Mortgage Broker Lender Policy Comparisons: Use case and AI Confidentiality
A lender policy comparison sets one client’s numbers against several lenders’ rules: how much of a bonus is counted, how much of the expected rent, the highest loan-to-value ratio, the rate applied to a card limit and what each lender would pay the brokerage. Brokers paste the matrix or upload the file to ChatGPT or Claude to ask which lender fits, to find the policy that blocks a deal and to write up why one was chosen. The sheet carries the client’s employer and pay, a rent estimate, existing debts, credit policy read from lender portals, commission rates and sometimes a lender manager’s unwritten remark. This page marks every cell in a lender policy comparison that the National Consumer Credit Protection Act and the Privacy Act bear on, and shows how the same sheet is worked on Ermos.
The lender policy comparison
Built after the fact find and before a lender is chosen, and kept with the file. No provision requires a policy comparison. ASIC’s RG 273 expects a mortgage broker to keep records that show the options and the recommendation given and the reasons why (RG 273.165(g)), and lists outputs of product comparison tools and calculators among the forms a record can take (RG 273.167(e)); RG 273 is guidance and not law. The best interests duty (section 158LA) and the conflict priority rule (section 158LB) of the National Consumer Credit Protection Act 2009 apply to a licensee that is a mortgage broker, and sections 158LE and 158LF apply to its credit representatives.
| A | B | C | D | E | F | |
|---|---|---|---|---|---|---|
| 1 | Policy item | Lachlan Plunkett | Southgate Bank | Tamarind Bank | Orrin Building Society | Hartwell Credit Union |
| 2 | Client and purchase | Lachlan Plunkett, 47. Investment unit at 4/22 Pinebrook Court, Werrington, $585,000. Loan $410,000 (LVR 70.1%)1 | ||||
| 3 | Policy used (portal copies, 18 Nov) | Max investment LVR 90%. Bonus 80% of two-year average. Rent 80%. Card 3.0% of limit. Investment rate 6.19%6 | Max investment LVR 90%. Bonus 100% of lower year. Rent 75%. Card 3.8% of limit. Investment rate 6.04%6 | Max investment LVR 80%. Bonus 50% of two-year average. Rent 70%. Card 3.0% of limit. Investment rate 6.29%6 | Max investment LVR 85%. Bonus 75% of lower year. Rent 80%. Card 3.8% of limit. Investment rate 6.24%6 | |
| 4 | Base salary counted ($ a year) | Operations manager, Pennywell Packaging Pty Ltd, permanent since 2019, base $138,0002 | 138,000 | 138,000 | 138,000 | 138,000 |
| 5 | Bonus counted ($ a year) | Bonus $11,000 (2024-25) and $13,000 (2025-26), average $12,0003 | 9,600 | 11,000 | 6,000 | 8,250 |
| 6 | Rent counted ($ a year) | Agent’s appraisal $560 a week, $29,120 a year. No lease yet4 | 23,296 | 21,840 | 20,384 | 23,296 |
| 7 | Total income counted ($ a year) | 170,896 | 170,840 | 164,384 | 169,546 | |
| 8 | Card commitment counted ($ a month) | Home loan with Hartwell, $298,400, $2,350 a month. Card limit $8,0005 | 240 | 304 | 240 | 304 |
| 9 | Repayment on $410,000, 30 years P&I ($ a month) | 2,508 | 2,469 | 2,535 | 2,522 | |
| 10 | Annual package fee ($) | 395 | 0 | 350 | 0 | |
| 11 | Upfront commission ($) | 2,6657 | 2,8707 | 2,4607 | 2,6657 | |
| 12 | Lender manager | Lena Pritchett, Wed 18 Nov, 3.10pm: “might look at 80% of rent for a client like this”. Nothing in writing8 | ||||
| 13 | Short list | Tamarind first: lowest repayment and no package fee. Hartwell second: counts as much rent as any lender and has no package fee. Tamarind also pays the highest upfront commission, so if it is recommended the file must show why it suits his goals and the cost. Tax effect is for his accountant9 | ||||
| 14 | Status | Fact find done Tue 17 Nov. Credit guide sent. No preliminary assessment yet, so nothing is recommended or lodged until it is made10 |
An invented policy comparison as at Wednesday 18 November 2026. The client, employer, property and lender manager are invented, and so are every lender policy, rate, package fee and commission rate. Hover or tap any highlighted cell for the analysis; the full list is below.
Lender policy comparison builder
An Agent+ that lays one client's position against each lender's policy, working from the fact find and the policy notes and commission tables your brokerage holds. It fills the comparison grid, shows where the policies differ, and flags anything resting on a verbal remark rather than a written policy.
What it does
- Reads the fact find and your lender policy notes
- Fills a comparison grid, one column per lender
- Flags points resting on verbal or unconfirmed advice
What stays with your people. A broker chooses the lender and records why. The agent lays out the comparison; it does not recommend a loan.
An Agent+ is built once and anyone in the practice can run it. It works from your own documents and runs on Ermos Dominion, the AI unit in your office, or on Ermos Edge, your own instance in an Australian data centre.
What leaves the brokerage
- 1The client and the purchase
A named client, his age, the address of the unit he is buying, the price and the loan. Personal information, and the deal itself. Whether the Privacy Act reaches a particular brokerage depends on its turnover and activities (section 6D); the client expects confidence either way. Privacy Act guide.
Frontier Models (ChatGPT, Claude) A named client and the unit he is buying transmitted; generally offshore on personal plans Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office Use case Lender policy comparison builder. Builds a side-by-side comparison of lender policies against one client's income, debts and rent, using policy notes you supply, and lists unwritten or unconfirmed points. See the use case - 2Employer and salary
A named employer, a role, a start year and a base salary. Section 117(1)(b) of the National Consumer Credit Protection Act requires reasonable inquiries about the consumer’s financial situation, and this is what those inquiries found. Privacy Act guide.
Frontier Models (ChatGPT, Claude) His employer and salary transmitted; on consumer tiers they can train future models Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office Use case Lender policy comparison builder. Builds a side-by-side comparison of lender policies against one client's income, debts and rent, using policy notes you supply, and lists unwritten or unconfirmed points. See the use case - 3Bonus history
Two years of variable pay. Each lender counts it differently, so the figure that matters is the one the broker has verified. Section 117(1)(c) requires reasonable steps to verify the financial situation, and under section 118(4) only information the licensee had reason to believe was true, or would have had reason to believe was true had it made the inquiries and verification in section 117, is taken into account in deciding whether a contract is unsuitable. Privacy Act guide.
Frontier Models (ChatGPT, Claude) His bonus history transmitted Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office Use case Lender policy comparison builder. Builds a side-by-side comparison of lender policies against one client's income, debts and rent, using policy notes you supply, and lists unwritten or unconfirmed points. See the use case - 4The rent estimate
An agent’s appraisal is an estimate and no lease exists yet. A model given the figure can treat an estimate as verified income. Under section 118(4) only information the licensee had reason to believe was true, or would have had reason to believe had it made the inquiries and verification in section 117, counts.
Frontier Models (ChatGPT, Claude) An unverified rent estimate transmitted Ermos Edge Stays on your instance in Australia; the appraisal is still an estimate and a person decides whether to rely on it Ermos Dominion Stays on the unit; the appraisal is still an estimate and a person decides whether to rely on it Use case Lender policy comparison builder. Builds a side-by-side comparison of lender policies against one client's income, debts and rent, using policy notes you supply, and lists unwritten or unconfirmed points. See the use case - 5Existing home loan and card
The lender, the balance and the repayment on his own home, and a card limit. The commitments a lender counts, and a map of his credit relationships. Privacy Act guide.
Frontier Models (ChatGPT, Claude) His mortgage balance, repayment and card limit transmitted Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office Use case Lender policy comparison builder. Builds a side-by-side comparison of lender policies against one client's income, debts and rent, using policy notes you supply, and lists unwritten or unconfirmed points. See the use case - 6The lenders’ credit policy
Four lenders’ rules as read from their broker portals: loan-to-value limits, how much of a bonus and of rent is counted, the rate applied to a card limit and the investment rate. Commercial information the brokerage holds through its accreditation; check the lender and aggregator terms before pasting it elsewhere. A model asked from memory can also state a policy that has since changed. ASIC’s RG 273.60 recognises that a lender’s credit policy and risk appetite may keep some consumers from the lowest cost products.
Frontier Models (ChatGPT, Claude) Depends on plan and on your lender and aggregator terms; a model asked from memory can state a policy wrongly Ermos Edge Stays on your instance; the policy is only as current as the portal copy you load, so check it before relying on it, and the lender and aggregator terms about the policy still apply Ermos Dominion Stays on the unit; the policy is only as current as the portal copy you load, so check it before relying on it, and the lender and aggregator terms about the policy still apply Use case Lender policy comparison builder. Builds a side-by-side comparison of lender policies against one client's income, debts and rent, using policy notes you supply, and lists unwritten or unconfirmed points. See the use case - 7Commission by lender
What each lender would pay the brokerage on this loan, from $2,460 to $2,870. A difference in what lenders pay is a possible conflict between the consumer’s interests and the licensee’s, and section 158LB requires a licensee that knows or reasonably ought to know of such a conflict to give priority to the consumer’s interests. Also commercial terms the brokerage may hold under confidence; check yours.
Frontier Models (ChatGPT, Claude) Your commission rates by lender transmitted Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office Use case Lender policy comparison builder. Builds a side-by-side comparison of lender policies against one client's income, debts and rent, using policy notes you supply, and lists unwritten or unconfirmed points. See the use case - 8A lender manager’s unwritten remark
A named lender employee, a date and a time, and an indication that is not policy. A model asked about the sheet may treat it as policy. A broker who relies on it should record it: RG 273.167(b) lists file notes, including records of conversations, among the forms a record can take.
Frontier Models (ChatGPT, Claude) A named lender employee’s unwritten remark transmitted Ermos Edge Stays on your instance; a model asked about the sheet may still treat the remark as policy, so a person checks it Ermos Dominion Stays on the unit; a model asked about the sheet may still treat the remark as policy, so a person checks it Use case Lender policy comparison builder. Builds a side-by-side comparison of lender policies against one client's income, debts and rent, using policy notes you supply, and lists unwritten or unconfirmed points. See the use case - 9The short list and the reasoning
Which lender comes first and why, the commission conflict and a note that the tax effect belongs to his accountant. RG 273.92 says it would generally be helpful to present the consumer with a shortlist with one option recommended, and RG 273.93 says it is important that the consumer understands why options were chosen and others left out, RG 273.54 expects evidence for recommending a higher cost loan, and RG 273.141 to 273.143 do not expect a broker to give detailed tax advice. Section 158LA is the duty that the reasoning has to meet.
Frontier Models (ChatGPT, Claude) Your reasoning, and the commission conflict behind it, transmitted Ermos Edge Stays on your instance; whether the reasoning meets the best interests duty is for the broker to judge, and a model cannot Ermos Dominion Stays on the unit; whether the reasoning meets the best interests duty is for the broker to judge, and a model cannot Use case Lender policy comparison builder. Builds a side-by-side comparison of lender policies against one client's income, debts and rent, using policy notes you supply, and lists unwritten or unconfirmed points. See the use case - 10The status line
A step in the process: fact find done, credit guide sent, no assessment yet. Section 115(1) says a licensee must not suggest that the consumer apply for a particular credit contract with a particular credit provider, or assist the consumer to apply for one, unless within 90 days (or another period the regulations prescribe) before that day it has made a preliminary assessment and made the inquiries and verification in section 117. No personal detail beyond the process.
Frontier Models (ChatGPT, Claude) A process status with no personal detail; harmless alone Ermos Edge A process step; nothing to keep in Ermos Dominion A process step; nothing to keep in Use case Lender policy comparison builder. Builds a side-by-side comparison of lender policies against one client's income, debts and rent, using policy notes you supply, and lists unwritten or unconfirmed points. See the use case
What happens in Frontier Models (ChatGPT, Claude)
- The whole document is transmitted to the provider’s servers. On personal plans the user cannot choose where it is stored or processed, and for the major providers that has generally meant outside Australia, under that country’s legal process. Some business plans offer storage in Australia, but the provider still receives the content.
- On consumer tiers, prompts can be retained and used to train future models.
- The provider’s staff and systems can reach the content under the provider’s own policies.
- Once sent, the brokerage no longer controls it. Retention and deletion happen on the provider’s terms.
The same document on Ermos
Ermos Dominion
The document is drafted on a unit in your office, from your own templates and the client file. Every marked item stays on the unit, which keeps working with the internet switched off. Nothing in it is transmitted to an AI provider, so there is no disclosure to analyse: the confidentiality work is the same as for your file server.
Ermos Edge
Your documents, the index and your access boundaries stay on your own instance in an Australian data centre. When a staff member asks for this draft, only their question and the excerpts they are permitted to see go to a named Australian provider, who is contractually barred from keeping the content or training any model on it. Nothing is processed outside Australia.
| Frontier Models (ChatGPT, Claude) | Ermos Edge | Ermos Dominion | |
|---|---|---|---|
| Where the document is processed | Provider servers, generally offshore on personal plans | Your instance in an Australian data centre; answers generated in Australia | The unit in your office |
| Who can read it | Provider staff and systems, under policy | Your staff, within the boundaries you set. The named Australian provider processes only permitted excerpts, under contract, and keeps nothing | Your staff only |
| Is it kept | On the provider’s terms | Kept on your instance; the provider is barred from retaining it | Stays on the unit |
| Can it train a model | On consumer tiers, yes | No, by contract | Only your own unit learns from it, on your hardware |
Part of Use cases in mortgage brokerages. See how this works in practice: Lender policy lookups on Ermos.
Common questions
Do ChatGPT and Claude use the information in a lender policy comparison?
Can we use ChatGPT or Claude for a lender policy comparison if we remove the client's name?
Can ChatGPT or Claude be trusted to draft a lender policy comparison?
How can a mortgage brokerage use AI for a lender policy comparison without sending it to ChatGPT or Claude?
Does a mortgage broker have to compare several lenders?
Can a broker recommend the lender that pays the highest commission?
What records should a broker keep of a lender comparison?
See Dominion answering from your own documents.
A demonstration takes 30 minutes, uses no client data, and comes with no obligation.
Book a demo