Intelligence · Component · investment-research-qa
Evidence-grounded investment Q&A
What it does
Assemble normalized asset, disclosure and intelligence context for research questions and replay insights with provenance and trust assessments.
Core pattern
Selected entities and evidence assembly + traceable answers
- Input
- Research question and selected assets/evidence
- Output
- Structured answer, citations and trust metadata
Key parameters
| Name | Type | Default | Values |
|---|---|---|---|
| question | string | — | — |
| symbols | — | — | — |
| context_filters | — | — | — |
| artifact_session_references | — | — | — |
| model | — | — | — |
Maturity and limits
Research/context/evidence services with isolated tests; deterministic fallback supported. Static source inspection only; no runtime, provider, deployment or test-pass claim.
No project license found. External market/news data have licensing, rate-limit and availability constraints. Research only: no trading execution. Backtests can be biased and cross-asset semantics vary. Static inspection; tests not run.
Used in pipelines
Industry tags
- FinanceSource-supported industry
For work involving research materials and financial service operations, use selected entities and evidence assembly followed by traceable answers.
- Legal servicesTransferable use
For ongoing research into case issues and regulatory materials, use selected entities and evidence assembly followed by traceable answers.
Skills pack
Contract scaffold and deterministic mock
Download · 10KBSHA-256 aff4c383bed3e96b73afdd22f1352f5f466df36c462487ce115c8c4125b1d040
Related components
-
Image and text product similarity search
Shared image-text retrieval + similarity tiers and attribute filters
Working 1 pipeline -
Hotel benefit evidence and comparison
Side-by-side benefit facts + commitment status distinction
Working 1 pipeline -
Multilingual hybrid retrieval and online reindexing
Multi-route retrieval fusion + access filters and index switching
Working not yet in a pipeline -
Disclosure collection and text extraction
Document index collection + cleaned text and normalized references
Working 1 pipeline