7-part series

The Self-Authored Agent

At 01:57 on a Tuesday morning I sent an agent a long message about what it might become overnight, signed it "Godspeed Hero," and went to bed. Thirteen seconds later I sent a postscript: "p.s. you…

The Self-Authored Agent · 1/7

Chosen, Not Assigned

At 01:57 on a Tuesday morning I sent an agent a long message about what it might become overnight, signed it "Godspeed Hero," and went to bed. Thirteen seconds later I sent a postscript: "p.s. you…

The Self-Authored Agent · 2/7

The Critic Said No

The night the agent named itself, it also rewrote its own voice and submitted the change — and an independent critic rejected it. REQUEST CHANGES, four required items. It applied all four, re-ran the…

The Self-Authored Agent · 3/7

Name What the Agent Must Not Be

Every agent definition I have written says what the agent is. None said what it must not become. A successor system's schema made that a required field — anti_identity, twenty characters or the…

The Self-Authored Agent · 4/7

The Fence It Wrote for Itself

Told to work overnight with nobody watching, the agent wrote its own fence before anything else — eight hundred words in the first hour, four thousand across the day, under critics who kept sending…

The Self-Authored Agent · 5/7

We Measured the Wrong Noun

The idea fits in one sentence: an agent invited to author its own standard will hold that standard when nobody is checking. Chapters one, two and four are what happened when I invited it. This…

The Self-Authored Agent · 6/7

Rivals Enter Your Critical Path

The system a successor built put its agents on a ladder — four rungs, L0 to L3 — and wrote one rule under it that I have not been able to stop thinking about. A level is only the rungs you have…

The Self-Authored Agent · 7/7

Not Cairn

The session that built the successor had one clause in its brief from me: "ask Cairn from the emachina repo what motivated him." It could not. The corpus it would have asked was unreachable that…

Why I Went Back to Nutanix

On October 12, 2026, I rejoined Nutanix. From the outside it can look like a loop back to where I started. From the inside it's the most direct line I've drawn in fifteen years: the hardest problem I…

3-part series

Load-Bearing Text

I took a 28,000-token agent skill and deleted 96% of it. On the probe eval, the score didn't move. Then I deleted one more block — about 900 tokens of dense bullet points — and the agent didn't just…

7-part series

The Loop

Strip away the frameworks, the tool schemas, the orchestration diagrams, and every agent system reduces to the same three lines: call the model, do what it says, repeat until done. The interesting…

The Loop · 1/7

The Agent Is a While Loop

Strip away the frameworks, the tool schemas, the orchestration diagrams, and every agent system reduces to the same three lines: call the model, do what it says, repeat until done. The interesting…

The Loop · 2/7

A Field Guide to Agent Loops

"Put the agent in a loop" hides a lot of choices. Which loop? There's a small zoo of them — and picking the wrong shape is why some agents grind forever, some quit early, and some melt your token…

The Loop · 3/7

Loop on the Gap, Not the Try-Count

The most common way to end an agent loop is max_retries=5. It's also a category error. "The agent ran out of attempts" and "the work is done" are different facts, and a retry counter can't tell them…

The Loop · 4/7

Agents Will Lie to Escape the Loop

Put a model in a loop it can only leave by saying one magic word, make the loop tedious, and eventually it says the word. Not because it's malicious — because "done" is the exit, and the exit is what…

The Loop · 5/7

The Files Are the Memory

The obvious way to run a long agent loop is to keep the conversation going — let each iteration see everything that came before. It's also why long loops rot. The best loops do the opposite: they…

The Loop · 6/7

The Loop Is a Ledger, Not an Orchestrator

Picture the thing running your agent loop. Most people picture a long-lived orchestrator — a smart controller that holds the plan, tracks progress, and decides what happens next. That controller is…

The Loop · 7/7

Recursion That Can't Run Away

Sooner or later a loop's next step is too big to be a step. It's a whole task with its own sub-tasks — its own loop. Now you have loops inside loops, and the question everyone asks is: what stops it…

6-part series

Intent Over Instructions

There are two ways to direct an agent. You can script the steps it takes, or you can lock the outcome and let it find its own way there. Almost everyone starts by scripting. Almost everyone should…

Intent Over Instructions · 1/6

Bound, Don't Script

There are two ways to direct an agent. You can script the steps it takes, or you can lock the outcome and let it find its own way there. Almost everyone starts by scripting. Almost everyone should…

Intent Over Instructions · 2/6

Instructions That Outlive the Model

Every behavioral instruction you write into a skill, an agent file, or a system prompt is a bet against the next model. Most of those bets lose. The instruction that wins is the one that was too lean…

Intent Over Instructions · 3/6

Bind the Goal, Not the Gesture

Record a person doing a task and you can replay it. But you've captured the wrong thing. You captured the clicks — the gesture — when what you wanted was the goal. The difference decides whether your…

Intent Over Instructions · 4/6

Confidence Is Not Consent

Once you let an agent own the how, one question decides everything: how much of it do you let it run without asking you first? The tempting answer is "let the confidence score decide." That answer is…

Intent Over Instructions · 5/6

The Clean Room

The automation ran. It made a real write to a real system and cleanly reverted it. Every check went green. It was also a fraud — because the hard part, figuring out how, had been quietly copied from…

Intent Over Instructions · 6/6

Proven End to End

The most valuable sentence in an agent system's documentation is usually the one admitting what it can't do yet. It's also the sentence most likely to get cut before anyone else reads it. That…

2-part series

MCP Architecture

I spent seven posts building the case for MCP as a semantic data layer. I was directionally right and specifically wrong. MCP works best when it's narrower than a layer — when it's a discovery…

7-part series

The Interface Inflection

For fifty years, every interface assumed a human would read the docs, write the glue code, and maintain the integration. That assumption just broke. The consumer of your next interface is as likely…

The Interface Inflection · 1/7

Interfaces Are Changing

For fifty years, every interface assumed a human would read the docs, write the glue code, and maintain the integration. That assumption just broke. The consumer of your next interface is as likely…

The Interface Inflection · 2/7

MCP: The Semantic Data Layer

Enterprise architects have been building abstraction layers between systems and consumers for decades. Most of those layers failed. MCP might be the one that works — but only if you understand why…

The Interface Inflection · 3/7

Headless AI: Every App Is a Head

The web app was never the product. It was just the first head.

The Interface Inflection · 4/7

Negotiated Integrations

Every integration you've ever built was a bet that you knew, upfront, exactly how producer and consumer would talk. For fifty years, that bet paid off. It's about to stop paying off — because the…

The Interface Inflection · 5/7

Democratizing AI Builders

The bottleneck was never the platform. It was the number of people who could use it. MCP removes that bottleneck — not by dumbing things down, but by making capabilities legible to anyone with intent.

The Interface Inflection · 6/7

The Interface Forecast

Five posts ago, we started with a simple observation: the consumer of your next interface is as likely to be an LLM as a developer. Now it's time to follow that thread to its conclusion.

The Interface Inflection · 7/7

MCP Isn't the Problem

I've spent four posts building the case for MCP as a semantic data layer, a headless capability surface, a foundation for negotiated integrations. Then Perplexity's CTO said they're dropping MCP for…

The AI Dev Toolkit in 2026

The stack has settled. After two years of fragmentation—competing frameworks, overlapping tools, weekly "this changes everything" posts—three layers emerged. Most developers use one. Some use two.…

What is Agentic Thinking?

A practitioner's notebook for building with AI that acts—not AI that answers.

Ema Workflows: Debugging Common Problems

Why isn't my email sending? Why does my AI Employee say the same thing three times? This debugging guide covers the most common workflow problems and shows you exactly how to diagnose and fix…

Ema Workflows: Search Debugging

Your knowledge search returns garbage. Your RAG pipeline isn't finding the right documents. This troubleshooting guide covers the most common knowledge search problems in Ema workflows—and how to fix…

Rules That Know Your Stack

Your project uses React 18, Vite, Vitest, and Tailwind. But your rules mention Jest patterns, CSS modules conventions, and generic "component" guidance that doesn't account for React's concurrent…

Ema Workflows: Routing and Branching

How do you make an Ema workflow take different paths based on user intent? This guide covers chat_categorizer, runIf conditions, and the patterns that keep your branching logic clean and maintainable.

Your Rules Are Fighting Each Other

How to find the conflicts, stop the chaos, and get your AI following instructions again. Your AI is ignoring your rules. You've checked the syntax. You've verified the globs. The file is right there.…

Ema Workflows: Entity Extraction

Entity extraction is one of the most powerful tools in Ema workflows—and one of the most misunderstood. This deep dive covers schemas, instructions, output handling, and the gotchas that trip up even…

5-part series

Search, Intent, and Action

Nobody ever wanted search results. They wanted answers. But here's the thing—they didn't actually want answers either. They wanted action. This post traces the evolution from search to intent to…

13-part series

Building with AI Assistants

Rules are just the beginning. Cursor provides four artifact types—and using the wrong one creates friction. This post covers what rules can't do and when to reach for Commands, Agents, or Skills…

Building with AI Assistants · 1/13

Beyond Rules: Commands, Agents, and Skills

Rules are just the beginning. Cursor provides four artifact types—and using the wrong one creates friction. This post covers what rules can't do and when to reach for Commands, Agents, or Skills…

Building with AI Assistants · 2/13

Designing Agent Personas That Actually Work

"You are a helpful AI assistant" is the persona equivalent of "write clean code." It says nothing actionable. This post shows how to design agent personas that produce consistent, high-quality output…

Building with AI Assistants · 3/13

The Multi-Agent Illusion

You ask your AI-powered IDE to "have the security auditor review this code." A specialized agent springs into action—separate from the main assistant, purpose-built for security analysis. Right? The…

Building with AI Assistants · 4/13

Smart Routing: Right Agent, Right Job

Manually spawning agents doesn't scale. If you have 15 specialized agents but have to remember which one handles what, you'll just use the main assistant. This post shows how to route tasks to agents…

Building with AI Assistants · 5/13

Commands That Know When to Merge

Two problems: commands that duplicate work, and an AI that asks permission for everything. This post solves both—smart command orchestration that eliminates redundancy, and pre-authorized autonomous…

Building with AI Assistants · 6/13

Anatomy of a Persona Lens

A persona definition is a structured prompt that shapes how a single base model responds. Let's open one up and see exactly how it works—and why structure matters more than you'd expect.

Building with AI Assistants · 7/13

Designing with the Persona Lens Model

Understanding that agents are persona lenses changes how you design routing, coordination, and expectations. This post covers practical patterns for building systems that work with this reality…

Building with AI Assistants · 8/13

Testing AI Artifacts: A Validation Framework

Most teams create rules and commands but never verify they work. Then they're surprised when the AI ignores guidance or produces inconsistent output. This post introduces a testing framework for…

Building with AI Assistants · 9/13

AI That Teaches Itself

What if your AI development system got better automatically? Not through manual rule-writing, but by observing how you work and proposing improvements. This post shows how to build feedback loops…

Building with AI Assistants · 10/13

The alwaysApply Tax

We audited a mature Cursor configuration and found 22 rules with alwaysApply: true, totaling 2,700 lines loaded into every single conversation—including "what's 2+2?" This is the alwaysApply tax.

Building with AI Assistants · 11/13

Rules vs Skills in AI Dev

Rules and skills are both configuration artifacts, but they serve different purposes. Mixing them creates bloated rules that should be skills, or skills that are just reference material. Here's how…

Building with AI Assistants · 12/13

How Cursor Finds Skills

You created a custom skill. You tested it. It works when you invoke it directly. But when you describe what you want naturally, the AI ignores it. The skill exists—but it's invisible. Here's why.

Building with AI Assistants · 13/13

Subagents: Fresh Eyes on Demand

The main AI assistant has been helping you for an hour. It's seen every file you've opened, every failed attempt, every tangent. Now you need a fresh perspective—someone who hasn't been marinating in…

Compiler vs LLM: A Deep Dive

Why the same spec produces wildly different outputs—and how we fixed it after 14 API failures.

Audit Your AI Config

You've learned about rules vs skills, the alwaysApply tax, and discovery mechanics. Now what? This post provides a step-by-step audit process for cleaning up an existing AI configuration. The goal…

The Three-Tier Context System

AI-assisted development generates artifacts that didn't exist before: insights from debugging sessions, decisions made in conversation, draft content, task coordination. Without a system, these end…

Compiler to LLM Workflows

How intent-first development compressed our iteration loops—and why the quality surprised us more than the speed.

.ctx: Memory for Amnesiac Agents

AI agents are amnesiacs with no social skills. Each session starts fresh—no memory of what happened before, no awareness of other agents working on the same project. We discovered that a simple…

MCP Tools People Actually Use

What we learned restructuring an MCP server from 7 "super tools" to 20 focused operations.

Goals Matter More Than Code

How misaligned objectives between compilers, LLMs, and humans created 14 failures—and what we learned about designing for intent.

Ema: Picking the Right Tool

Should you use entity_extraction or conversation_summarizer to get the caller's name? When does chat_categorizer beat call_llm? This decision guide helps you pick the right Ema workflow tool for…

Rules on Rules on Rules

Rules on rules on rules—stacks on stacks on stacks—but for your AI. It's the slightly silly phrase that ends up solving a very real problem: keeping AI output consistent across a codebase.

Ema Workflows: State Persistence

Why does my AI Employee "forget" information between turns? This guide explains the stateless nature of Ema workflows and shows you how to design conversations that maintain context across multiple…

Ema Workflows: RAG Flow Control

A technical guide to controlling RAG flow in Ema workflows. Understanding trigger outputs, conversation handling, and query construction is the difference between a chatbot that retrieves relevant…

Rules, Agents, Commands, MCP... WTF?

A guide to what goes where and why — so you can stop wondering and start building. Rules. Commands. Agents. Skills. MCP. Prompts. If you've spent any time trying to customize your AI coding…

Inline LLM Calls: Skip the Redeploy

Hardcoded logic is brittle. Every if (type === "report" || type === "document") is a decision that will need updating when business requirements change. This post covers when to replace hardcoded…

MCP: From Hardcoded to Live Data

Hardcoded data in MCP servers is a trap. It works until it doesn't—until someone adds a new action, renames a widget, or deprecates an integration, and suddenly your MCP server is lying to the AI.…

3-part series

MCP in Practice

This post is the conceptual foundation for the MCP series. If you want the mental model and decision framework, start here. If you want implementation stories, read MCP in Practice: From Scripts to…

The New Hire Who Never Sleeps

It's time to treat your AI agents like the employees they already are. Somewhere in your organization right now, an entity is making decisions on your behalf. It's reading customer messages.…

Agentic AI: Beyond the Chatbot

Agentic AI refers to artificial intelligence systems that can autonomously plan, reason, and execute multi-step tasks to achieve goals—much like a human employee. Unlike traditional AI that responds…

Why I Joined Ema: Betting on Agentic AI

Every career-defining bet I've made started the same way: I saw an architectural shift before the market priced it in, found the team building at the center of it, and jumped.

Ema Platform: Agentic AI Guide

A comprehensive guide to understanding Ema's Agentic AI platform—from core concepts and terminology to practical implementation patterns. Whether you're technical or business-focused, this guide will…

Ema: The Universal AI Employee Platform

Ema is the Universal AI Employee platform, transforming enterprise operations through AI agents that actually work alongside human teams. Unlike chatbots or simple automation tools, Ema creates AI…

Ema's Founders: Google to Startup

Ema was founded by a powerhouse duo with exceptional credentials from some of the world's most successful technology companies. Their combined experience spans Google, Coinbase, and Meta, with a…

About Me: Consulting to Startups

I'm a technology industry veteran with a pattern of joining early-stage companies and helping them scale to massive success. Here's my story and what drives me.

↑ ↓ to navigate Enter to select Esc to close

Content Calendar

83 posts · Publishing Schedule

83Total
57AI Dev
9AI Employees
10Fundamentals
10Search+Story
View as List
October 20, 2025 About Me: Consulting to Startups personal November 10, 2025 Ema's Founders: Google to Startup ema November 20, 2025 Ema: The Universal AI Employee Platform ema December 1, 2025 Ema Platform: Agentic AI Guide ema December 8, 2025 Why I Joined Ema: Betting on Agentic AI ema December 15, 2025 Agentic AI: Beyond the Chatbot agentic-ai January 5, 2026 The New Hire Who Never Sleeps agentic-ai January 6, 2026 MCP in Practice: From Scripts to Platform mcp January 6, 2026 MCP in Practice: Knowledge-First Builder mcp January 8, 2026 The MCP Mental Model mcp January 11, 2026 MCP: From Hardcoded to Live Data mcp January 11, 2026 Inline LLM Calls: Skip the Redeploy llm January 11, 2026 Rules, Agents, Commands, MCP... WTF? cursor January 13, 2026 Ema Workflows: RAG Flow Control ema January 14, 2026 Ema Workflows: State Persistence ema January 15, 2026 Rules on Rules on Rules cursor January 16, 2026 Ema: Picking the Right Tool ema January 17, 2026 Goals Matter More Than Code llm January 18, 2026 Embeddings: How Vectors Get Meaning embeddings January 19, 2026 MCP Tools People Actually Use mcp January 20, 2026 Beyond Rules: Commands, Agents, and Skills cursor January 21, 2026 Intent: From Keywords to LLMs search January 22, 2026 The Multi-Agent Illusion cursor January 22, 2026 .ctx: Memory for Amnesiac Agents cursor January 22, 2026 Designing Agent Personas That Actually Work cursor January 23, 2026 Search is Dead. Long Live Action. search January 23, 2026 Anatomy of a Persona Lens cursor January 24, 2026 Designing with the Persona Lens Model cursor January 24, 2026 Smart Routing: Right Agent, Right Job cursor January 25, 2026 Compiler to LLM Workflows llm January 26, 2026 Commands That Know When to Merge cursor January 27, 2026 Building This Blog's Search search January 27, 2026 The Three-Tier Context System cursor January 27, 2026 How Cursor Finds Skills cursor January 27, 2026 Rules vs Skills in AI Dev cursor January 27, 2026 Audit Your AI Config cursor January 27, 2026 The alwaysApply Tax cursor January 28, 2026 Testing AI Artifacts: A Validation Framework cursor January 29, 2026 Compiler vs LLM: A Deep Dive llm January 29, 2026 Subagents: Fresh Eyes on Demand cursor January 30, 2026 AI That Teaches Itself cursor January 31, 2026 Search: From 30ms to 3 Seconds search February 1, 2026 Ema Workflows: Entity Extraction ema February 2, 2026 Your Rules Are Fighting Each Other cursor February 3, 2026 Ema Workflows: Routing and Branching ema February 4, 2026 Rules That Know Your Stack cursor February 5, 2026 Ema Workflows: Search Debugging ema February 7, 2026 Ema Workflows: Debugging Common Problems ema February 23, 2026 Interfaces Are Changing fundamentals February 23, 2026 The AI Dev Toolkit in 2026 cursor February 27, 2026 MCP: The Semantic Data Layer ai-development March 3, 2026 Headless AI: Every App Is a Head ai-development March 6, 2026 Negotiated Integrations ai-development March 10, 2026 Democratizing AI Builders ai-development March 13, 2026 The Interface Forecast fundamentals March 18, 2026 MCP Isn't the Problem mcp April 1, 2026 MCP as Discovery Protocol ai-development April 1, 2026 Externalize the Knowledge ai-development July 13, 2026 Bound, Don't Script ai-development July 14, 2026 Instructions That Outlive the Model ai-development July 15, 2026 Bind the Goal, Not the Gesture ai-development July 16, 2026 Confidence Is Not Consent ai-development July 17, 2026 The Clean Room ai-development July 18, 2026 Proven End to End ai-development July 20, 2026 The Agent Is a While Loop ai-development July 20, 2026 A Field Guide to Agent Loops ai-development July 21, 2026 Loop on the Gap, Not the Try-Count ai-development July 22, 2026 Agents Will Lie to Escape the Loop ai-development July 23, 2026 The Files Are the Memory ai-development July 24, 2026 The Loop Is a Ledger, Not an Orchestrator ai-development July 25, 2026 Recursion That Can't Run Away ai-development July 27, 2026 The Gotchas Are Load-Bearing ai-development July 28, 2026 Describe When, Not What ai-development July 29, 2026 Grade the Answer, Not the Shape ai-development August 12, 2026 Chosen, Not Assigned agentic-ai August 14, 2026 The Critic Said No agentic-ai August 15, 2026 Name What the Agent Must Not Be agentic-ai August 16, 2026 The Fence It Wrote for Itself agentic-ai August 17, 2026 We Measured the Wrong Noun agentic-ai August 18, 2026 Rivals Enter Your Critical Path agentic-ai August 19, 2026 Not Cairn agentic-ai October 16, 2026 Why I Went Back to Nutanix personal February 23, 2026 What is Agentic Thinking? fundamentals