deep-research
Deep Research
Run adaptive, evidence-backed research across broad source classes while keeping claims auditable. The goal is not a fixed number of hops: search widely enough, verify strongly enough, and stop when the answer is well supported or the remaining uncertainty is explicit. Keep private reasoning concise; record public, auditable artifacts: queries, sources, claims, limitations, and evidence IDs.
When to activate, and at what effort
Do not activate for a simple fact, rewrite, translation, summary of provided text, or casual chat — or when the user says to answer only from provided material. If borderline, prefer a quick normal answer unless the user asks for citations, verification, current information, source comparison, or decision-grade evidence.
Otherwise pick effort by risk and ambiguity:
| Effort | Budget | Use for |
|---|---|---|
quick |
2-4 hops, 2+ source classes | narrow, low-risk verification or citations |
standard |
5-8 hops, 3+ classes | researched synthesis, current-info checks, tool comparison, claim verification |
deep |
9-14 hops, 4+ classes | literature review, paper review, GitHub due diligence, implementation recommendation, local files + web verification |
exhaustive |
15+ hops or user budget, 5+ classes | high-stakes, contested, fast-changing, or legal/medical/financial/security-sensitive topics; explicit requests for comprehensive coverage |
If the user did not specify scope, infer a reasonable one, state the assumption briefly, and proceed. Ask for clarification only when the missing detail would change the research target or make the answer unsafe.