Problem
Community lenders lose applicants to friction. A standard small-business loan inquiry takes days just to receive a preliminary yes/no, because intake staff must manually collect financials, run scoring models, and compile document requests. Applicants abandon and go to fintechs that give instant answers. Meanwhile, loan officers spend the majority of their time on applications that will never qualify.
Solution
An AI agent inside Salesforce that takes a loan applicant from first contact to a pre-qualification decision. It collects financials through a guided conversation, runs a deterministic scoring engine, and returns an instant Qualified, Conditional, or Declined decision, along with a tailored document checklist.
Demo
What the demo shows
- Pre-qualification runs on submission
- 6-document auto-checklist per qualification tier
- 4 lending workflows automated
Four Agent Script topics with a linear intake flow: (1) Identity Verification collects applicant email, calls VerifyApplicant Apex action (Contact → active Application → Account chain), binds applicant_id as a session guard for all downstream actions. (2) Pre-Qualification Scoring collects annual revenue, years in business, and requested loan amount via guided conversation. A deterministic Apex scoring engine applies three-tier logic: Qualified (revenue ≥ 3× loan AND ≥ 2 years in business), Conditional (meets one criterion), Declined (meets neither). No LLM involvement in the decision. Creates a Loan_Application__c record with score, tier, and timestamp. (3) Document Checklist: based on the qualification tier, it generates a tailored checklist: Qualified applicants get the standard 6-doc package (tax returns, bank statements, P&L, balance sheet, business license, personal guarantee). Conditional applicants get the standard package plus additional collateral documentation. Declined applicants receive denial reasoning and next-step guidance. (4) Application Status queries Loan_Application__c for existing applications, returns status, document completion percentage, and estimated timeline. Auto-lookup pattern: Status topic calls the action immediately on entry since applicant_id is already bound.
Tech Stack
- Salesforce Agentforce
- Agent Script DSL
- Apex
- Autolaunched Flows
- SOQL
- ExternalCopilot
- EinsteinServiceAgent
- Custom Objects