Run multiple targeted searches and return raw results grouped by section.
The caller defines all sections and queries — this tool does not decide what is
relevant. Before calling, reason about which topics and data sources matter for
this specific company: financial metrics, risk factors, sector-specific macro
drivers (e.g. freight rates for shipping, power prices for aluminium smelters),
recent press releases, peer context, etc. Formulate one query per section.
Each query is run independently as a full hybrid search (dense + sparse + rerank).
Results are raw chunks — the caller is responsible for synthesis.
For a fully orchestrated due diligence report (AI-planned sections, synthesized
narrative), use the Alfred MCP server instead: alfred.aidatanorge.no/mcp
IMPORTANT — use 'ticker' on company-specific sections to avoid false positives.
Without a ticker filter, documents that merely mention the company (e.g. as a
customer or competitor) can rank above actual filings from that company. Omit
'ticker' only for sections where cross-company results are intentional, such as
sector macro context or peer comparisons.
Args:
company: Company name, used for metadata only (not a filter).
sections: Up to 8 sections. Example:
[
{"name": "financials", "query": "Equinor revenue EBITDA operating profit 2024", "ticker": "EQNR"},
{"name": "risk", "query": "Equinor climate regulatory risk stranded assets", "ticker": "EQNR"},
{"name": "macro", "query": "Brent crude oil price energy sector Norway 2024", "limit": 3},
{"name": "news", "query": "Equinor press release dividend acquisition 2024", "ticker": "EQNR"}
]
Returns:
Dict with 'company', 'generated_at', and 'sections' — one entry per requested
section with its name and results (same format as search_filings).
Sections with no results return an empty list.
