Loan Processing

Persona

Role: Solutions architect at a community credit union consortium (12 credit unions, 300 employees total) building a shared loan origination platform.

Each credit union operates as a separate tenant with its own underwriting criteria and member data. The shared platform reduces development costs while maintaining complete data isolation between institutions.

Business Problem

Loan applications move through multiple stages -- intake, credit evaluation, underwriting, and disbursement -- often across disconnected spreadsheets and email threads. Loan officers lack real-time visibility into application status, and credit check results are manually copied between systems. This scenario builds a structured loan processing pipeline where applications flow from submission through approval to disbursement with full traceability.

Four-Step Application

This scenario works best as a four-step, human-in-the-loop application. The existing object model already gives this scenario a strong delivery backbone through LoanApplication, CreditCheck, and Disbursement.

• Mission metric focus: faster cycle time, better compliance quality, and stronger revenue or loss performance.
• Human + AI pattern: Each step combines structured workflow data with chat assistance, background generation, document understanding, and accessible interaction patterns when they improve the experience.

Step 1. Capture demand and context

• Goal: Make it easy for the user to start the Loan Processing journey with complete, trusted context.
• Required data: LoanApplication context such as applicant, amount, term, and purpose.
• AI support: Use chat to guide intake, generate clearer prompts, create accessible summaries, and assist with voice or vision-led capture when a form alone is not the best experience. EAI can support structured intake, chat workflows, and document-centred capture today; richer native multimodal capture may still need workflow extensions or connected services.
• Business impact: Improve completion rate, reduce first-touch effort, and raise customer or staff confidence in the UX from the very first interaction.
• EAI delivery: Model the intake as tenant-isolated object types and resources, then use actions, chat workflows, and document indexing or classification to keep the initial record complete and usable.

Step 2. Prepare the decision

• Goal: Turn the captured context into the next best action for Loan Processing without forcing the human reviewer to assemble the case manually.
• Required data: LoanApplication state and history; CreditCheck fields such as score, report, date, and bureau.
• AI support: Run background summarisation, extraction, classification, recommendation drafting, and answer generation so a reviewer sees a prepared case instead of raw fragments. EAI delivers the structured records and AI workflow hooks for this today; specialised scoring engines, external rules, or advanced reasoning controls may still need integration work.
• Business impact: Reduce cycle time, improve quality and consistency, and protect the mission-critical metric before the case moves into execution.
• EAI delivery: Link records across the scenario, persist decision state as resources, and use workflow actions plus chat assistance to keep humans in control while AI prepares the work.

Step 3. Execute and collaborate

• Goal: Coordinate the actual work, handoffs, approvals, and user updates needed to deliver the service or outcome.
• Required data: CreditCheck actions such as runCreditCheck; Disbursement fields such as amount, method, date, and status.
• AI support: Draft replies, produce work packets, monitor exceptions in the background, and surface the next action for each operator. EAI can orchestrate tenant-isolated records, actions, chats, and document workflows today; deeper system-to-system automation may require additional connectors or workflow capability.
• Business impact: Increase operator productivity, reduce rework across handoffs, and improve service consistency across the application journey.
• EAI delivery: Use linked object types, actions, resource updates, and workflow-triggered AI assistance so the team can execute in one model instead of splitting work across disconnected tools.

Step 4. Resolve, explain, and improve

• Goal: Close the loop with a clear outcome, an understandable explanation, and feedback that improves the next case.
• Required data: final status, outcome, audit history, and follow-up signals across LoanApplication, CreditCheck, and Disbursement.
• AI support: Generate outcome summaries, customer-friendly answers, compliance-ready notes, management insights, and accessible follow-up content. EAI can store outcome records and support answer generation today, while richer proactive agents, advanced analytics, or channel-specific accessibility features may need additional product capability.
• Business impact: Increase trust, quality, and measurable business value through faster cycle time, better compliance quality, and stronger revenue or loss performance.
• EAI delivery: Keep the full audit trail in structured resources, use AI workflows to explain outcomes, and feed the resulting signals into future product, service, and operational improvement work.

EAI Platform Support By Step

EAI provides the safe service boundary for Loan Processing through Object Types, tenant-scoped resources, document processing, chat workflows, and CLI verification. For this scenario, the main records are LoanApplication, CreditCheck, and Disbursement.

Process step	What EAI provides	Calling pattern
Step 1. Capture demand and context	Tenant-scoped intake resources for LoanApplication context such as applicant, amount, term, and purpose. Object Type validation, starter forms, optional document intake, and chat-guided capture keep the first record complete.	Define fields in src/eai.config/object-types.ts, run eai types validate and eai types seed, create initial LoanApplication records with useResources('LoanApplication') or eai resources create LoanApplication, and keep browser calls behind /api/eai/....
Step 2. Prepare the decision	Linked resource queries over LoanApplication state and history; CreditCheck fields such as score, report, date, and bureau. Search, schema checks, document classification or RAG indexing, and chat summaries turn raw context into a prepared decision.	Use useResources('LoanApplication') list/query/search patterns, verify shape with eai resources schema, use useDocuments().upload/classify/ragIndex, eai docs upload, eai docs classify, and eai docs index where supporting material exists, and send decision-support prompts through useChat(workflowId, 'chat') or eai chat send.
Step 3. Execute and collaborate	Resource updates and actions for CreditCheck actions such as runCreditCheck; Disbursement fields such as amount, method, date, and status. Status changes, assignments, notes, generated work packets, and chat support keep humans in control during execution.	Model actions in the Object Type code, call client.resources.executeAction(type, id, action) or the app hook equivalent, update records through the app service layer, and verify with eai resources get/list/query.
Step 4. Resolve, explain, and improve	Outcome resources for final status, outcome, audit history, and follow-up signals across LoanApplication, CreditCheck, and Disbursement. Audit-friendly links, indexed final documents, reporting snapshots, and answer generation make the result explainable and reusable.	Persist outcomes as resources, index final material with eai docs index or useDocuments().ragIndex, send explanation prompts with useChat or eai chat stream, and use eai resources aggregate/search for reporting checks.

Prompt, Code, And Service Pattern Mapping

The Object Type code example on this page is the implementation contract for the EAI platform services. eai-gofer should read that code as the source of truth for which resource, document, and chat calls belong in the app.

Use this prompt shape when asking eai-gofer or another coding agent to implement the scenario:

Use the EAI App Template. Model Loan Processing with Object Types for LoanApplication, CreditCheck, Disbursement. Use useResources for records and actions, useDocuments for uploads/classification/RAG where documents appear, useChat for workflow assistance, and verify with eai types/resources/docs/chat commands. Use eai publicapi only when no named command covers the required platform call.

Scenario artifact	How it maps to EAI service calls
Four-step process	Step 1 becomes resource creation, Step 2 becomes resource query/search plus optional document or chat preparation, Step 3 becomes resource update/action calls, and Step 4 becomes outcome persistence plus explanation/reporting calls.
Object Type definitions	eai types validate, eai types seed, and eai resources schema make the model available and checkable before UI work starts.
Properties and indexes	Fields become useResources payloads, filters, list views, and eai resources create/list/query/search checks. Indexed fields should support lookup and triage, not duplicate canonical records.
Links between Object Types	Relationships become linked-resource UI, timeline context, and audit trails that app code loads through resource queries rather than separate bespoke stores.
Actions and status fields	Workflow buttons and operator transitions call resource action/update helpers, then verify state with eai resources get/list/query.
Document and chat prompts	Prompts should call the platform documents and chat patterns: useDocuments().upload/classify/ragIndex, eai docs upload, eai docs classify, and eai docs index for documents, and useChat, eai chat send, or eai chat stream for conversational assistance.

Object Types

Name	Key Properties	Links	Actions
LoanApplication	applicant (text), amount (number), term (number), purpose (select: home, auto, personal, business), status (select: submitted, under-review, approved, denied, disbursed)	one-to-many → CreditCheck, one-to-many → Disbursement	reviewApplication
CreditCheck	score (number), report (text), date (date), bureau (text), debtToIncomeRatio (number)	many-to-one → LoanApplication	runCreditCheck
Disbursement	amount (number), method (select: ach, wire, check), date (date), status (select: pending, processed, failed), referenceNumber (text)	many-to-one → LoanApplication	processDisbursement

CLI Workflow

1. Scaffold the project

   eai init loan-processing

2. Authenticate and pull environment

   eai login
   eai env pull --include-secrets

   If you are an external developer, see [Configuration](/docs/configuration) for login and local environment setup.

3. Define your Object Types

   Create the LoanApplication, CreditCheck, and Disbursement types in src/eai.config/object-types.ts (see code example below).

4. Validate the type definitions

   eai types validate

   Tenant: loan-processing
   ✔ LoanApplication — 5 props, 2 links, 1 action
   ✔ CreditCheck — 5 props, 1 link, 1 action
   ✔ Disbursement — 5 props, 1 link, 1 action
   
   ✔ All Object Types are valid

5. Seed types to the platform

   eai types seed

6. Create a sample loan application

   eai resources create LoanApplication --data '{"applicant": "Maria Gonzalez", "amount": 25000, "term": 60, "purpose": "auto", "status": "submitted"}'

7. Query applications by status

   eai resources list LoanApplication

8. Start local development

   eai dev

Code Example

// src/eai.config/object-types.ts
export const objectTypes = {
  'loan-processing': [
    {
      name: 'LoanApplication',
      displayName: 'Loan Application',
      description: 'A loan application submitted by a member for underwriting review',
      properties: [
        { name: 'applicant', type: 'text' as const, required: true, indexed: true },
        { name: 'amount', type: 'number' as const, required: true },
        { name: 'term', type: 'number' as const, required: true },
        {
          name: 'purpose', type: 'select' as const, required: true,
          options: [
            { label: 'Home', value: 'home' },
            { label: 'Auto', value: 'auto' },
            { label: 'Personal', value: 'personal' },
            { label: 'Business', value: 'business' },
          ],
        },
        {
          name: 'status', type: 'select' as const, required: true,
          defaultValue: 'submitted',
          options: [
            { label: 'Submitted', value: 'submitted' },
            { label: 'Under Review', value: 'under-review' },
            { label: 'Approved', value: 'approved' },
            { label: 'Denied', value: 'denied' },
            { label: 'Disbursed', value: 'disbursed' },
          ],
        },
      ],
      linkTypes: [
        { name: 'creditChecks', targetObjectType: 'CreditCheck', cardinality: 'one-to-many' as const },
        { name: 'disbursements', targetObjectType: 'Disbursement', cardinality: 'one-to-many' as const },
      ],
      actions: [
        {
          name: 'reviewApplication',
          displayName: 'Review Application',
          description: 'Advance the application to the next stage of the underwriting pipeline',
          inputs: [
            { name: 'decision', type: 'select' as const, required: true },
            { name: 'notes', type: 'text' as const, required: false },
          ],
        },
      ],
      status: 'published' as const,
    },
    {
      name: 'CreditCheck',
      displayName: 'Credit Check',
      description: 'A credit bureau inquiry associated with a loan application',
      properties: [
        { name: 'score', type: 'number' as const, required: true },
        { name: 'report', type: 'text' as const, required: true },
        { name: 'date', type: 'date' as const, required: true },
        { name: 'bureau', type: 'text' as const, required: true },
        { name: 'debtToIncomeRatio', type: 'number' as const, required: true },
      ],
      linkTypes: [
        { name: 'loanApplication', targetObjectType: 'LoanApplication', cardinality: 'many-to-one' as const },
      ],
      actions: [
        {
          name: 'runCreditCheck',
          displayName: 'Run Credit Check',
          description: 'Initiate a credit bureau inquiry and record the results',
          inputs: [
            { name: 'bureau', type: 'text' as const, required: true },
            { name: 'applicantId', type: 'text' as const, required: true },
          ],
        },
      ],
      status: 'published' as const,
    },
    {
      name: 'Disbursement',
      displayName: 'Disbursement',
      description: 'A funds disbursement for an approved loan application',
      properties: [
        { name: 'amount', type: 'number' as const, required: true },
        {
          name: 'method', type: 'select' as const, required: true,
          options: [
            { label: 'ACH Transfer', value: 'ach' },
            { label: 'Wire Transfer', value: 'wire' },
            { label: 'Check', value: 'check' },
          ],
        },
        { name: 'date', type: 'date' as const, required: true },
        {
          name: 'status', type: 'select' as const, required: true,
          defaultValue: 'pending',
          options: [
            { label: 'Pending', value: 'pending' },
            { label: 'Processed', value: 'processed' },
            { label: 'Failed', value: 'failed' },
          ],
        },
        { name: 'referenceNumber', type: 'text' as const, required: false },
      ],
      linkTypes: [
        { name: 'loanApplication', targetObjectType: 'LoanApplication', cardinality: 'many-to-one' as const },
      ],
      actions: [
        {
          name: 'processDisbursement',
          displayName: 'Process Disbursement',
          description: 'Execute the funds transfer and record the reference number',
          inputs: [
            { name: 'method', type: 'select' as const, required: true },
            { name: 'amount', type: 'number' as const, required: true },
          ],
        },
      ],
      status: 'published' as const,
    },
  ],
};

Key Takeaways

• Full origination pipeline: The LoanApplication, CreditCheck, and Disbursement types model the complete loan lifecycle from submission through funds transfer, replacing fragmented spreadsheet workflows.
• Credit check integration: The runCreditCheck action captures bureau-specific scores and debt-to-income ratios, giving underwriters structured data for consistent decision-making.
• Consortium model: Each credit union operates in its own tenant with independent underwriting criteria, while sharing the same platform infrastructure and codebase to reduce costs.
• Disbursement traceability: Every fund transfer is recorded with method, reference number, and status, providing a complete audit trail from approval to payment.