yuri-semenenko Research
Turn a technical question into a decision you can defend: evidence from primary sources, a cited comparison, and a recommendation that states its own uncertainty. The output feeds an RFC or ADR; it is not the decision document itself. Depth is proportional to the blast radius of the decision.
The Loop
- Frame the question and the criteria that will matter — those become the matrix columns. If the question is too broad to answer, ask one or two clarifiers and stop.
- Go to primary sources: official docs, specs, changelogs, benchmarks, the source itself, and the repo's own constraints. Date volatile facts.
- Capture evidence and cite as you go. Separate what the source says from your inference; keep a short trail of sources kept and dropped.
- Surface contradictions explicitly; what you cannot resolve becomes an open question, not a silent pick.
- Build the decision matrix: options as rows (include "do nothing / defer"), criteria as columns, cells filled with cited evidence.
- Recommend with uncertainty: the recommendation, your confidence, what would change it, and what remains unknown.
- Hand off to rfc (Options, Trade-offs) or adr (Alternatives Considered). Research is not the decision doc.
Guardrails
- Primary sources over secondary. Cite load-bearing claims; date the volatile ones.
- Not a literature review or a full report harness: bound the search to what the decision needs.
- Flag uncertainty explicitly; keep contradictions visible.
- Distinct from rfc (explores and decides at system altitude) and adr (records a settled decision). Research produces the cited evidence they consume.