Google Developer Knowledge API: Live Documentation as MCP Infrastructure
A source audit of Google Developer Knowledge API and MCP server, evaluating live Markdown doc retrieval, 24-hour freshness, and agentic hallucination mitigation.
Fodev JEO
LATEST INVESTIGATIONS
Source audits & field notes
Stop Generating, Start Thinking: Cognitive Debt and Verification in AI Engineering
An architectural critique of blind AI code generation, examining cognitive debt, the erosion of engineering mental models, and verifier-first agent harnesses.
BMAD Method Architecture: Phase-Gated Agentic Agile and TEA Execution
A source audit of the BMAD Method, evaluating phase-gated agentic agile lifecycles, Task-Execute-Architect (TEA) loops, role specialization, and code review gates.
Edge Sandbox Engineering: Deploying Autonomous Agents on Mobile Hardware
A source audit of physical edge sandboxing for autonomous agents, evaluating Termux userlands, zero-trust network isolation, and mobile multi-agent topologies.
How Claude Code Works: The Agent Loop, Tool Dispatch, and Security Boundaries
An architectural source audit of Claude Code, deconstructing its ReAct loop, tool isolation, hierarchical memory, and permission checkpoints.
Easy Dataset: Architecture and Pipeline for Synthetic LLM Data and RAG Evaluation
A technical source audit of Easy Dataset (arXiv:2507.04009), examining persona-driven data synthesis, chunking strategies, and built-in model evaluation.
Curating Agent Skills: The Four Primitives That Survived the Proliferation
A source audit of the open-source agent skill explosion, deconstructing four enduring workflow primitives—Superpowers, Humanizer, UI-UX Pro Max, and Vercel Skills CLI.
LightRAG: Graph-Enhanced Retrieval with Dual-Level Context
A source audit of HKUDS’s LightRAG (arXiv:2410.05779), analyzing entity-relation indexing, dual-level retrieval, incremental updates, and graph vs. vector tradeoffs.
Self-Learning Skills: Autonomous Documentation Synthesis for AI Agents
A source audit of Philipp Schmid’s self-learning-skill framework and Gemini 3 tooling, analyzing autonomous search, documentation extraction, and SKILL.md synthesis.
Claude Code /insights: Analyzing Developer Telemetry and Agent Friction
A source audit of Claude Code’s /insights command, examining how local session telemetry is analyzed to detect workflow bottlenecks, intent gaps, and automation opportunities.
인기 태그
Search article titles, categories, and tags. Full text is searched when needed.
Type to search articles.