# blog

Field notes

Long-form notes on AI systems, software engineering, information security, fraud detection, and digital trust.

articles: 02
latest: 2026-06-04
format: long-form notes

2026-06-04 / ai workflow, prompt engineering, mental models / 5 min read

Pre-Prompt, Post-Prompt, Automate: A Mental Model for Working with AI

A practical three-stage mental model for working with AI tools, drawn from years of fraud and chargeback work: do the homework before prompting, name every iteration, and automate only when the process has earned it.

ai workflow prompt engineering mental models

Read article →

2026-06-01 / ai, language models, representation learning / 5 min read

If LLMs Are Just Predicting the Next Word, How Can They Do Amazing Things?

Next-token prediction sounds simple, but difficult predictions force language models to build internal representations of facts, concepts, goals, sentiment, and uncertainty.

llms reasoning concepts

Read article →

Field notes

Articles

Pre-Prompt, Post-Prompt, Automate: A Mental Model for Working with AI

If LLMs Are Just Predicting the Next Word, How Can They Do Amazing Things?