Methodology

Better questions lead to better research.

We publish structured analytical frameworks, not investment recommendations. AI models can be confidently wrong; our prompts are designed to make their reasoning inspectable.

Research quality over quantity

Every prompt has one analytical purpose and a defined deliverable.

Structured thinking

Prompts guide a logical process instead of inviting generic commentary.

Evidence over narratives

Primary sources, dated data, and traceable claims are required.

Honest analysis

Estimates are never presented as facts, and nothing implies guaranteed returns.

Analysis is not a decision

Each prompt separates the analytical process from the investment decision.

Prompt anatomy

Complex research uses the full structure. Simple tasks stay concise.

01Role and objective
02Research question
03Required inputs
04Research scope
05Analytical framework
06Evidence and source requirements
07Valuation or calculation methodology
08Risks and alternative explanations
09Required output format
10Limitations and final assessment

The evidence standard

Appended to every prompt in the library.

- Separate clearly: (a) reported historical facts, (b) management guidance, (c) third-party/analyst estimates, (d) your own model assumptions. Label each.
- Cite dated, traceable sources for every material claim. Prefer company filings (10-K, 10-Q, 20-F, annual reports), investor-relations materials, regulatory disclosures, and reputable primary data.
- Do not invent figures, citations, or quotes. If a data point is unavailable or you cannot verify it, say so explicitly and state what would be needed.
- Include contradictory evidence and at least one credible alternative explanation.
- State when a method is unsuitable or incomplete for this situation.
- This is an analytical exercise, not investment advice. Keep the analysis separate from any decision.