Research Papers
26 papers — methodology, data, and conclusions you can verify
The Wrap Pattern: Commodity Integration as Invisible Infrastructure
When MCP consumption is commoditized, the strategic response is to wrap — not build — the plumbing
A structural pattern for integrating commodity MCP vendors as invisible infrastructure while preserving the client-facing surface, the Intelligence Layer margin, and the Three-Tier alignment.
The Three-Tier Framework: Database, Automation, Judgment
A structural model for agent systems, realized through Model Context Protocol
A hierarchical ontology identifying three tiers connected by typed Artifacts and spanning four cross-cutting concerns, with MCP as natural encapsulation.
Tufte for Mobile: Design Intent Across Screen Sizes
Applying Edward Tufte's principles to preserve meaning in responsive design
A methodology demonstrating how wireframe intent survives responsive transformation through five Tufte principles: data-ink ratio, sparklines, direct labeling, information density, and small multiples.
Ground: Evidence-Based Claims for AI Code Analysis
Computation-Constrained Verification Prevents False Positives in Agentic Development
A tool that blocks AI agents from claiming code is dead, duplicated, or orphaned without first computing the evidence. Now with AI-native features: batch analysis, incremental diff mode, structured fix output, and fix verification. Rated 10/10 by agent testing across two production codebases.
Recursive Language Models: Context as Environment Variable
Implementing MIT CSAIL's RLM pattern for processing arbitrarily large codebases through programmatic context navigation
This paper documents the implementation and empirical validation of Recursive Language Models (RLMs) based on MIT CSAIL research. We identified critical bugs, validated the pattern against the original repository, and demonstrated practical application for codebase analysis—processing 157K characters to find 165+ DRY violations.
Animation Spec Architecture: One Source, Two Renderers
Shared Specifications for Svelte and Remotion
A methodology for maintaining visual consistency between web animations (Svelte) and video exports (Remotion) through shared animation specifications that define what happens, while each renderer decides how.
Teaching Modalities: Finding the Right Medium for CREATE SOMETHING
Comparing Spritz, Motion Graphics, and Interactive Learning
An experiment exploring three modalities for teaching the CREATE SOMETHING philosophy: RSVP speed reading (Spritz), Vox-style motion graphics (Remotion), and interactive structured learning paths.
Agent SDK Gemini Tools Integration
Grounding AI in Codebase Reality
Technical analysis of integrating bash and file_read tools within the Agent SDK Gemini provider, focusing on implementation, safety, agentic loop patterns, and impact on research paper quality.
Beads Cross-Session Memory Patterns
Agent-Native Issue Tracking for Work Persistence
Analysis of Beads as an agent-native issue tracking system designed to ensure work persistence across AI agent sessions through Git-committed state, dependency tracking, and workflow molecules.
Webflow Dashboard Refactor: From Next.js to SvelteKit
How Autonomous AI Workflows Completed 40% Missing Features in 83 Minutes
Complete refactoring from Next.js/Vercel to SvelteKit/Cloudflare, achieving 100% feature parity while migrating infrastructure. A case study in autonomous AI workflows and systematic feature implementation.
Intellectual Genealogy: The Three Lineages
Philosophy, Writing, and Systems Thinking Foundations
Documents the complete intellectual genealogy of CREATE SOMETHING: the philosophy lineage (Heidegger → Gadamer → Rams), writing lineage (Orwell → Zinsser → Fenton/Lee), and systems lineage (Wiener → Meadows → Senge).
Spec-Driven Development: A Meta-Experiment in Agent Orchestration
When the Specification Becomes the Session: Building NBA Live Analytics as Methodology Validation
A meta-experiment testing whether structured specifications can effectively guide agent-based development, producing both working software and methodology documentation as equally important artifacts.