Engineering notes and research.

I write about AI agent architectures, distributed systems, and the tools that connect them. Currently building at Microsoft.

Recent Writing

AI AgentsHITLGovernanceSeriesSep 26, 2026

The road ahead: What evidence would justify more autonomy?

Before removing an approval step, ask what evidence would justify the change, what the trial cannot show, and what would reverse the decision.

AI AgentsHITLOperationsSeriesSep 26, 2026

Incident resolution with AI: A hypothetical reference design

A fictional incident workflow follows an AI-assisted rollback from alert to verified recovery, with explicit authority, handoff, and failure constraints.

AI AgentsHITLEngineeringSeriesSep 26, 2026

From vibe coding to verified: Practising independent diagnosis

A proposal for practising independent diagnosis in AI-assisted engineering, with synthetic exercises and tests of whether the learning transfers.

AI AgentsHITLSecuritySeriesSep 26, 2026

What sleeper agents mean for production AI systems

Sleeper-agent experiments show why cleaner evaluations do not prove harmful behaviour is gone, and why production checks need independent evidence.

Seriesarchitecturedecision-frameworkSep 26, 2026

Designing Decision Boundaries for AI Autonomy

How to turn autonomy policy into testable action conditions, using a hypothetical booking service to examine consent, reversibility, retries, and the cost of delay.

Seriesreliabilityfailure-modesSep 26, 2026

Five Ways to Question an AI Agent's Success

A proposed review framework for checking an agent's diagnosis, scope, lasting outcome, downstream effects, and context freshness beyond a successful tool call.

SeriesgovernanceorganizationalSep 26, 2026

AI Governance Needs Shared Rules and Different Controls

How to keep shared AI governance rules while tailoring controls to each use, with explicit ownership, testable evidence, and reassessment when permissions change.

SerieseconomicsroigovernanceSep 26, 2026

When Human Oversight Pays for Itself

A practical cost model for human review, with a hypothetical payback calculation, sensitivity checks, and cases where oversight does not break even.

Seriessecuritysupply-chainSep 26, 2026

Your AI Agent's Skills Might Be Malware

What the ToxicSkills audit found, what its numbers do not prove, and how to limit the damage from a compromised agent skill.

SeriesarchitecturegovernanceautonomySep 24, 2026

Graduated Automation: How to Scale AI Without Losing Control

How a procedure earns permission to act: scoped approvals, independent checks, and withdrawing autonomy when conditions change.

Seriescode-qualitytechnical-debtSep 23, 2026

The Hidden Debt in AI-Generated Code

What public studies reveal about persistent code-quality issues, the limits of AI-versus-human comparisons, and reviewing architectural change.

Seriescognitive-scienceresearchSep 22, 2026

AI and critical thinking: What the research actually shows

What an EEG experiment, a knowledge-worker survey, and a perspective paper tell us about AI, critical thinking, and meaningful human oversight.

SeriesJul 2026

The Amplification Thesis

Human alone and AI alone score about the same. Human plus AI wins. An animated case for amplification over replacement.

SeriesJul 2026

AI Comes for the Grunt Work, Not the Judgment

The accountant already answered what happens to a job when the machine arrives. A scrollytelling essay on AI, work, and the bubble question.

SeriesHITLJul 2026

Why Human-in-the-Loop is Not Optional for Production AI Agents

The six-pillar argument for why HITL is not a transitional compromise but a structural requirement of any production AI system.

PaperJun 2026

Decentralized Granular Access Control for Agentic AI Systems

Multi-layered access control architecture for agentic AI in critical cloud infrastructure.

PaperJun 2026

The Case for Human-in-the-Loop: A Six-Pillar Framework

53 research papers argue HITL is a structural requirement of any production AI system.

SecurityApr 2026

Zero Trust in Azure: Strategies for Securing Cloud Infrastructure

Seven practical strategies covering NSGs, Private Links, Azure Policies, AVNM.

PaperJun 2026

Autonomous Incident Resolution at Hyperscale

Multi-agent orchestration for autonomous network incident resolution with safety guarantees.

PaperJun 2026

From Reactive to Autonomous: Evolution of AI Operations

Five-generation maturity model from manual troubleshooting to autonomous resolution.

ResearchJun 2026

MCP vs CLI: Comparative Analysis of AI Agent Tooling

Complementary transport layers evaluated across 14 dimensions with benchmarks.

View all writing →

Explore Series

9 partsIn Progress

AI as Human Amplifier vs Replacement

13 of 13 publishedComplete

Strategic HITL for Production AI Agents

SecurityIn Progress

Cloud Security

View all series →