Sigillum Finans
TRContact us

SIGILLUM FİNANS

AI transaction traceability for financial institutions

Connect model responses, service calls and version references to each transaction. Review record integrity and coverage gaps within your institution’s own environment.

Explore the productView example workflow↓

For banks and financial institutions.
Deployed within the institution’s network.

Institution-hosted
Cryptographic integrity
Offline verification
Multi-language integration

01 / PRODUCT CAPABILITIES

Transaction context,
integrity and coverage

01

Transaction context

Review inputs, model responses, document versions and service calls as related records within a transaction.

02

Record integrity

Verify accepted records through cryptographic signatures, an evidence chain and separate witness records.

03

Source-record comparison

Compare selected trace fields with the institution’s corresponding source record. Review matches, differences and missing values.

02 / TRANSACTION REVIEW

ILLUSTRATIVE WORKFLOW

Review the records
behind an AI response

Select a workflow to examine the relationship between inputs, reference documents, service calls and recorded outcomes.

TRANSACTION RECORD EXAMPLEIllustrative example
Records linked to one transaction
CONTEXT & REFERENCES↗

Documents and policies used

Review the document, policy and service responses recorded for the transaction, with their version references.

Document
Credit assessment policy
Reference
Version and content hash
Record origin
Service declaration
Retained references show which version was recorded at the time of the decision.

An illustrative example of how it works: review a request, its supporting records, model response and outcome within the institution’s configured recording scope.

HOW IT WORKS

Institutional data flow

Each layer has a defined responsibility, from collecting the trace to reviewing sealed evidence.

THE INSTITUTION’S SERVERS AND NETWORK
  1. 01
    .NET · Java · Python

    Institution applications

    Actual transaction context and related service steps

  2. 02
    Assembly and sealing

    Application layer

    Evaluates transaction completion and signs the package.

  3. 03
    Durable transport

    Apache Kafka

    Delivers sealed packages to the batch writer.

  4. 04
    Compressed transaction record

    ClickHouse

    Stores transactions and steps together for retrieval.

Review and verification run through the institution portal. Users, environments and service definitions belong to the control plane.

Technical guide
Explore the architecture and verification flow

SDKs AND INTEGRATIONS

View supported integrations
.NETJavaPythonOpenTelemetryKafkaClickHouse

04 / TEAMS AND RESPONSIBILITIES

A SHARED RECORD OF THE TRANSACTION

For technology,
risk and audit teams

01

Technology teams

Shared service integration

Integrate shared gateways and AI services once. Connect additional applications through transaction context and configuration.

02

Risk & audit teams

Evidence review

Examine decision records, assess recording gaps and verify exported evidence packages.

03

Infrastructure teams

Institution-hosted deployment

Deploy the portal, evidence store and witness within your institution’s infrastructure and operating boundaries.

SIGILLUM DEVELOPERS

Integration guides and technical reference

Step-by-step guides, language-specific SDK examples and a searchable API reference.

Open developer center

DISCUSS YOUR REQUIREMENTS

Plan an evaluation for your institution.

Bring your workflow, integration requirements and review questions. We’ll discuss how Sigillum Finans fits your environment.

Talk to our team