Essays · Field Notes

Writing on architecture, attribution, and operating discipline.

Jul 3, 2026

Closed-loop attribution closed the loop for the seller, not for you.

A wave of closed-loop products shipped this month. They all share one feature nobody is naming: the company reporting the conversion is the company selling the media. That is last-click's oldest failure in a 2026 costume.

Jul 3, 2026

Your agent's role tags are a suggestion, not a wall.

New research says models decide who is speaking from style, not from the role label. If you run recommend-only agents with a human approving each move, good. But that approval is one guardrail among several, and it does not patch the hole underneath.

Jul 3, 2026

A new ad channel just launched with no way to measure itself.

ChatGPT ads are being sold on intent, with no channel-native attribution. They borrow a measurement spine that is being absorbed into a holding company. Running on the channel early is worth it. Trusting its self-reported numbers is not.

Jun 13, 2026

Two games, built to learn

A woodblock samurai brawler and a head-tracked rail shooter, both built as proof of concepts. The point wasn't the games. It was being a beginner again, where the agent can't fake it.

Jun 12, 2026

Your agent's bill isn't the model. It's the query path.

The 2026 AI cost reckoning trains your attention on the token meter. When I traced where an agent's spend actually went, the model was the easy part. The leak was the warehouse the agent queries.

Jun 12, 2026

Agentic media buying is real now. The wall isn't the AI, it's the account model.

This week agentic buying went from panel topic to live deals. Having built the agent, the bottleneck isn't the buying decision. It's that every network is a different country with no shared passport.

May 24, 2026

Publicis paid $2.2 billion for the substrate. The operator question is which deterministic layer you own.

Publicis bought LiveRamp for $2.2B to feed Marcel. That's the holding-company tier publicly pricing a thesis operators have been building toward for two years.

May 24, 2026

The agent control plane is the actual fight

Karpathy joined Anthropic to run autoresearch at frontier scale. The same closed loop is the operator-tier curriculum now, one tier down.

May 15, 2026

When the model labs ship your agents, the moat moves elsewhere

Anthropic just shipped ten finance-agent templates and a managed runtime. The interesting question isn't whether you're ahead. It's what survives commoditization.

May 15, 2026

Notes on how observer-agents fail

Three failure modes in agents that synthesize work you own, and why the third one breaks the whole review chain.

May 8, 2026

The shape of agents that observe their own outputs

A class of agent is emerging that doesn't do new work. It reads what you already have through a perspective you didn't take.

May 8, 2026

What Meta passing Google means for measurement stacks built on Google's gravity

Meta overtaking Google in ad revenue isn't a horse-race story. It's a structural argument that the measurement stack most marketers built fifteen years ago is now under-resourced for the world they're actually in.

May 4, 2026

Build, don't buy: how we architected AIMG's marketing intelligence stack

Why three layers — AiTRK, Atrilyx, and the Atrilyx Agent — beat any single off-the-shelf attribution tool, and what we learned in the process.