Content Strategy
5 practical articles on content strategy from Fanpino. Latest: AI-Generated Code Quality: A 12-Point Review Checklist Before You Merge

AI-Generated Code Quality: A 12-Point Review Checklist Before You Merge
AI-written code looks finished, which is why reviewing it by feel fails. Twelve checks for pull requests an agent wrote: plan match, real tests, real dependencies, swallowed errors, duplicated helpers and permission checks.

RPI in Practice: Research, Plan, Implement with Claude Code Subagents
Part two of our RPI series: how we actually run Research, Plan, Implement with Claude Code subagents on a multi-product monorepo, and the incidents that taught us to give every agent an owner and a real check.

AI Answers With Citations, Not Guesses
General AI chatbots give confident answers about your documents, with no way to check the source. EnergyFile pairs every answer with a page-level citation back to the original document.

How a 7M-Parameter Model Outscored Much Larger LLMs on ARC-AGI (Is Bigger Still Better?)
The usual assumption in AI is that bigger is better. Yet a 7-million-parameter model, TRM, outscored LLMs like Gemini 2.5 Pro and o3-mini on the ARC-AGI-1 puzzle benchmark, and its 27M-parameter predecessor HRM beat o3-mini there too. Here is what the papers and ARC Prize's own re-tests actually show.

Context Engineering: How to Prevent AI from Generating Low-Quality Code Using the RPI Framework
Do you know why AI works great for small projects but fails in legacy codebases? Learn about Context Engineering and the RPI workflow to prevent AI from generating low-quality code (Slop).
Last updated: