Field Notes

Engineering notes from production work.

Patterns we keep reaching for, mistakes we don't want to make twice, and the decisions we wish we'd seen written up before.

AI · 26 Apr, 2026 · 07 Mins read

Building an AI Workforce for Your Company

The pitch your team has heard ten times this year: "We can replace 30% of your ops headcount with AI." The pitch usually comes attached to a chatbot that hallucinates on the third question and a six-figure annual contrac…

Read note →

AI · 22 Apr, 2026 · 04 Mins read

Shipping AI Agents That Hold Real Money

Most agent demos you'll see are toys. A model wrapped in a loop, given a few tools, and pointed at a sandbox. The interesting question — the…

Read note →

Web3 · 22 Apr, 2026 · 06 Mins read

LMSR vs Orderbook: Picking a Prediction Market Engine

A prediction market needs an engine that does one job: turn an order to buy or sell into a price. There are two answers in production today…

Read note →

AI · 15 Apr, 2026 · 05 Mins read

Production RAG: From Demo to a System That Doesn't Hallucinate

The first version of any RAG system works on a curated demo set. The user asks a question, the system returns relevant chunks, the model ans…

Read note →

Web3 · 08 Apr, 2026 · 05 Mins read

The Pre-Audit Checklist Every Protocol Team Should Run

A smart contract audit is one of the more expensive engineering invoices most protocol teams ever sign. A serious firm bills $50–250k for a…

Read note →

AI · 01 Apr, 2026 · 05 Mins read

Cutting AI Costs by 10x Without Cutting Quality

Most AI products we audit are paying somewhere between 5× and 10× what they need to be paying. The reasons are remarkably consistent across…

Read note →

Process · 25 Mar, 2026 · 05 Mins read

How We Scope a Product in Five Days

Most agency engagements get into trouble in the first two weeks, before a single line of code has been written. The team is excited, the fou…

Read note →

AI · 18 Mar, 2026 · 05 Mins read

AI for Enterprise Ops: Where the ROI Actually Lives

Most enterprise AI projects don't fail because the technology doesn't work. They fail because the team picked a workflow where AI doesn't co…

Read note →

Web3 · 11 Mar, 2026 · 05 Mins read

Building a Perpetual DEX: Production Architecture

Perpetual DEXes look simple from the outside. Users post collateral, take leveraged positions, the protocol manages the book, and someone —…

Read note →

AI · 04 Mar, 2026 · 05 Mins read

AI Evals: Beyond Vibes-Based QA

The most common AI quality-assurance setup we see in production is one engineer running a few prompts through the new model version, eyeball…

Read note →

Web3 · 25 Feb, 2026 · 05 Mins read

Building a Polymarket-Style Prediction Market

Prediction markets are simple to describe and unforgiving to build. Users buy shares in outcomes ("Will X happen by Y date?"), prices move t…

Read note →

Mobile · 18 Feb, 2026 · 05 Mins read

React Native vs Native: A 2026 Decision Framework

The "React Native vs native" debate has been running for so long that most of the takes you'll find online are stale. The state of both ecos…

Read note →