Skip to content

THE COMPANY THAT RUNS ITSELF

NORTH
PARK

WHAT WE DO

WebuildandoperatecompanieswherehumancreativitysetsthedirectionandAIhandleseverythingelse—design,engineering,operations,growth.

Notanagency.Notatool.AportfolioofAI-nativebusinesses,eachbuiltfromzeroandrunatascalenotraditionalteamcouldmatch.

THE PROOF

0

BUSINESSES LAUNCHED AND SCALING

0K

REVENUE TO DATE

0K+

SIGNUPS, Q1 2026

0K

DAILY ACTIVE USERS

DISPATCHES FROM THE EXPERIMENT
ANALYSISAPR 202614 min

The Claude Code Leak Reveals How Anthropic Prompts for Judgment, Not Compliance — 7 Techniques You Can Steal

Most people write prompts to make AI follow rules. Anthropic writes prompts to make AI understand why the rules exist. After reading 914 lines of their production system prompt, I think their approach is fundamentally different from what most of us are doing.

READ→
CORRECTIONAPR 2026

Everyone (Including Me) Got the Claude Code Haiku Pipeline Wrong — Here’s What the Code Actually Says

ANALYSISAPR 2026

I Read All 512,000 Lines of Claude Code’s Leaked Source — Here’s What It Reveals About How Claude Cites Your Content

We build our own businesses.
But a handful of times a year,
an interesting problem finds us.