From Lab to Life21 Oct 2026 · Case study
One Founder, Eight Weeks, Four Hundred Agents
I delivered a working, deployed MVP in eight weeks, alone, by directing more than four hundred AI agents.
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.
Start here
The thesisChasing Jarvis: The Bottleneck Was Never the CodeWe are learning to build and ship real digital products using AI coding agents. The gap between idea and shipped product is no longer technical, it is contextual.The methodEvery Product Needs a HomeBuilding a modern website in the age of AI agents: a manual, told through the new website of The CuratorThe researchContext as Architecture: Full-Corpus Grounding, Orchestrated Agentic Development, and Compliance-by-Design in a Production AI Assistant PlatformThis paper reports a longitudinal design-science case study of a single production artefact — Lumina, a multi-tenant AI assistant platform — across two complete generations built fourteen months apart in capability terms and seven months apart in calendar terms.
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.
From Lab to Life30 Sep 2026 · Essay
The Right Context, Not All of It
Written deliberately as a lesson rather than a product story, taught through The Curator v3.80.0.
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
From Lab to Life16 Sep 2026 · Essay
Every Product Needs a Home
Building a modern website in the age of AI agents: a manual, told through the new website of The Curator
From Lab to Life3 Sep 2026 · Essay
Where Your Context Lives
The Curator ships as a native Mac app (v3.45.0). Covers the three layers (personal wiki, Shared Brain, agent working state), the menu-bar widget, bring-your-own-key across three providers at about €5 a month, and plain-markdown portability.
Get the next one first
New essays from From Lab to Life arrive on Substack before they reach this library.
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.
From Lab to Life24 Aug 2026 · Essay
Field Notes
I turned fifty-plus articles into a corpus you can question, download, and hand to your own AI.
From Lab to Life17 Aug 2026 · Essay
The Mixed Fleet
Can a frontier orchestrator on a subscription delegate to local open-weight models?
From Lab to Life6 Aug 2026 · Essay
I Could Tell You My AI Has Never Lied. I'm Not Going To.
Seven months, two generations, one production rebuild — and five things I learned that I did not expect to learn.
Research1 Aug 2026 · Paper
Context as Architecture: Full-Corpus Grounding, Orchestrated Agentic Development, and Compliance-by-Design in a Production AI Assistant Platform
This paper reports a longitudinal design-science case study of a single production artefact — Lumina, a multi-tenant AI assistant platform — across two complete generations built fourteen months apart in capability terms and seven months apart in calendar terms.
From Lab to Life31 Jul 2026 · Essay
Lumina: An AI Agent Your Business Can Stand Behind
The behind-the-scenes rebuild of Lumina from Gen-1 to an enterprise-grade Gen-2.
From Lab to Life20 Jul 2026 · Essay
From 0 to Dev in One Day: What a Real Coding Harness Actually Looks Like
A summer manual for the curious non-developer who keeps seeing people build apps out of thin air and wondering: could I actually do that?
From Lab to Life10 Jul 2026 · Essay
Six Months After I Shipped Lumina; Here's What Actually Happened
Running Lumina with real customers six months after launch. A Ljubljana massage studio hit a forgotten 2,000-character personality limit mid-conversation; the systemic fix raised the limit fourfold and added live counters.
Research8 Jul 2026 · Paper
The Fight for Intelligence — Putting the ØØT to Work: Use Cases, Vendor Independence, and the Brain Behind the Framework
Argues that competition has shifted from a fight for resources to a fight for intelligence, using the 19-day frontier-model suspension of June 2026 as evidence of single-vendor risk.
From Lab to Life8 Jul 2026 · Essay
The Fight for Intelligence
Putting the Organisation of Tomorrow to Work; Use Cases, Vendor Independence, and the Brain Behind the Framework
From Lab to Life3 Jul 2026 · Essay
Second Brain to Shared Brain: Building a Neural Network of Your Own Knowledge
A follow-up seven weeks after the Shared Brain launch. The author's own wiki has 3,305 nodes and 15,095 edges at v3.0.6.
From Lab to Life1 Jul 2026 · Essay
Anthropic Shipped Two Models This Week. I Only Wanted One Back.
Two Anthropic announcements 24 hours apart. Sonnet 5 (30 June) becomes the new default, and its real story is follow-through on multi-step tasks.
From Lab to Life28 Jun 2026 · Essay
Chasing Jarvis: The Bottleneck Was Never the Code
We are learning to build and ship real digital products using AI coding agents. The gap between idea and shipped product is no longer technical, it is contextual.
From Lab to Life22 Jun 2026 · Essay
I Built Auto Loops Before They Had a Name
How Claude Code plus Playwright via MCP became an autonomous testing loop in early 2025, before "loop engineering" had a name.
From Lab to Life19 Jun 2026 · Essay
I Built a 24/7 AI Email Support Agent for My App. Here's the Exact Stack.
Every founder I know has the same problem with email support. In the early days, you handle it yourself. You are fast, you are personal, and you actually know the product. Then you get busier. Response times slip. Users start to notice. You think about hiring someone, but the volume does not justify it yet. So you buy a helpdesk tool, set up some canned responses, and tell yourself you will get to the backlog this weekend. You never get to the backlog.
From Lab to Life18 Jun 2026 · Essay
16x Cheaper, Open Weights, and the Model That Doesn't Disappear on Fridays
Compares Kimi K2.7 and Claude Fable 5 using real production data (24 landing pages, 12 prompts).
From Lab to Life18 Jun 2026 · Essay
The Curator — Product Update (v3.0.1-beta.20 → beta.23)
Release notes for The Curator v3.0.1 beta.20 to beta.23: Shared Brain synchronisation improvements, a new test-automation infrastructure, and stability fixes.
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
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.
From Lab to Life1 Jun 2026 · Essay
Building the Organization of Tomorrow
ORGANISATION OF TOMORROW (ØØT): An Open-Source Framework and Playbook for Partner-Run, AI-Augmented Organisations
From Lab to Life19 May 2026 · Essay
The Shared Brain: When Second Brains Start Thinking Together
Introduces The Curator v3.0.0-beta Shared Brain: private, attributed contributions merged into a collective wiki for teams and cohorts.
From Lab to Life14 May 2026 · Essay
The Agent Memory Problem — And Why Your Second Brain Might Be the Answer
A survey of how the industry is attacking agent memory (vendor memory products, vector stores, managed memory services, file-based memory), why context windows alone fail at agent scale ("context rot"), and why a compiled Markdown…
From Lab to Life4 May 2026 · Essay
The Brain Is Ready. The Body Is the Problem.
State of AI, May 2026. Frontier models have reached capability thresholds (1M context, open-source parity).
Research1 May 2026 · Paper
Organisation of Tomorrow (ØØT) — Building the Organization of Tommorow: An Open-Source Framework and Playbook for Partner-Run, AI-Augmented Organisations
Presents ØØT as an open-source framework and playbook for partner-run, AI-augmented firms.
From Lab to Life27 Apr 2026 · Essay
From Graph to Intelligence: The My Curator MCP and the Art of Querying Your Second Brain
How My Curator MCP Turns Your Second Brain into a Frontier AI Research Partner
From Lab to Life23 Apr 2026 · Essay
Building Knowledge Immortality Through the Second Brain Architecture and The Curator App
The philosophical case for the second brain: knowledge immortality, externalised expertise, and curation (compounding) versus retrieval (stateless).
From Lab to Life15 Apr 2026 · Essay
The Second Brain That Grows Smarter and Lives on Your Computer
Introduces The Curator through Karpathy's "LLM as wiki" insight: a local, private, Markdown-based knowledge graph that Obsidian can read.
From Lab to Life7 Apr 2026 · Essay
Three Philosophies, One Goal; A Practitioner's Comparison of Augment Code, Claude Code, and Codex CLI
A practitioner's comparison of three coding-agent philosophies.
From Lab to Life26 Mar 2026 · Essay
Two Worlds of Code: The Gap Between AI Agent Orchestration and Legacy Development
The canonical home of the Solo era / Symphony era framing.
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.
Research15 Mar 2026 · Paper
Chasing Jarvis: Can Technically Sophisticated Non-Programmers Deploy SaaS Applications Using AI Coding Agents? An Empirical Investigation Through Context Engineering and the Lumina AI Case Study
The empirical study behind the non-developer thesis.
From Lab to Life9 Mar 2026 · Essay
From Writing Code to Directing Intelligence: Five Days Inside Augment Code's Intent
Five days testing Augment Code's Intent orchestration tool on the production Lumina platform (building Lumina Pro).
From Lab to Life2 Mar 2026 · Essay
Law = Code: Can AI Finally Democratise the World's Most Exclusive Algorithm?
It all started with a conversation between me and my friend Anton Dobrina — legal expert, fellow AI enthusiast, and someone who has spent years studying and working in legal practice in Slovenia, co-writing Slovenian legislation and is an expert in the Slovenian retirement code.
Research2 Mar 2026 · Paper
Law = Code; Research Paper
Can AI Democratise the World's Most Exclusive Algorithm? A Review of Emerging Legal AI Capabilities and Their Implications for Access to Justice
From Lab to Life17 Feb 2026 · Essay
From One Agent to Coding Agent Armies: My 15-Month Journey to AI Orchestration
How Augment Code’s Intent Just Changed Everything — Again
From Lab to Life30 Jan 2026 · Essay
OpenClaw: The AI Assistant That Lives in Your Pocket (And Actually Gets Things Done)
A research-based overview of OpenClaw (formerly Moltbot / Clawdbot), the open-source, always-on personal AI assistant created by Peter Steinberger.
From Lab to Life21 Jan 2026 · Essay
Why I Ditched RAG Pipelines for 1M Token Context Windows
An 18-month build of a legal-document AI for Slovenian building legislation (Moj AI).
From Lab to Life14 Jan 2026 · Essay
How I Built an AI Marketing Team That Actually Works: From Memes to Technical Content in Minutes
An AI multi-agent marketing workflow in which different agents handle different content types.
From Lab to Life5 Jan 2026 · Essay
From Prototype to Production: Building Lumina an AI Widget Platform in 30 Days
The Lumina Widget build story: a 30-day sprint from concept to production on a budget of about $100 in AI credits, using Augment Code with Claude Haiku 4.5.
From Lab to Life11 Dec 2025 · Essay
From Google AI Studio to Production: Building Lumina v1 in 48 Hours
How the first version of Lumina was prototyped in Google AI Studio and taken to production on Firebase in 48 hours.
From Lab to Life24 Nov 2025 · Essay
Chasing Jarvis: The Three Missing Pieces in AI Coding Agents
A Two-Year Journey From Fiction to Reality (and the Creativity Blockers Still Holding Us Back)
From Lab to Life27 Oct 2025 · Essay
Understanding AI Agents: From Chatbots to Autonomous Digital Workers
The foundational definitions essay. Sets out the taxonomy of chatbots, assistants, agents and autonomous workers, with a four-tier autonomy hierarchy and a five-level maturity model for agentic AI.