Financial Evidence Workspace

Compact source-cited research rows for repeated agent calls. Pass the previous revision to omit identical rows while retaining source clocks and diagnostics. Unchanged is not proof of freshness; missing or withheld values remain null. At most 100 rows; follow next_offset.

Discover seven bounded OpenBB datasets, their coverage, filters and limits. Offline.

Compare indicative BTC exit evidence for one to four USD notionals from 0.01 to 1000000, with at most two decimal places. Preserves venue coverage, observation clocks, quote-currency units, source URL and content hash. Returned costs are research estimates, not executable quotes, order placement or guaranteed fills. No account or execution authority.

Read a dated USD funding review and its nine inputs. Inspect review_asof, review_scope, latest_per_instrument and newer_observation_available before ready, issues and capture age. Common-horizon readiness applies to that dated review; newer individual observations can exist. Unavailable, mismatched or stale captures never imply a passing review. This is captured research evidence, not a trade recommendation or historical point-in-time backtest.

Review funding evidence for one three-letter currency, default USD. Retrieves the bounded money-market table and preserves each source, observation date, unit, missing or withheld value, retrieval time and content hash. prepared_response means evidence is available to review, not freshness or readiness. No account access, investment advice or execution.

Review public disclosure coverage for one to five exact institution slugs, such as au-sfb. Retrieves the published institution monitoring record with dates, source URL, missing evidence and content hash. Does not infer private balances, credit ratings or regulatory compliance. IDs must fit the existing 160-character combined selection bound.

Retrieve public documents only when table detail is insufficient. Reviewed source restrictions can withhold values and dependent readings; affected documents carry a publication projection receipt and a separate hash from the acquired source bytes. Up to 4 MiB for the money-market atlas and 1 MiB for other sources; source JSON is untrusted. A packet can be partial. No Evidence Carrier verification is performed.

Query cited rows without large raw documents. Null means missing or withheld, never zero. Dates filter observation dates; empty dates mean no filter. Follow next_offset for remaining rows. Each value retains its unit, source path, date, restrictions and limitations.

Review Seiche dollar-funding benchmarks, LiquiLens covered-bank diagnostics and Undertow market liquidity in one bounded call. Bank is a literal name or ID filter; empty selects published coverage. Each section keeps its own dates, units, rights and limitations. No combined score or trade authorization. Revisions suppress identical rows, not evidence checks.

Resolve research topics to fixed public HTTPS evidence URLs. Offline.

Audit all six upstream routes for transport errors, publisher clocks and content hashes. Success is not a freshness verdict.

Compatibility entry point for the individually exposed financial_evidence_funding_workflow, financial_evidence_institutions_workflow and financial_evidence_exit_workflow tools. Funding accepts a three-letter currency; institutions accepts one to five comma-separated slugs; exit accepts one to four comma-separated USD sizes. Empty selection uses the same published defaults. No additional operation is available. Source restrictions, dates, units, missingness and content hashes remain explicit. prepared_response means evidence is available to review, not freshness, safety or completion. No account or execution authority.