Research Papers

18 papers — methodology, data, and conclusions you can verify

research 15 min read advanced

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.

Agent SDKGeminiTool IntegrationAgentic LoopResearch PapersCodebase Grounding
research 12 min read intermediate

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.

BeadsAgent MemoryCross-Session PersistenceIssue TrackingGit-Based StateWorkflow Orchestration
case-study 45 min read advanced

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.

SvelteKitCloudflareAutonomous WorkflowsInfrastructure MigrationFeature ParityHarnessAI-Native Development
methodology 12 min read advanced

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).

Intellectual GenealogyHeideggerOrwellMeadowsSystems ThinkingHermeneuticsWritingPhilosophy
methodology 15 min read advanced

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.

Spec-DrivenAgent OrchestrationHarnessBeadsMeta-ExperimentNBA AnalyticsTufte
research 18 min read advanced

The Norvig Partnership: When Empiricism Validates Phenomenology

How Peter Norvig's Advent of Code 2025 Experiments Confirm Heideggerian Predictions About AI-Human Collaboration

Peter Norvig's empirical findings—"maybe 20 times faster" with LLM assistance—mark the Zuhandenheit moment when a tool recedes so completely that it becomes inseparable from practice itself.

Peter NorvigAdvent of CodePartnershipZuhandenheitComplementarityHermeneutic Circle
methodology 8 min read intermediate

The Cumulative State Anti-Pattern

When "Current" Masquerades as "Ever"

How ambiguous field semantics in database design create invisible bugs that punish users for legitimate actions. A case study from Webflow template validation.

Database DesignState ManagementAnti-PatternsAirtableValidation
research 15 min read intermediate

The Subtractive Studio: Philosophy as Infrastructure

Most Agencies Add. CREATE SOMETHING Removes What Obscures.

A positioning paper establishing CREATE SOMETHING's differentiation: philosophy as infrastructure, not marketing. The Subtractive Triad applied to agency practice.

Subtractive TriadAgency PositioningPhilosophyHermeneutic CircleDieter RamsHeidegger
case-study 12 min read intermediate

The Hermeneutic Triad

How Reviewers, Harness, and Agent Collaborate

Case study of parallel peer review identifying DRY violations through the hermeneutic triad of reviewers, harness, and agent.

Peer ReviewDRYHarnessArchitecture Review
case-study 12 min read intermediate

Harness Agent SDK Migration: Empirical Analysis

Security, Reliability, and Cost Improvements Through Explicit Tool Permissions

Empirical analysis of migrating from --dangerously-skip-permissions to --allowedTools in autonomous Claude Code orchestration.

Agent SDKClaude CodeHarnessAutonomous OrchestrationTool Permissions
research 15 min read advanced

The Autonomous Harness

Agent Orchestration with Human Agency—how progress reports enable reactive steering without proactive management.

Applying Heidegger's dwelling concept to autonomous agent systems, demonstrating how progress reports preserve human agency through reactive oversight.

Autonomous OrchestrationAgent OrchestrationHeideggerDwellingProgress Reports
research 20 min read advanced

From Learning About to Dwelling Within

Agentic Engineering as Methodology Transfer in the Terminal

Examining how Claude Code can transfer CREATE SOMETHING methodology through agentic engineering, transforming passive learning into active ethos adoption.

EthosMethodology TransferClaude CodeMCPDwelling