Resources

Tools, prompts, and reusable artifacts from this project.

AI Research Methodology

A unified research methodology for AI agents combining nine intelligence and scientific frameworks into an evidence-based process. It makes AI produce defensible, auditable research instead of building a case for whatever you expect to hear.

The methodology combines ICD 203 (intelligence analysis), GRADE and Cochrane (clinical medicine), IPCC (climate science), PRISMA and ROBIS (systematic review), NAS (institutional standards), and Chamberlin/Platt (philosophy of science) into a single machine-executable prompt. It includes explicit anti-sycophancy constraints — telling the AI not just what to do, but what it is prohibited from doing and why.

Available as a Claude Code plugin, a standalone prompt for any AI interface (Claude, ChatGPT, Gemini), or a standalone file you can paste into any conversation.

Repository: https://github.com/wphillipmoore/ai-research-methodology

The detailed background — the framework evaluation, the design decisions, and the evidence for every feature — is documented in:

• The Truth is Out There. But How Do You Find It? — the what and the why (Part 1)
• The Truth is Out There. Now Go Find It. — the how and how to get it (Part 2)