Stephen Luc · Lifecycle marketing and automation

I build the systems that help customers get started, keep learning and come back.

I’ve been building and teaching since 2003. My work brings email, courses, content and customer journeys together. I use AI agents to research and build, then check what they produce.

What I do

From a customer problem to a working system.

01

Design the workflow

Who researches, who builds, who checks, and in what order. Agents from different AI companies, each on work it can handle.

02

Give agents the right context

What to hand an agent, when to hand it over, and how to check that the next session has what it needs.

03

Check the work

Builders test and review their work first. Separate reviewers and evals add another check, with records of what actually ran.

Proof

One real run, start to finish.

On September 26, 2026, my crew reviewed Misfit Hollow, an app we built. No agent certified its own work. Every number below comes from the run’s own records.

Notebook sketch of the September 26 review in four stages: Investigate with 7 reviewers from 2 AI model families, Merge into 18 problems, Repair with 4 repair agents fixing 16 and putting 2 off on purpose, and Review by an independent checker, 86 of 86 and 49 of 49.
Fig. 1 · One review, September 26, 2026. Drawn from the run’s recorded stages.
  1. 1 · Investigate

    7 reviewers from 2 AI model families look separately, blind to each other.

  2. 2 · Merge

    Their reports merge into 18 problems and missing tests.

  3. 3 · Repair

    4 repair agents fix 16. Two are put off on purpose, named, not hidden.

  4. 4 · Review

    An independent checker confirms: 86/86 code checks, 49/49 browser checks.

What it doesn’t prove: that every run goes this well. The November 10, 2026 recount found 143 substantive workflow attempts: 105 completed, 27 failed and 11 unresolved. App work, research and discussions are counted; installation and toy checks are separate. These are attempts, not shipped apps, and the failures stay in.

See the full run →

From the Lab

We test our own tools. Here’s what we found.

We keep the failed and inconclusive results alongside the successes.

See every experiment →

Worked · October 28, 2026

Can a mistake become a test?

Two preserved failures became local reference tests. The old answer fails, the current agent passes, and the same mistake is blocked in those cases.

Mixed result · October 8, 2026

Can one UI guide help a fresh agent?

One UI guide scored higher in 5 of 30 matched comparisons, tied in 17 and lower in 8. Two CSS tasks; no consistent upgrade in this batch.

Full count · October 27, 2026

How much agent history can be checked?

56,474 verdicts over 3,322 records. 46,364 could not be verified from the available evidence.

What we’ve built

Tools my crew and I built to run the work.

Most of them started with one question: why is an agent doing this by hand?

A completed Composer workflow, showing its first stages and agents.

Archived completed workflow · not a live run

Composer

Private tool

Turns one brief into a plan a crew of agents can carry out: research, build, then try to break it. Keeps every run’s record, failures included.

Private tool, running on my own machines and connected cloud workspaces. Its page shows the parallel trials, outcomes and current limits.

How Composer works →
Notebook sketch, Fig. 1: describe the job, approve the plan, exam, receipts, and a mistake becomes a new test.

Foundry

Local prototype

Gives an agent a job, a method and a way to check its work. Two preserved failures have become local reference tests; the full live learning loop is still ahead.

How Foundry works →
A WarmStart handoff note in a terminal, from a synthetic sample repository.

Recorded terminal handoff · synthetic sample repository

WarmStart

Public release

Turns repository evidence into short handoff notes a fresh agent can read. Whether those notes improve its work still needs testing.

About WarmStart →

All tools, including what’s still in the lab →

Where it came from

Same job, bigger tools.

I’ve always been the person who automates the business behind the product. The crew used to be people. Now it’s agents.

Steve wearing glasses and an orange shirt against a charcoal background.
Stephen (Steve to the crew) · AI-edited portrait

Since 2003

450+ video courses and launches

Built a video-training business and partnered on products with Russell Brunson, Jeremy Gislason and Simon Hodgkinson. My courses have reached 26,919 learners on Udemy ↗.

Earlier marketing work

An audience I could reach directly

I built a list of about 9,000 internet marketers and had top-3 affiliate finishes.

Watercolor Misfit

A creative community

I co-own Watercolor Misfit, whose YouTube channel has 182K subscribers. I work on the systems behind its courses and community.

Teaching

A university help desk

Helped faculty and students use the systems we built. That’s where I learned to explain hard things simply.

Now

Leading a crew of AI agents

Designing the workflows, the context and the checks, and building the tools when they don’t exist yet. My story →

Audience figures updated November 3, 2026.

Need help with lifecycle marketing or automation? Let’s talk.

Email, onboarding, content reuse, or a customer journey that needs clearer steps. I can help map the work and build what’s missing.