concordancehq.duckdns.org

The cross-category synthesis endpoint: one call replaces manually calling /tools/search once per category and merging results yourself. Deliberately NOT an LLM-generated summary -- pure structured aggregation of real search hits, keeping the same zero- marginal-cost model as the rest of this service (an LLM call here would need its own paid API key and per-call cost, undermining the whole "free sources, free to run" design).

The cross-source correlation endpoint: joins market quotes (3 providers), SEC filings, and general mentions (news/academic/legal/ dev-community) for one company in a single call -- something no single-source competitor in this space can offer, since it requires owning all the underlying sources already. Partial results are normal and expected here (e.g. market data present but no recent filings) -- this endpoint aggregates across inherently-optional sources, unlike /tools/series which is about exactly one source and where "not synced yet" is a meaningful 503 signal.

Is this claim independently corroborated across multiple unrelated sources, or does it trace back to a single origin? Groups matches by SOURCE (not category, unlike /tools/digest) so a caller can see exactly how many independent outlets/agencies/publications back a claim, not just how many raw documents mention it -- the literal meaning of "concordance": where a claim is attested across a body of independently sourced texts.

How has coverage of this topic developed over time, across every aggregated source? Chronologically ordered (oldest first), unlike /tools/search (relevance-ranked) or /tools/digest (grouped by category) -- for tracking a story's evolution or an emerging trend across independently-sourced outlets.