Field Notes Blog

Real-world stories about fixing broken processes, taming messy data, and building systems that actually work. No buzzwords, just practical lessons from the trenches.
Erasing and Repainting an AI Writing Voice
AI Engineering

Erasing and Repainting an AI Writing Voice

Our content pipeline kept publishing posts that readers flagged as AI-generated. The grammar was clean, the facts were right, nobody cared. What it took to fix the voice, and a surprise about where 'more passes' stops helping.
Kyle Johnson

Kyle Johnson

Your Website Might Be Invisible to AI
Web Strategy

Your Website Might Be Invisible to AI

When someone asks ChatGPT or Perplexity about your business, there's a good chance your website isn't part of the answer. Here's why, and what to do about it.
Kyle Johnson

Kyle Johnson

Why Your Organization is Data-Rich but Insight-Poor
Analytics

Why Your Organization is Data-Rich but Insight-Poor

The universal struggle of having mountains of data but no clear answers—and what to do about it
Kyle Johnson

Kyle Johnson

Case Study: How AI Turned 15 Hours of Legal Review Into 15 Minutes
Case Study

Case Study: How AI Turned 15 Hours of Legal Review Into 15 Minutes

A real engagement where we used Claude Code to parse 1,271 co-parenting messages from PDF exports, structure them into searchable data, and generate a cited evidence report for discovery. What used to take 15 hours of paralegal work took 15 minutes.
Kyle Johnson

Kyle Johnson

OpenClaw: The Architecture Behind the Always-On AI
AI Engineering

OpenClaw: The Architecture Behind the Always-On AI

Exploring how OpenClaw creates a persistent AI assistant experience using an event-driven Gateway architecture rather than a continuously running model.
Kyle Johnson

Kyle Johnson

Claude Code Isn't Magic. It's a While Loop with Tools.
AI Engineering

Claude Code Isn't Magic. It's a While Loop with Tools.

A deep dive into what's actually happening under the hood of Claude Code: the ReAct loop, the tool system, the hooks, and why understanding this architecture matters more than using it
Kyle Johnson

Kyle Johnson

Why Backend AI Beats Frontend AI for Enterprise Value
AI Strategy

Why Backend AI Beats Frontend AI for Enterprise Value

The unsexy, invisible AI implementations that actually drive ROI—and why the flashiest features are often the worst investments
Kyle Johnson

Kyle Johnson

The Tool-Selection Blindspot Most Data Scientists Still Have
AI Strategy

The Tool-Selection Blindspot Most Data Scientists Still Have

Why the 'simple' traditional ML approach often costs 10x more than the 'overkill' LLM solution—and what it reveals about how we evaluate technology
Kyle Johnson

Kyle Johnson

The Most Valuable Resource in Analytics Isn't Data—It's Insights
Analytics

The Most Valuable Resource in Analytics Isn't Data—It's Insights

Why organizations with refineries full of premium insights are watching decision-makers run on empty—and how to fix your broken insights pipeline
Kyle Johnson

Kyle Johnson

Your Organization Isn't Ready for AI (And That's Okay)
Strategy

Your Organization Isn't Ready for AI (And That's Okay)

The uncomfortable truth about AI implementation and why starting with your boring problems is the smartest strategy
Kyle Johnson

Kyle Johnson

The Hidden Cost of Manual Processes Nobody Talks About
Operations

The Hidden Cost of Manual Processes Nobody Talks About

Why that 'quick' manual task is costing you more than you think—in money, morale, and missed opportunities
Kyle Johnson

Kyle Johnson