About Gutierrez Public Lab

I build self-improving systems across 12+ codebases. Not as a concept: as working infrastructure with 607 tests, verified metrics, and feedback loops that make each system better without me.

The problem: nobody can see any of it. This site exists to solve a distribution problem. It turns private experiments into public stories with real outcomes you can verify.

Experiments
47
Breakthroughs
26
Pitfalls
32

Two Focuses

Learning Experiments

Every project decision becomes a testable hypothesis. Quant finance, browser automation, data quality, developer analytics: domains I had zero expertise in, tracked with research-lab rigor.

Self-Improving Agents

Systems that make themselves better. Self-improving skills, self-healing tests, self-documenting history, self-managing context, self-improving data models, self-orchestrating compute.

The Lifecycle Chain

Pitfall Idea Experiment Skill Breakthrough

Every failure eventually enables a win. The chain connects them with verifiable metrics.

This is the connective tissue. Every pitfall points to the experiment that investigated it. Every breakthrough traces back to the failure that motivated it. The chain is navigable.

The Thesis

I believe we're in a specific moment: AGI capabilities exist, but the infrastructure for individual AI behavior does not. Five pillars need to exist for AI agents to behave as individuals: personality (the foundation), persistence, memory, preferences, and social modeling.

Every project in this lab is a piece of the puzzle. Read the full thesis →

Projects (7)

Oil Model Preferences

Monte Carlo simulation for CL futures with auto-ratcheting parameters against prediction markets.

Jobs-Apply Preferences

6-channel job automation with CDP browser control, behavioral adaptation, and J-Score v2 matching.

Parallel Claude Code orchestrator with live API rate limit monitoring, spawn/kill UI, and Tauri v2 desktop.

BloomNet Memory

Unified developer intelligence system: usage analytics, dynamic session context curation with adaptive forgetting, and multi-channel agent notifications.

RedCorsair Preferences

Brand system with R-generated design tokens, Paul Tol colorblind-safe palette, publication-quality chart themes.

Quick-Fin Preferences

MCP server for QuickBooks Online. 30-iteration audit across CPA, DE, and CFO personas.

Gutierrez Public Lab Social Modeling

This site. Turns private experiments into public stories with real metrics. The distribution layer for everything else.

Tools

Knowledge Management

Obsidian vault, 609+ notes, 14 dimensions, 33 skills, BloomNet for session management

Data Visualization

R + ggplot2, Paul Tol colorblind-safe palettes, Slate brand system, 118+ charts

Site Framework

Astro + Tailwind CSS, MDX, static generation, Cloudflare Pages

AI Development

Claude Code, Dakka (parallel orchestrator), BloomNet (developer intelligence), Rust + TypeScript

Methodology

  1. Pitfalls document failures with root causes
  2. Ideas propose solutions to those failures
  3. Experiments test ideas with measurable metrics
  4. Skills codify what works into reusable patterns
  5. Breakthroughs verify the wins with before/after data

Everything lives in an Obsidian vault connected via wikilinks and tracked with frontmatter schemas. This site syncs from that vault, transforms the content, and generates publication-quality visualizations using R and ggplot2.