Skip to main content

Finance Data Flow

What entities exist, how they relate, and how a single fact moves from a raw filing into a binding decision.

Naming System

Every entity in finance is named by whoever has the most power to enforce the name. The name hides where the power actually sits.

  • Security — named by the issuer; the legal definition lives in the prospectus
  • Counterparty — named by the regulator; the identity check lives in the KYC file
  • Position — named by the custodian; the legal owner is whoever the custodian's ledger says it is
  • Cash flow — named by the accountant; the timing depends on which standard the firm applies
  • Risk — named by the model owner; whichever model is signed off becomes the firm's truth

The agentic shift renames two of these. Position moves from the custodian's ledger to the wallet's signature. Counterparty moves from a legal entity to a verified-agent credential under a named human driver.

Data Model

Finance data has five entities. Every workflow is a path through them.

EntityDefinitionPrimary keysLives on
IssuerLegal entity that creates the security or tokenLEI, ticker, contract addressRegistry or blockchain
SecurityThe instrument itself — equity, debt, tokenCUSIP, ISIN, token addressRegistry or contract
CounterpartyWho is on the other side of the tradeLEI, wallet, verified-agent credentialKYC file or chain
PositionThe holding — who owns what, how much, whenAccount ID + security ID, or wallet + tokenCustodian or wallet
Cash flowThe economic outcome — coupon, dividend, fee, yieldDate + amount + sourceGL or on-chain event

State Transitions

A finance fact moves through five states. The state model is invariant across both rails.

  1. Raw — the filing, transcript, or block event arrives. Untrusted.
  2. Structured — mapped to the firm's schema. Each field has a source citation.
  3. Reconciled — cross-checked against an independent source. Variance recorded.
  4. Signed — qualified human approves before it binds a decision.
  5. Bound — the fact is now an obligation, a position, or a precedent.

Step four is the gate. The agentic shift compresses steps one through three; it does not remove step four. Step five is the only state the regulator and the auditor recognise as final.

Data Footprint — Schema to Feedback

The maturity of any finance data flow is set by how far it travels through the footprint. Most firms stall between Schema and API. The agentic shift demands all five.

LayerWhat it means in financeTypical maturity (today)Agentic-era requirement
SchemaField names, types, constraintsMature for filings; weak for on-chainBoth rails on one schema
DataThe values populated, with provenanceMature for prices; weak for intentEvery fact carries its source date
APIProgrammatic access, versionedMature for market data; uneven for filingsStable, agent-accessible
UIHuman-readable surface for reviewMature for terminals; poor for receiptsReceipt-first, table-second
FeedbackThe loop: model output → reality → recalibrationWeak — variance reports often unreadContinuous; agent-driver reads variance daily

A firm that closes the Feedback layer first wins the next decade. Most firms have never tried, because the loop requires admitting the model was wrong.

Decisions Data Drives

Each entity supplies the input to a specific decision. Map the decision to the entity before building the model.

EntityDecision it informsAction it triggers
IssuerShould we underwrite or partner?Coverage call, NDA, IC pre-screen
SecurityWhat is it worth, and what is the risk?Valuation, position sizing, hedge
CounterpartyCan we transact safely?Onboarding, line limit, settlement instruction
PositionAre we exposed where we expect?Risk report, margin call, rebalance
Cash flowDid reality match the model?Variance commentary, reforecast, post-close review

Provenance Becomes the Audit Trail

When an agent runs the model, the receipt is the audit trail. Three fields make a receipt audit-grade:

  1. Inputs — every value the agent used, with a source citation and a timestamp
  2. Prompt + version — the exact instruction the agent received, hashed
  3. Output + sign-off — what the agent returned and who bound it

A receipt missing any one of these is not yet an audit trail. It is a draft.

Context

Questions

What does the data layer look like when the agent is one of the readers — and one of the writers?

  • Which of your five entities still lives in a system that cannot emit a receipt?
  • Which decision in your firm runs on data with no provenance trail?
  • Where does your variance report die before it reaches the model owner?