- Intake
- Verify
- Pre-approved
- Sign
- Disb.
CRM for financial work · Human–AI collaboration
Turning experience in financial work into systems where people and AI work together.
gentry fixes the tangled workflows and information problems of existing customer-management systems. We work from workflow diagnosis and CRM design through building AI-assisted features, verification and roll-out.
Customer record
- Customer
- 000011222 · 2 earlier applications
- Phone
- 000011222
- Owner
- Team 2 · Staff 01
- Status
- Signing booked
- Next
- Oct 14, morning signing
- Documents
- Lease checked · income proof pending
Linked history
- 10.08 14:20Call: confirmed balance date, asked for income proofStaff 01
- 10.08 14:22Appointment: signing on 10.14
- 10.07 17:05Lender result checked → status updated
- 10.06 10:12Intake text structured → saved after staff review
- 2023.03Earlier application kept
Record, status, owner, schedule, documents and history connected on one screen. Rebuilt with sample data, not real customer information.
About gentry
A software company built on real financial-work experience
gentry is a technology company that builds customer-management and workflow-automation solutions based on hands-on experience in financial work.
We design work environments where consultation notes, customer history, progress status and schedules are connected. Drawing on our experience of rebuilding our own legacy admin into “NewAdmin”, we improve the screens and processes that staff use every day while preserving the data that has built up over years.
On top of that, we are adding AI that organizes information, drafts documents and assists with tasks, so that staff can review, decide and stay in control.
gentry started from the customer-management admin we used in loan-consultation work. The legacy system was hosted externally and could not be modified, and checking one customer's progress meant cross-checking status, signing and disbursement dates, lender results, recent activity and the next contact date separately.
Solutions and current status
What works today, and what we are building
Each item shows its actual status in NewAdmin. “In use” means it is used in real daily work; “In development” means being built or stabilized; “Planned” means not yet implemented.
| Capability | Status | What it does |
|---|---|---|
| Customer list and detail screens | In use | Status-based lists, saved custom lists and column settings, mobile customer cards and detail view. |
| Linked notes, schedule and status | In use | Consultation notes, signing and disbursement dates, next contact date and status in one customer record. |
| Data preservation | In use | Source data is read-only; NewAdmin's own notes and statuses live in a separate store that sync never overwrites. |
| Role-based display of personal data | In use | The server sends masked copies to non-admin accounts across lists, detail, search, data responses, Excel, print and mobile. |
| Lender result checks | In development | Results are fetched through office browser sessions and saved to the record; session renewal is being stabilized. |
| Change review and full restore rehearsal | In development | Changes are logged without personal values; a grouped change-review screen and restore rehearsal are part of the cut-over criteria. |
| Structuring free-text intake | In use | An internal AI agent turns free-text intake messages into fixed fields; staff review a preview before anything is submitted. |
| Required-field checks, follow-up dates | In use Rules | Missing required fields block the next step; recent records are checked by fixed rules to correct status and set the next contact date. No AI involved. |
| Consultation summaries, missing-item hints, drafts | Planned | To be built on the Claude API, shown as drafts and saved only after staff approval. |
What AI does not do. It does not make loan underwriting, approval, rate or limit decisions, which belong to the lender. Submitting applications, changing a customer's status or contacting customers happens only after a staff member has checked the content.
Case study · Our own system · Started March 2026 · Running in parallel
Admin → NewAdmin: keeping years of customer history while redesigning how staff work
This is an improvement of the system we use ourselves, not a project for an external client and not a core-banking replacement. Switch between the old list and the new work board below.
| No. | Received | Lender | Team | Name | National ID | Address | Phone | Type | Status | Pre-approved | Signing | Disbursed | Disb. date | Edit | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 000101 | 2026-10-01 10:12 | Lender A | Team 01 | 000011222 | 000011222 | Region 01 | 000011222 | General | Verified | KRW 0 | KRW 0 | 0000/00/00 | Edit | ||
| 000102 | 2026-10-01 11:40 | Lender B | Team 02 | 000011223 | 000011223 | Region 02 | 000011223 | General | Pre-approved? | KRW 34M | KRW 0 | 0000/00/00 | Edit | ||
| 000103 | 2026-10-02 09:05 | Lender A | Team 01 | 000011224 | 000011224 | Region 03 | 000011224 | General | Pre-approved? | KRW 18M | 2026/10/09 | KRW 0 | 0000/00/00 | Edit | |
| 000104 | 2026-10-02 15:30 | Lender C | Team 03 | 000011225 | 000011225 | Region 04 | 000011225 | General | On hold? | KRW 22M | KRW 0 | 0000/00/00 | Edit | ||
| 000105 | 2026-10-03 13:20 | Lender B | Team 02 | 000011226 | 000011226 | Region 05 | 000011226 | General | Disbursed | KRW 26M | 2026/10/05 | KRW 26M | 2026/10/06 | Edit | |
| 000106 | 2026-10-03 16:45 | Lender A | Team 01 | 000011227 | 000011227 | Region 06 | 000011227 | General | Declined? | KRW 0 | KRW 0 | 0000/00/00 | Edit |
- Personal data shown to every account
- Status, amounts and dates in separate columns
- Lender results checked on other sites
- No next action on screen
Status distribution
- All6
- Verified1
- Pre-approved1
- Signing booked1
- Disbursed1
- On hold1
- Declined1
- Intake
- Verify
- Pre-approved
- Sign
- Disb.
- Intake
- Verify
- Pre-approved
- Sign
- Disb.
- Intake
- Verify
- Pre-approved
- Sign
- Disb.
- Intake
- Verify
- Pre-approved
- Sign
- Disb.
- Intake
- Verify
- Pre-approved
- Sign
- Disb.
- Progress at a glance
- Next action and schedule
- Automatic lender-result checks
- Role-based masking
Background
- The legacy PHP admin was externally hosted; its server and database could not be changed.
- Progress information was scattered across status, dates, lender sites and notes.
- Same-name customers, repeat applications and ten-year-old records all had to be kept.
- Personal-data visibility had to differ by role, enforced on the server.
What we built
- A new Python web application that reads the source data read-only and keeps the original IDs.
- Its own store for notes, statuses and schedules, protected from sync overwrites.
- Sync rules: source-owned fields follow the source, progress never moves backwards, valid missing dates are filled in.
- Server-side masking for non-admin accounts, verified by automated tests.
Role of AI
- Development: Claude Code and other AI coding tools for code analysis, writing failing tests, reviews, pre-deployment audits and documentation. Every change is backed up, tested and approved by a person.
- Operations: an internal AI agent structures free-text intake; staff confirm before submission.
- Product: the Claude API is not yet connected to NewAdmin. Planned features are listed above.
Where it stands
- Built: lists, detail, status views, custom lists, mobile, role-based display, separated stores.
- Verified: masking, preservation and sync-protection rules covered by automated tests.
- Deployed: running on our server alongside the legacy admin, which remains the source system.
- Not yet done: full cut-over criteria (7 consecutive days of successful sync, zero data drift, zero permission bypass, restore rehearsal, final sign-off).
We do not publish time-saving, revenue or error-rate figures for this case. We will add numbers only when they have been measured.
How we use Claude
Development tool, product feature, roadmap
Solid lines are connections running today in NewAdmin; dashed lines are planned Claude API connections.
-
01 Input Consultation notes, intake messages and lender results collect in the customer record. In use
-
02 Select what is needed Only the fields a role needs are shown. Rules limiting what goes to AI will be built with the AI step. In use
-
03 · AI AI assistance Summaries, missing-item hints and draft messages, to be built on the Claude API. Planned
-
04 · Staff Staff review A person checks and edits. Every AI suggestion must pass this step. In use
-
05 Approved action Only confirmed content leads to submission, status changes or customer contact. In use
-
06 Record the result Outcomes and changes are written back to the customer record. In use
Running today: paste the call notes, confirm in Telegram
Staff used to fill every box of an input form. Now they paste the notes they took, an internal AI agent sorts them into fields, and the staff member confirms in Telegram before anything is submitted.
| Applicant | Phone | Home Mobile | |
|---|---|---|---|
| National ID | - Duplicate checkVerify | ||
| Loan amount | 0k KRW | Debtor | Check |
| Deal type | GeneralProduct 2Product 3 / NewRenewal | ||
| Address | Find | ||
| Employer | Monthly income | ||
| Deposit | Deposit Rent Market | ||
| Lender | Select lender ▾ | ||
| Memo | |||
- Every box typed by hand
- Same data retyped for each lender
- Results checked separately
1Paste the call notes
Called customer 000011222. Deposit 80M, no rent, balance due end of month so needs about 20M. Employed 3 yrs, credit average. Phone 000011222 ID 000011222 region 01 rental apt. Wants Lender A
As the staff member received it2AI sorts it into 10 fields
- Name000011222
- ID000011222
- Phone000011222
- AddressRegion 01 rental apt
- DepositKRW 80M
- LoanKRW 20M
- LenderLender A
- PurposeBalance
- CreditAverage
- Notes3 yrs employed, no rent
3Staff confirm in Telegram
Please check the 10 fields.
Lender A preview checked → ✓ Submitted
4Saved to the NewAdmin record
- Intake
- Verify
- Pre-appr.
- Sign
- Disb.
- Original text and structured fields saved
- Lender result recorded · next: book signing
- Paste text, fields fill in
- Confirm and submit from Telegram
- Results linked to the record
Nothing is submitted until a staff member confirms the AI-structured fields in Telegram, and each lender submission gets its own preview first. The structuring is done by an internal AI agent; a Claude API integration inside NewAdmin is planned. This is a demo: names, ID numbers and phone numbers are replaced by digit codes.
Development tool · in use
Claude Code for code analysis, test writing, change review, audits, handover documents and this website, alongside other AI coding tools. People check test results before anything ships.
Product feature · not yet connected
NewAdmin and Bankly do not call the Claude API today. We built an internal, test-only MCP server that lets AI tools look up our loan-condition tables; it is not connected to any customer-facing service.
Roadmap · planned
Claude API for consultation summaries, missing-item hints and follow-up drafts. Only the fields a task needs are sent, never national ID numbers, and results are saved only after staff approval. We will test on sample data first, then run alongside the current process.
Company information and contact
gentry
- Brand
- gentry
- Business entity
- YJ Solution (Gentry Info) · 와이제이솔루션(젠트리인포)
- Founder & CEO
- Sangjun Jung
- Founded
- November 2024
- Business Reg. No.
- 738-45-00483
- Location
- Gyeonggi-do, Republic of Korea
- taktwosj@gentryinfo.com