In production · 180+ iterations deep

Lurch runs my businesses. I can build you one.

Five businesses run on it, and 12+ products and services have shipped across them. It takes a product, or a whole business, from concept to market in under a day, and its scheduled jobs run overnight and through the day with no human in the loop. Lurch is the custom AI operating system underneath all of it.

You can't buy Lurch, yours would be a different system with different agents and different gates. So the engagement finds out first whether your business can carry one at all, and only then designs it.

The numbers behind the claim

These come off a system in production, doing the day-to-day work of real businesses.

5
businesses taken from zero to live and running on it
12+
products and services in market across those businesses
7
architectural layers
2
machines, with a baton handoff between them
10+
business tools joined into one workspace
600+
events consolidated nightly from 95+ venues

Everything above is running right now. I'll show you the live system on the call.

Book a Call

Six company functions, running at the same time

Lurch isn't one assistant waiting on one prompt, it's a staff. Agents work concurrently, each owning a function with a defined job, and the work lands whether or not I'm at the desk.

🔍

Outreach

A scored prospect database ranks and batches who to contact, so the order of the day comes off evidence and not off whoever looks interesting that morning. LinkedIn and email are both scanned and logged, and anything needing a response becomes a follow-up task on its own.

📣

Marketing

The morning briefing pulls current news and routes it where it belongs: tasks, positioning, website updates and post topics. It produces 15 curated items, 5 talking points and 4 content ideas before I've opened anything, so the content work starts from material instead of a blank page.

💼

Sales

The CRM sits inside the system instead of beside it. Live pipelines get snapshotted every 3 hours, and the follow-ups that fall out of scanned mail arrive already attached to the right record.

🚀

Product Development

12+ products in market is the record, and 6 production websites were built end-to-end with AI-assisted development, plus a feature upgrade on an existing community platform. Every web property sits on an automated deploy pipeline, so a push updates the live site with nobody touching a server.

⚙️

Operations

10+ business tools (CRM, email, cloud storage, hosting, design, tracking) connect into one workspace, so a change made in one place shows up everywhere it matters. One dashboard renders the whole portfolio live and emails itself to me every morning, and edits made on my phone sync back to the desktop automatically.

🩺

System Health

A watchdog agent finds broken jobs, fixes them, verifies each fix with a re-run, and logs whatever it couldn't repair. The design goal is self-healing: the system detects its own gaps, closes them, and reports in the past tense.

Seven layers, and a person at every gate

What holds Lurch up is the structure underneath the models, not the models. The rules, the methods and the data live in the layers, never inside a model.

1
Instructions
The standing rules every model and every agent reads before it acts.
2
Skills
The methods, written down. My full AI transformation and workflow opportunity analysis methodology lives at this layer, so the consulting IP sits in the system and not only in my head.
3
Runtime
The shared code every agent calls, so a method is written once and every agent gets the same one.
4
Agents
The staff. Research, content, operations, system health and CRM, each one a distinct company role.
5
Orchestrator
Scheduling and dispatch. Jobs run overnight and through the day across two machines, with a baton handoff between them.
6
Data
Version-controlled and backed up. The whole business infrastructure moved in during a single 7-hour session, zero data loss.
7
Surfaces
Where a person touches the system: one live dashboard, a morning email, and mobile access from any device.
The gates are where a person is required, and they are drawn tight on purpose: money, credentials, legal exposure and anything an outside audience will read cannot move without me. The rest runs unattended. The AI does the heavy lifting, my product judgment sets the direction and decides what clears each gate, and the boundary is written into the system instead of left to discipline.

It runs many jobs at once without stepping on itself

The hard part of a system like this isn't the models, it's the traffic control. Several AI sessions run at the same time, some writing code, some doing business work, and more than 40 scheduled jobs run unattended alongside them. That only holds together if they cannot corrupt each other, so collisions are made impossible rather than made rare.

Every session gets its own workspace. Each one works in an isolated copy of the system, named for the job, the machine and the AI driving it. A guard blocks any session from writing into another session's workspace outright, instead of catching it afterwards.

Shared files have exactly one writer. Anything several sessions need to touch goes through a single locked path. The lock is the only way in, so two writers can never collide.

Work survives the session that produced it. When a session ends it writes a handover brief for whoever picks the work up: what it was doing, what it decided and why, and the single next action. The brief is good for 48 hours, can be claimed exactly once, and can be claimed from either machine.

Nothing is lost when a session fills up. The system measures its own working memory as it goes, warns before a session runs out of working memory, and refuses the first attempt to compress a session until the work has been written to disk. A running session can also send a note into another one, so a finding in one lane reaches the lane that needs it.

Cost is managed per job, not per month. Every task names the cheapest model that can actually do it: the small fast ones for mechanical work, the expensive one only where judgment is genuinely needed. Finished workspaces clean themselves up once their work is committed, pushed and idle for 24 hours, and anything failing those tests is kept rather than deleted.

One person built this. Doesn't that make it fragile?

Fair question, and the answer is in the architecture. A system like this breaks in three places, and Lurch was built against all three.

Nobody notices when a job dies. The watchdog agent finds broken jobs, repairs them, verifies each repair with a re-run, and writes down what it couldn't fix. A broken job shows up as a written record instead of a job that quietly stopped running.

One machine stops and the business stops. Two machines carry the workload with a baton handoff between them, so the automation keeps running when a machine goes down.

The software quietly does something nobody approved. The gates cap the blast radius. Nothing spends money, touches credentials, takes a legal step or publishes copy without me saying yes.

Then there's the question of what actually built it. Lurch is an architecture problem, not a typing problem: the layering, the role definitions, the gates, and the call on what a machine is allowed to do unsupervised. I brought 30+ years of product and technology strategy at Fortune 500 director level to those decisions, and the governance and regulatory compliance work I did in fintech is where that discipline comes from. Those calls are the ones I'd be making on your system too.

That's the whole machine. The call is where we talk about yours.

Book a Call

The functions it covers

Each line below is a function a growing company needs done. In Lurch each one is an agent with a defined job, all of them working at once instead of waiting their turn. That is coverage of the function, not a replacement for the person: I have not measured any of this against what a hired team would produce, and I am not going to claim I have.

Research analyst
Market and competitive scanning, and the weekday briefing that starts every morning with material instead of a blank page.
Content marketer
Post topics, positioning updates and website changes, routed out of that briefing to the place each one belongs.
Sales operations
The live pipelines, the scored prospect database that sets the outreach order, and the follow-up tasks generated from scanned mail.
Operations coordinator
The tool integrations, the scheduled jobs that run while nobody is watching, and the dashboard that renders the portfolio live.
Reliability engineer
The job that watches the other jobs, and the standing record of what is running, what broke, and what got fixed.
Product and delivery
Concept to market, with the shipped websites and products behind the claim.

If you counted which of those functions you're short, that's the agenda for the call.

Book a Call

What Lurch is not

Five things this system does not do, so you can rule it out on your own terms rather than mine.

It isn't autonomous, and it shouldn't be. Plenty of it runs unattended, but money, credentials, legal steps and anything an outside audience will read stop and wait for a person. A system that runs your company unsupervised isn't a stronger version of this, it's a liability with better marketing.

It isn't shrink-wrapped software. Lurch was built for one business, mine, and yours would be a different system with different agent roles and different gates. What transfers is the architecture and the method, never the code.

It won't be a 2-day miracle for you. FunParrots.com went from idea to live in 2 days because the operating system already existed underneath it. Your first build is the slow one, which is exactly why the diagnostic and the blueprint come before it.

It doesn't self-heal everywhere. The watchdog writes down what it couldn't repair, which is the half of the job it can't do. Any system claiming it never fails is a system nobody is checking.

It doesn't replace judgment. The models and the agents do the heavy lifting, they don't decide what's worth doing, and that call has stayed with a person through 180+ iterations on purpose.

Three stages, a real gate after the first, and the build only if you want it

You don't buy Lurch, you buy the design of yours. I find out first whether your business can carry an operating system at all, and only if the answer is yes do I design one. Most AI engagements skip that question and bill you either way.

Stage 1: The Diagnostic$5,000
One week

Can your business carry an AI operating system, and what would it cost you to run one? I map how work actually moves through your company, where the judgment calls sit, and what your data and your processes can support today. It ends in a straight yes or no, in writing.

If the answer is no, the engagement stops here and you keep the finding.
Stage 2: The Blueprint$7,500
Two weeks · runs automatically on a yes

Your system on paper: the architecture, the agent roles and what each one owns, the governance model that decides what a machine may do unsupervised, and the build sequence in the order it has to happen. A document your own team, or any builder you choose, can implement.

Stage 3: The BuildQuoted against the blueprint
Its own engagement · its own agreement

The blueprint becomes a running system, built in the order it lays out. There is no number here on purpose: the build is priced against the blueprint you have already read, so neither of us prices work sight unseen. Build it with me, hand it to your own team, or take it to any builder you choose.

$12,500 total if the diagnostic says go. $5,000 if it says stop.
The signature covers Stages 1 and 2 and nothing else: the build is its own agreement, later, if you want it.
Book a Call

How the engagement runs

Length
Three weeks end to end: one for the diagnostic, two for the blueprint. Fixed dates, agreed before we start.
Sessions
Three. A kickoff, the diagnostic readout where you get the yes or no, and the blueprint walkthrough.
Your side
Your executive sponsor for 4 to 6 hours, plus about 90 minutes from the owner of each workflow in scope. Three workflows is the standard engagement, so roughly 9 to 11 hours across your whole team. Not a standing committee.
What you get
A written document at each of the two stages and a live walkthrough of the blueprint, with one revision round inside two weeks of delivery.
What you own
Your architecture, your data and your processes, outright, including the right to have any builder you choose implement them for you. The method and the system schema underneath are licensed to you for your own business, and I keep the rights to those.
Who decides
The yes or no is my professional judgment, written down with the reasoning and shown to you. You commit to the diagnostic and the blueprint when you sign: a yes commits the blueprint, a no ends the engagement at $5,000.
The diagnostic exists because the honest answer is sometimes no. If your workflows can't carry a system yet, it says so and names what has to change first. That is the finding, not a failed project, and you stop at $5,000 instead of paying for a design nobody can build against.

Start with the Diagnostic.

$5,000 for a straight yes or no on whether your business can carry one. $12,500 for the full design if the answer is yes, and the blueprint runs automatically from there. Building it is a separate quote, written against the plan you have already read.