5 minutes on one GPU. This article explains the mechanism: safety alignment concentrates in the first few output tokens, creating a shallow defense that fine-tuning, prefilling attacks, and adversarial suffixes bypass trivially.

#ai-governance#ai-safety#llm-alignment#model-risk

AI Governance & Safety April 11, 2026 · 8 min read

LLM Safety After Fine-Tuning: Governance, Regulation, and What To Do

The EU AI Act makes you responsible for safety when you fine-tune. Reasoning models can autonomously jailbreak other models at 97% success. Half of organizations have no formal AI guardrails. This article provides the regulatory map, the liability analysis, and a minimum viable safety governance checklist.

#ai-governance#ai-safety#model-risk#eu-ai-act

AI Products & Strategy April 4, 2026 · 7 min read

Willison's Agentic Engineering Patterns: What Data Practitioners Should Steal

Bad code crashes visibly. Bad data looks plausible. That asymmetry makes agent-assisted data work riskier than software, and it is why Simon Willison's Agentic Engineering Patterns guide matters for data practitioners. His Red/Green TDD maps to data contracts before transformation. His testing discipline gives teams a framework for agent verification. But some patterns need adaptation: 'pipelines are cheap' is only half true, and hoarding knowledge is harder when institutional context lives in people's heads, not in code.

#agentic-engineering#coding-agents#data-quality#judgment-in-the-loop

AI Governance & Safety April 4, 2026 · 14 min read

Context Engineering, Formalized: Five Criteria That Validate the Agent Quality Thesis

Vishnyakova's 'Context Engineering' paper (arXiv 2603.09619) proposes five production-grade quality criteria for agent context and a four-level maturity pyramid. The framework independently validates the thesis from our three-part agent quality series and extends it with Isolation, Economy, and two higher-order disciplines: Intent Engineering and Specification Engineering.

#context-engineering#ai-agents#data-quality#ai-governance

AI Governance & Safety April 4, 2026 · 7 min read

Overview · Data Privacy Guide

The Data Privacy Practitioner's Guide

A ten-part series from teardown to framework to implementation. Two company analyses (Netflix, Apple), an 8-component privacy program framework, the 2026 regulatory landscape, a complete implementation walkthrough using a fictitious B2B SaaS company, a three-part deep dive into Privacy-Enhancing Technologies, and a synthesis of what it all means for practitioners.

#data-privacy#data-governance#gdpr#ai-governance

AI Governance & Safety April 4, 2026 · 8 min read

Part 10 of 10 · Data Privacy Guide

What This Series Taught Me About Privacy

The conclusion to the Data Privacy series. Two company teardowns, a framework, a regulatory map, two implementation walkthroughs, and a three-part deep dive into Privacy-Enhancing Technologies. Here is what surprised me, what I got wrong, and what practitioners should do next.

#data-privacy#data-governance#gdpr#ai-governance

AI Governance & Safety April 4, 2026 · 23 min read

Part 5 of 10 · Data Privacy Guide

Privacy in Practice: Diagnosing the Gaps and Building the Foundation

A fictitious B2B SaaS company receives a DPIA request it cannot answer. This walkthrough applies the privacy framework from Part 3 to build Data Classification, retention schedules, consent architecture, and sub-processor transparency from scratch.

#data-privacy#data-governance#privacy-engineering#ai-governance

AI Governance & Safety April 4, 2026 · 17 min read

Part 6 of 10 · Data Privacy Guide

Privacy in Practice: From Compliant to Operationally Ready

Meridian Analytics completes its privacy transformation. This walkthrough covers cross-border transfer documentation, EU AI Act compliance mapping, PET assessments, the governance operating model, and what the company looks like six months later when Allianz asks the same DPIA questions.

#data-privacy#data-governance#privacy-engineering#ai-governance

AI Products & Strategy April 4, 2026 · 8 min read

Part 10 of 12 · Guide to AI Agents

Multi-Agent Systems: When One Agent Isn't Enough

Nine articles in this series used a single agent. This one explains when that stops being sufficient and what to do about it. Four signals tell you it is time. Three patterns handle 90% of cases. The hardest part is not building the system; it is debugging it when something goes wrong.

#ai-agents#multi-agent-systems#agent-orchestration#agent-architecture

AI Products & Strategy April 2, 2026 · 12 min read

The Evolution of AI Agents: From AutoGPT to Production (2023-2026)

A practitioner's timeline of how AI agents evolved from viral GitHub demos to production infrastructure in three years. The hype, the correction, the protocols, and the lessons that survived.

#ai-agents#agent-evolution#agentic-engineering#agent-architecture

AI Products & Strategy April 1, 2026 · 14 min read

Part 5 of 12 · Guide to AI Agents

Prompt Engineering for Production Agents

Production agents need prompts that produce consistent, structured output under adversarial conditions. This article covers the five patterns that separate production prompt engineering from tutorial-grade prompting: explicit criteria, few-shot examples, nullable fields, enum-with-fallback, and output format contracts.

#ai-agents#prompt-engineering#structured-output#tool-calling

AI Products & Strategy April 1, 2026 · 12 min read

Part 9 of 12 · Guide to AI Agents

Observability: Seeing What Your Agent Actually Does

Your monitoring says 200 OK. The agent returned the wrong answer. Traditional APM was designed for deterministic software. Agents reason, branch, and call tools in sequences they decide at runtime. This article covers the five dimensions of agent observability, the tooling landscape, and a practical instrumentation plan.

#ai-agents#agent-observability#monitoring#data-observability

AI Governance & Safety March 25, 2026 · 16 min read

Part 6 of 12 · Guide to AI Agents

Context Is the Program: Why Data Quality Inside the Agent Matters More Than the Model

Pike's Rule 5 says data dominates. In AI agents, the context window IS the data structure. This article traces why context quality determines agent behavior more than model capability, maps the five criteria that define good context, and shows what happens when stale data enters the reasoning loop unchecked.

#ai-agents#context-engineering#data-quality#ai-governance

AI Governance & Safety March 25, 2026 · 15 min read

Part 8 of 12 · Guide to AI Agents

Guardrails and Safety: The Boundaries Every Agent Needs

Pike's Rule 4 says fancy algorithms are buggier. In agent systems, complexity multiplies failure surfaces. This article maps the three guardrail layers every agent needs, identifies the gap most frameworks miss, covers escalation patterns and workflow gates, and explains why simpler architectures are safer.

#ai-agents#ai-governance#agent-safety#guardrails

AI Governance & Safety March 25, 2026 · 13 min read

Part 7 of 12 · Guide to AI Agents

Evals: How to Know If Your Agent Actually Works

Most agent teams ship without evals and rely on 'looks right' testing. Pike's first two rules apply directly: you cannot tell where an agent fails, and you cannot fix what you have not measured. Here is how to build an eval strategy that catches what demos miss.

#ai-agents#evals#ai-governance#agent-safety

AI Products & Strategy March 25, 2026 · 8 min read

Part 3 of 12 · Guide to AI Agents

Pike's Five Rules Are Now the Five Rules of Agent Development

Rob Pike wrote five rules of programming in 1989 at Bell Labs. Thirty-seven years later, they map onto AI agent development with striking precision: measure before tuning, start simple, and get the data right. Nobody has made this connection explicitly. Here is the mapping, the evidence, and the framework it gives you.

#ai-agents#agent-development#context-engineering#agentic-engineering

AI Products & Strategy March 25, 2026 · 15 min read

Part 11 of 12 · Guide to AI Agents

The Self-Improving Agent: From Static Prompts to Learning Systems

Most AI agents run the same prompt every time. The best ones evolve. This article maps the spectrum from static to self-improving agents, introduces the inner loop / outer loop architecture, and walks through a real system that learns from feedback weekly. Pike's Rules 3-4 set the boundary: start simple, add complexity only when measurement demands it.

#ai-agents#self-improving-agents#agentic-engineering#learning-systems

AI Products & Strategy March 25, 2026 · 11 min read

Part 1 of 12 · Guide to AI Agents

What Is an AI Agent (and What Isn't)?

An AI agent is a system that uses an LLM to decide which actions to take in a loop until a goal is met. This article breaks down the four components every agent shares, the spectrum from chatbot to autonomous agent, what tool calling actually looks like in code, and the design principles that separate good tool definitions from bad ones.

#ai-agents#agent-architecture#tool-calling#ai-fundamentals

AI Products & Strategy March 25, 2026 · 4 min read

Overview · Guide to AI Agents

The Practitioner's Guide to AI Agents

A twelve-part series that takes you from 'what is an agent?' to building self-improving systems. Pick your starting point based on where you are today.

#ai-agents#series-guide#agent-architecture#ai-fundamentals

AI Products & Strategy March 25, 2026 · 18 min read

Part 4 of 12 · Guide to AI Agents

Build a Real Agent This Weekend: From Zero to a Working Research Assistant

The series has defined agents, established design principles, and mapped failure modes. This article builds one. A complete research assistant agent with three tools, structured error handling with error categories and retry logic, context management, and a basic eval, all in one runnable Python file using the Anthropic SDK.

#ai-agents#agent-development#tool-calling#anthropic-sdk

AI Products & Strategy March 25, 2026 · 17 min read

Part 12 of 12 · Guide to AI Agents

From Problem to Agent: An Implementation Reference Guide

The series taught ten concepts across ten articles. This capstone walks through all of them applied to one problem: building a Data Quality monitoring agent. Seven steps, from problem definition through production deployment, showing the decision-making process that separates agent projects that ship from agent projects that stall.

#ai-agents#data-quality#implementation-guide#context-engineering

AI Products & Strategy March 25, 2026 · 10 min read

Part 2 of 12 · Guide to AI Agents

When NOT to Build an Agent

Not every problem needs an AI agent. This article gives you a decision framework for when agents are the wrong choice, with a comparison table, anti-patterns, and the Klarna case study that proves the cost of over-engineering.

#ai-agents#agent-architecture#decision-framework#ai-strategy

AI Products & Strategy March 24, 2026 · 7 min read

From Vibe Coding to Agentic Engineering: What Karpathy's Shift Means for Data Work

Andrej Karpathy hasn't written a line of code since December. His 80/20 flip from manual coding to agent orchestration is not a personal anecdote. It is the clearest signal yet that the value in data and AI work has shifted from execution to judgment.

#ai-agents#agentic-engineering#context-engineering#coding-agents

AI Governance & Safety March 21, 2026 · 11 min read

Your AI Agent Has a Data Quality Problem and No One Is Checking

AI agents trust every tool response they receive, with no standardized quality controls between tool-calling outputs and LLM reasoning. This article maps the 6 traditional Data Quality dimensions onto the context window, exposing the most consequential unmonitored data pipeline in enterprise AI.

#ai-agents#data-quality#context-window#ai-governance

AI Governance & Safety March 21, 2026 · 10 min read

Judgment-in-the-Loop: The Human Role AI Cannot Automate

Everyone talks about keeping a human in the loop. But which human, and what do they bring? The answer is judgment: domain knowledge, institutional memory, and the ability to recognize when AI output looks right but is wrong. This article defines that role and the evidence behind it.

#ai-governance#judgment-in-the-loop#human-ai-collaboration#data-quality

AI Governance & Safety March 21, 2026 · 10 min read

The Missing Data Quality Layer in AI Agent Architecture

AI agent architectures have quality checks for input safety and output toxicity, but no standardized layer validates whether tool-calling results are accurate before they enter the context window. Here is what that missing layer should look like.

#ai-agents#data-quality#context-engineering#ai-architecture

Data Governance & Management March 21, 2026 · 4 min read

Welcome to The Data Praxis

Why this blog exists, what it covers, and where to start. The Data Praxis bridges the gap between what Data Governance frameworks promise in conference talks and what actually works when you build these systems at scale.

#data-governance#data-architecture#ai-governance#data-privacy

Data Governance & Management March 18, 2026 · 24 min read

Part 4 of 10 · Data Privacy Guide

The Data Privacy Regulatory Landscape in 2026: GDPR, CCPA, AI Laws, and the Insurance Market for When AI Goes Wrong

A practitioner's reference to the global privacy regulatory landscape. GDPR fines have crossed EUR 5.6 billion. Twenty US states have privacy laws with no federal standard. The EU AI Act is phasing in. And a new insurance market is emerging for AI agents that go off script. This is where the rules stand, what they require, and what is coming next.

#data-privacy#data-governance#gdpr#ccpa

Data Governance & Management March 17, 2026 · 20 min read

Part 3 of 10 · Data Privacy Guide

How to Build a Privacy Program in the Age of AI

A practitioner's framework for building a privacy program that treats AI data as a first-class concern. Covers Data Classification for training data, retention schedules for ML pipelines, consent architecture, third-party transparency, cross-border transfers, EU AI Act Article 10, NIST AI RMF, privacy-enhancing technologies, and governance operating models.

#data-privacy#data-governance#ai-governance#eu-ai-act

Data Governance & Management March 16, 2026 · 15 min read

Part 2 of 10 · Data Privacy Guide

Apple Privacy Teardown: When Privacy Is the Product, Where Does It Break Down?

A Data Governance teardown of Apple's privacy practices. What Apple actually collects, how hardware margins fund privacy positioning, where Apple falls short on Siri, China, and its own ad network, and what practitioners can learn from privacy as a business strategy.

#data-privacy#data-governance#apple#app-tracking-transparency

Data Governance & Management March 14, 2026 · 14 min read

Part 1 of 10 · Data Privacy Guide

Netflix Privacy Policy Teardown: What 325 Million Subscribers Actually Agreed To

A Data Governance teardown of Netflix's privacy policy. What they collect, who they share it with, how they compare to Apple TV+, what the €4.75M GDPR fine revealed, and what practitioners can learn from how Netflix structures its data practices.

#data-privacy#data-governance#gdpr#ccpa

AI Governance & Safety March 13, 2026 · 6 min read

Harness Engineering: The Real Lesson from OpenAI's Million-Line Experiment

OpenAI built a million-line product in five months without writing code manually. Most coverage focused on the spectacle. The real insight is that harness engineering principles apply to every team building products today, with or without AI agents.

#harness-engineering#ai-agents#engineering-practices#code-quality

Metadata & Data Quality March 13, 2026 · 23 min read

Metadata Management in 2026: Why Lineage Without Context Is Just Expensive Decoration

Why most Metadata Management investments deliver lineage graphs nobody uses, and what an actionable metadata strategy actually looks like in 2026.

#metadata-management#data-lineage#data-catalog#active-metadata

Industry Teardowns February 23, 2026 · 14 min read

Netflix Got the Hard Parts Right: A Teardown of Their LLM Post-Training Framework

Netflix published a detailed article on scaling LLM post-training. Here is what they built, what the engineering decisions reveal, what five peer companies are doing differently, and five open questions I would love their team to answer next.

#llm-fine-tuning#post-training#netflix#ml-infrastructure

AI Governance & Safety February 18, 2026 · 9 min read

AI Governance Is Not AI Ethics: A Practical Framework for Enterprise AI Oversight

A practical framework for enterprise AI Governance that maps NIST AI RMF, EU AI Act risk tiers, and SR 11-7 into a unified operating model with clear decision rights, risk classification, validation processes, and monitoring capabilities.

#ai-governance#nist-ai-rmf#eu-ai-act#model-risk-management

Industry Teardowns February 15, 2026 · 11 min read

Breaking Down Uber's Data Quality Platform: What Works, What Doesn't, and What It Means for the Rest of Us

A critical analysis of Uber's five-system Data Quality ecosystem -- DQM, D3, UDQ, Databook, and DataCentral -- examining what is genuinely innovative, what is standard practice in disguise, and which patterns are worth adopting at any scale.

#data-quality#uber#data-observability#DQM

Data Governance & Management February 12, 2026 · 9 min read

The Data Governance Maturity Model Most Organizations Get Wrong (And a Practical Alternative)

Why dominant Data Governance maturity models like CMMI DMM, DCAM, and Gartner measure documentation completeness instead of governance effectiveness, and a practical outcome-driven framework built around decision rights, Data Literacy, and measurable business impact.

#data-governance#maturity-model#CMMI-DMM#DCAM