Skip to Content (Press Enter)
Community › Forge › Assets list › Banking Policy & Support Agent
Login to follow
Banking Policy & Support Agent

Banking Policy & Support Agent (ODC)

Supported
Stable version 0.2.0 (Compatible with ODC)
Uploaded on 23 Apr by OutSystems
Banking Policy & Support Agent

Banking Policy & Support 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: CallBankingPolicySupportAgent

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

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): The user’s question (and any short clarifying context for this run).
SessionId (Text): Conversation or trace session identifier (for correlation/logging).
GroundingData (Data Type: Text): Optional structured or semi-structured payload your integration treats as extra context (for example, a product code or channel). The agent still treats the uploaded banking documents as the authoritative source for factual claims.
Documents (Data Type: DocumentStruct List): Banking documentation to ground answers: 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): Explainer output. The format or schema can be defined in the Output section of the AgentDefinition. By default this is a single Markdown document (not JSON): title `# Banking Terms -- {Product/Account}`, then sections Answer, Key Terms, Rules, Rate & Fee Summary, Edge Cases, Conflicts, Not Specified, Assumptions, Regulatory References, and Next Steps, with None. where a section has no applicable rows or bullets. Factual claims in the answer use inline anchors such as `[doc_name | section/heading | page/loc | short snippet]`. Parse or render this text as Markdown in your consumer module; you are responsible for correctness, auditability, and any business or regulatory use of the result.