Skip to Content (Press Enter)
Community › Forge › Assets list › Banking Document Intelligence Agent
Login to follow
Banking Document Intelligence Agent

Banking Document Intelligence Agent (ODC)

Supported
Stable version 0.2.0 (Compatible with ODC)
Uploaded on 23 Apr by OutSystems
Banking Document Intelligence Agent

Banking Document Intelligence Agent (ODC)

Documentation
0.2.0

Customer environment: Import or clone this Forge module into your factory. Your team attaches models, supplies grounding data and documents, integrates callers, and validates outputs. OutSystems does not manage your deployed copy.

To install this Agentic app, you must have the AI Trial Model used in the app (TrialClaudeHaiku4_5) added to your tenant. To do this:

  1. Go to AI Models on ODC Portal.
  2. Click on Add AI Model.
  3. Add the available trial model on the Trial Models tab.

After publishing it for the first time, you can now change the AI model of the agent to one of your organization’s approved models.

To see one example of usage of this pattern, install the companion app Banking Agents Showcase.


Entry point: CallBankingDocumentIntelligenceAgent

Other modules, processes, or UI in your application should call this Agent only through the public service action CallBankingDocumentIntelligenceAgent.

Contractual, regulatory, and oversight responsibility for how it is used remains with you as the customer developer and operator.


Input parameters:
UserInput (Data Type: Text): Optional user message or instructions for this run (e.g., context for the model).
SessionId (Text): Conversation or trace session identifier (for correlation/logging).
GroundingData (Data Type: Text): Structured or semi-structured payload, the agent should treat as authoritative context — typically the Loan Application Object (and optional Field Validation Matrix) as JSON or text, as your integration defines. E.g., "Loan Application for John Snow"
Documents (Data Type: DocumentStruct List): Supplied Documentation: each item has Type, FileName, and Binary (file content).
Profile (Data Type: AgentProfile): Overrides default agent behavior (tone, verbosity, reasoning depth, risk tolerance, action autonomy, proactivity).
AgentDefinition: (Data Type: AgentDefinition): Optional per-call Agent configuration - extensions for Goal, Workflow, Knowledge, Tools, and Guardrails (appended to default values); OutputDefinition (overrides default values).

Output parameters:
Response (Data Type: Text): Validation result. The format or schema can be defined in the Output section of the AgentDefinition. Defaults to a single raw JSON string (not wrapped in markdown), with the following sections: Recommendation, Title, Description, DataSummary — all required; no extra keys. Parse this text as JSON in your consumer module; you are responsible for correctness, auditability, and any business or regulatory use of the result.