How we think about AI-native work, what we run on, what we ship, how we plan, and how it lasts past anyone's departure. Every protocol has its own page.
Content management systems were built for a world where humans typed into boxes. AI generates, structures, and updates content directly. The CMS is now the model plus a folder of context.
Four tools, one operating model. Claude is the AI partner, GitHub is version control, Vercel is deployment, Supabase is the database. Master these four and you can build almost anything.
An agent is not a magical entity. It is a folder of markdown files plus a prompt. Structure the folder well and the agent works. Structure it badly and it does not.
How we lay out a project so agents can navigate, find context, and make decisions. Naming conventions, context files, status files: the boring parts that make everything else work.
Branching, committing, pulling, and merging discipline. The basics that let multiple people, and multiple agents, work in parallel without losing each other's work.
How deployments work, how custom domains attach, and the DNS basics you need so a site goes live cleanly the first time.
Tables, rows, columns, relationships, and row-level security. Enough of the data model to read, write, and reason about a database without breaking it.
Give Claude a design system and the output stays on-brand and consistent. Tokens, components, examples: what to feed in so what comes out matches.
Designing repeatable agent-friendly workflows that turn intent into output. The shape of a good workflow, the failure modes of a bad one.
How to send messages programmatically. Resend for transactional email, SMS providers for text, and the patterns for templating, deliverability, and opt-out.
Building internal tools (CRMs, dashboards, lightweight admin UIs) so the team can read and write data without escalating to engineers.
How we break vague ideas into epics, epics into tasks, and tasks into something a team can actually ship in a week.
A single HTML file per project that tracks epic progress in plain sight (what is done, what is next, who is stuck), readable by humans and agents alike.
Use a PM agent to set, prioritize, and review your daily work. The agent holds context across days so you do not have to re-explain yourself every morning.
When to escalate, how to brief, what to bring to the conversation. Engineers are a force multiplier. Used well, they unblock you in minutes instead of days.
Three humans, eight agents, one team. The founder, a subject matter expert at the founder's company, and an AI engineer. PM, developer, QA, writer, designer, web publisher, email marketer, and DevOps are all AI agents.
Where AI can self-test (correctness, regressions, completeness) and where humans still must (UX, taste, judgment calls). Knowing which is which saves hours.
How to hand off agent context, memory, and project state to the next person, so the work survives a transition without a knowledge tax.
At the Infinite Leverage retreat you walk all 18 protocols in 48 hours in the room, on a brand-new Mac Mini, building your own site, your own CRM, and eight working agents.