Writing
I write about diplomacy, technology, and the organizations that connect them. Practitioner notes, not commentary.
-
Back to the Analog: AI and the Future of Public Diplomacy
A conversation on Public Diplomacy Examined (IPDGC, GW) about what AI changes in diplomacy — and what it makes more valuable than ever.
-
What is "AI-Powered Diplomacy" anyway?
I just finished Dan Spokojny’s great article “Should Diplomats Trust AI?” The piece is anchored by two new items: the recent Foreign Service Journal issue that focused heavily on AI (which I contributed to), as well as the December 2025 AI-Powered Diplomacy paper from the Pavel Slunkin writing at the Belfer Center. Dan expresses skepticism about the claims in the Belfer study, as well as the broad claims that AI has the potential to render diplomats irrelevant or obsolete. I generally agree wi
-
You Got Promoted. Now What? An Adaptive Leadership Guide to Career Transition
The skills that got you promoted are often the ones that will undermine you next. This is a guide to the three career transitions that change what effectiveness means — from individual contributor to manager, from manager to leader of leaders, and the inner work that makes the difference.
-
Why your weekly 1:1 has compounding benefits
I was about seven years into my career before I had a manager who did regular 1:1s with me, not the quarterly check-ins or annual reviews I was used to, but actual recurring conversations about work, about thinking, about how things were going. About four months in, we were taking a walk on the National Mall, talking about something I'd done that had rubbed several colleagues the wrong way, enough that they'd complained to my boss. I hadn't done anything wrong, exactly. I'd done what I was supp
-
Claude Code and Antigravity for Federal Practitioners: One Vault with Two Tools
DoW designated Anthropic a supply-chain risk. If you built workflows around Claude Code, here's how to protect your investment by running two AI tools against one shared vault.
-
Claude Code Alternatives for Federal Practitioners: AI Work That Outlasts Any Vendor
The DoW designated Anthropic a supply-chain risk. If you built workflows around Claude Code, here's how to protect your investment with portable, vendor-agnostic AI setups.
-
Identic AI: Why Personalized Agents Are the Next Layer of Enterprise AI
Enterprise AI doesn't have to repeat the oldest mistake in IT. A three-layer model — shared data, standardized skills, and personalized agents — lets organizations amplify individual judgment instead of standardizing it away. The technology exists today.
-
Themes Are Not Feedback
Feedback built on aggregated impressions — "multiple people have raised concerns" — strips away everything that makes feedback useful. The research is clear: effective feedback is specific, actionable, and timely.
-
What Works on LinkedIn (And Why)
Most LinkedIn advice falls into one of two categories: tactical tricks that aim to game the system or vague encouragement to "post consistently and engage authentically." Neither helps you understand how the platform actually works, which is what you need to make good decisions about your own strategy. This is my attempt to explain the mechanics and the principles behind LinkedIn distribution (as of early 2026), so you can build something authentic that works for your specific goals rather than
-
Document Feedback Reference Sheet
For the reasoning behind this system, see Why Feedback Order Matters: A System for Document Review. The Three Tiers TierScopeAddressExamplesHigher Order (HOC)Whole documentFirstArgument, structure, purpose, audience fit, completenessMiddle Order (MOC)Sections/paragraphsSecondTransitions, evidence integration, tone, proportionalityLower Order (LOC)Sentences/wordsLastGrammar, spelling, word choice, formatting The core rule: Always work top-down. Don't polish what might move. Higher Order
-
Why Feedback Order Matters: A System for Document Review
Bad document feedback was the bane of my existence at the State Department. (We always talked about "happy to glad" changes). You've probably seen this happen. Someone sends a draft for review. The first reviewer opens it, spots a comma splice on page one, fixes it, notices an awkward phrase on page two, rewrites it, flags a structural problem on page three, catches another typo, and drops a comment at the bottom of the document that says that the paper missed the original intent and probably ne
-
How to Make your LinkedIn Profile Sing - 360Brew Edition
LinkedIn's algorithm has never been intuitive for users of other social media platforms: from its preference for once-a-day posting to how it values different forms of engagement. This got even more complicated in late 2025, when LinkedIn launched the 360Brew algorithm, a 150-billion parameter language model that reads your content semantically instead of just counting clicks. This new AI-driven recommendation system promises to understand what you write, not just how many people react to it. It
-
Getting Started with Claude Code: Building a Personalized AI System
Every conversation with AI starts from scratch. This tutorial builds the system that fixes that — persistent context, project memory, and a personal vault that makes each session smarter than the last. Built for diplomats, analysts, and federal professionals who need more than a chatbot.
-
How to Build a Secure AI Agent Setup (The OpenClaw Alternative)
This guide walks you through setting up an AI agent with persistent memory, modular skills, tool integration, and task automation, without exposing endpoints to the internet. Time required: ~2 hours Difficulty: Comfortable creating folders and text files; some terminal use helpful but not required Prerequisites: macOS/Windows/Linux, Anthropic API key or Claude Pro subscription What you'll have when done: * AI that remembers context across sessions * Custom skills triggered by simple phrases
-
Getting Started with GenAI.mil - Dec 2025 Edition
Two weeks ago, the Pentagon put Google's Gemini for Government on the desktops of 3 million military personnel, civilians, and contractors. If you have a CAC, you now have access to a frontier AI model cleared to handle CUI. Most people will poke at it a few times, get underwhelming results, and move on. This isn't because the tool is bad. It's because talking to AI is a skill, and nobody taught you how to do it. It's kind of like getting handed a professional camera. Point it at something and
-
Seven Steps to Move Teams from Chaos to Coordination
This is for teams who know their coordination is a mess but don't have the energy for another change initiative. If you've been putting off "fixing how we track work" because it sounds exhausting, this is the smallest-possible-steps version. You can feel the problem. Tasks live in people's heads. Three people are working on the same thing without knowing it. Someone's blocked waiting on a deliverable that nobody realized was assigned, or reassigned. A critical project exists only in the mind of
-
Nemawashi: The Coalition-Building Practice That Makes Change Stick
If you've worked in consulting or government transformation, you've probably encountered kaizen - Toyota's continuous improvement philosophy that revolutionized manufacturing. You might know the Lean methodology it spawned. But there's a less famous Japanese management practice that may matter more for organizational change: nemawashi. What Nemawashi Actually Means Nemawashi translates literally as "going around the roots." It's a gardening term describing the careful preparatory work done
-
Prompt: Reputation Audit
We all sometimes need to check up on what is published about us (or a friend, colleague, or potential partner) online. While you can certainly ask Claude or another LLM to do your research, it will work far better if you tell it exactly what you are after... Wayan Vota developed his original prompt back in summer 2025. After using his for a while, I adapted my own, iterating to add some of the things I needed that were missing. Full prompt is after the break – available for those who have signe
-
Linkedin Replaced Its Algorithm and It Rewards Substance
I've always loved LinkedIn as a content platform. Not ironically. I know that's an unfashionable opinion. The site gets mocked for performative thought leadership and quasi-work-related trash. But I find the platform hugely valuable for discovering new thoughtful people and for sharing my own insights about work-related stuff. I've built professional relationships through content here that never would have happened otherwise, including more than a few Linkedin connections that have turned into r
-
How AI Actually "Knows" Things
A practical guide for getting more out of Claude and ChatGPT (and written based on conversations last week!) There's a counterintuitive truth about working with AI that took me a while to internalize: more isn't better. Not more training data, not more context, not more conversation history. The models that perform best on specific tasks are often trained on carefully curated, focused datasets. And the conversations that produce the most useful outputs are ones where I've been deliberate about
-
How to Stop Wasting Hours on Slides: A Step-by-Step Guide to MARP
I spent three hours last Tuesday fighting with PowerPoint over text box alignment. Three hours. This is absurd, and we all know it. But most of the "AI solutions" aren't actually solving the problem. They're trying to help you think, communicate, and format all at once, which means they do a mediocre job of all three while charging you $40 a month for the privilege. There's a better way. It's called MARP, it's free, it runs locally on your computer, and you don't need to be particularly techni
-
From 48KB to 5KB: Rebuilding My AI Assistant's architecture to better manage context
Last weekend, I rebuilt my Claude PKM system. Not because it was broken—it was working perfectly fine. But "working" and "optimal" are two very different standards, especially when you're scaling AI collaboration across an organization. Over the past month, my Claude system had grown to 48KB of instructions. Every interaction loaded my entire professional context, voice guide, technical specifications, and decision frameworks—whether Claude needed them or not. It was like requiring every employ
-
Building a PKM with Obsidian and Claude: A Practical Guide
What This Is: A real-world guide to building a personal knowledge management system that actually works with AI and turns Claude from a chatbot into a genuine thought partner. The Real Problem I'm constantly synthesizing research, connecting patterns across projects, and developing frameworks that integrate insights from multiple domains. The challenge lies in building deeper knowledge - understanding what information means, how ideas connect, and what implications emerge from those connectio
-
BCL Bot v0.1: An AI Briefing Checklist Drafter
Briefing Checklists are a time-consume bane for many U.S. diplomatic staff. What if we could automate them? This has been the dream for many of us for a long time, but we've finally got the tools to do a first pass at a BCL very well. Over the last week, I've been tinkering with a System Instruction for Claude and ChatGPT that can easily take out some of the initial drafting. You give it some basic information, it'll go research topics and give you a (mostly) formatted brief. While I have many
-
Where to start with AI as a Diplomat? - September 2025 Edition
AI continues to grow at a dizzying pace. This beginner's guide helps diplomats get familiar with AI tools, regardless of their current proficiency.
-
Making Sense of Complexity: How Diplomats Can Use the Cynefin Framework
The Cynefin framework offers a diagnostic tool that helps leaders and teams recognize which type of challenge they face and select appropriate strategies for each context.
-
Understanding Loss Triggers In Change Management with SCARF
The SCARF framework identifies five key domains that trigger either threat or reward responses in the brain during periods of change and transition.
-
Expo Osaka 2025: Spain's Pavilion
First-hand review of Spain’s pavilion at Expo 2025 Osaka—design, audience, programming, partnerships, and takeaways, with photos from the visit.
-
28 Core Competencies for Public Diplomacy Success
The 28 core competencies for public diplomacy across five elements—policy, audiences, planning, management, and learning—to guide practitioner growth.
-
What is a McLuhan Tetrad, and how do you use it?
What is a media tetrad or a McLuhan Tetrad?
-
Understanding PD Foundations: Modern Diplomatic Tradecraft
How developing PD Foundations at the State Department created a systematized diplomatic tradecraft and gave practitioners a unified framework for excellence.
-
What Makes a Good Expo Pavilion?
This post focuses on what makes a good Expo pavilion, introducing a simple analysis framework and then diving in with a favorite example from Expo Dubai 2020.
-
Shaping LLM Responses: A Guide for Modern Diplomats
What are the best ways for modern diplomats to shape LLM prompts in ChatGPT, Claude, and other tools?
-
Audience Segmentation and Data Analysis
Audience segmentation is the practice of dividing broad stakeholder groups into smaller, more homogeneous segments that can be engaged more effectively through targeted approaches.
-
Expo 2025 Pavilions: An Index of Reviews
Browse an index of Expo 2025 Osaka pavilion reviews—with a simple evaluation framework and links to detailed write-ups like Spain.
-
Is this a Project or a CustomGPT?
When should you use Claude projects, ChatGPT customGPTs, and ChatGPT projects? Differentiating is a key to your success.
-
At the Crossroads of Tradition and Innovation with AI
Making AI work for diplomats at the State Department requires challenging the culture that underlies the department’s siloed structure.
I send new essays and exhibits as they ship. Add a note if you want to start a conversation.