Library

Everything I have published: essays and manuals from From Lab to Life, research papers, and the archive. Each work tells you where you can read it.

tr_notes from real builds

Start here

Showing 15 of 15 works · newest first · topic: Context Engineering

Reset filters
Research30 Sep 2026 · Paper

Knowledge Accumulates, State Supersedes: Structuring and Carrying Context for Multi-Session, Multi-Harness AI Agent Work — A Design Study of The Curator, an Open-Source Context Engine

Large language model (LLM) agents now carry out work that outlasts a single session: building software, running literature reviews, writing books, producing campaigns. Every session, however, begins with an empty context window, and when the work moves to a different agent harness, a different model or a different computer, whatever the previous session knew is lost.

The CuratorResearchGate
From Lab to Life20 Sep 2026 · Essay

The Context Engine

Three kinds of context, three write rules, and a project that outlives the session, the harness, the model and the machine

The CuratorMedium (canonical) · Substack
From Lab to Life30 Aug 2026 · Essay

The Handoff Writes Itself

The confession piece about two years of hand-written handoff files. The flaw: the most degraded model writes the most important document.

The CuratorMedium (canonical) · Substack
From Lab to Life14 Jun 2026 · Essay

Blueprint of a Frontier Coding Agent

Inside the machinery that powers modern AI development, and why understanding it matters even if you never write a line of code

Medium (canonical) · PDF · Substack

Get the next one first

New essays from From Lab to Life arrive on Substack before they reach this library.

From Lab to Life3 Jun 2026 · Essay

Context is the Code: The Complete Three-Phase Process for Building with AI Agents

In the first article, I named the phases: Context Engineering, The Build Phase, Production and Deployment. That naming had an unintentional effect. By calling Phase One “Context Engineering,” I implied that context engineering was something you did once — at the beginning — and then left behind.

Medium (canonical) · Substack
From Lab to Life16 Mar 2026 · Essay

Behind the Curtain: The Three-Phase Process I Use to Build Every AI-Coded Product

Two years ago, I started an experiment. I wanted to know whether I could build production-grade software products without writing most of the code myself. Not because I was lazy. Because I had thirty years of product ideas and not nearly enough development hours to explore them.

Medium (canonical) · Substack
Research1 May 2025 · Report

Exploring Early Indicators of AGI in Coding Agents: A Case Study on MCP-Powered Systems

This study, conducted under the COTRUGLI Business School 2 Co-lab initiative in Q1 and Q2 2025, investigates whether Model Context Protocols (MCPs) can enhance large language models (LLMs) to exhibit early indicators of Artificial General Intelligence (AGI) in coding agents.

ResearchGate (canonical) · Interactive dashboard · PDF
Every work, by year (77)