Real Estate Agent Tenant Reference Check Records: Use case and AI Confidentiality
After the applications close, the property manager phones the previous agent, the employers and the guarantor, and then has to turn a morning of calls into a recommendation for the owner. Pasting the call notes into ChatGPT or Claude to tidy them and rank the applicants is a natural shortcut. The notes hold more than a rental history. They hold what a referee said without being asked, an employer’s remark about leave, bank statement detail, a guarantor’s private doubts and a rival applicant’s pay. This page marks every item in a routine reference check record and shows how the same record is handled on Ermos inside the agency.
The tenant reference check
Completed by the property manager once a rental listing has closed and before the owner chooses. NSW Fair Trading’s guidance says an agent should collect only the minimum information reasonably necessary, which includes confirming identity, showing the tenants can pay the rent and showing they are likely to look after the property. It lists a reference from a previous landlord or agent as an example, and says unsolicited information that is not reasonably necessary should be destroyed as soon as possible.
Tenant reference check record
2/18 Mallee Street, Lewisham · $690 per week · applications closed Wednesday 28 October 20261 · Bronwyn Pike, Property Manager, Wattlebird Property
| Applicants | Hannah Louise Moretti, born 3 June 1994, and Callum James Reid, born 21 February 1992. Application received Monday 26 October. Authority to check references and search a tenancy database signed 26 October.2 |
| Previous agent | Tess Olawale, Brightwater Property, 04xx xxx 413, by phone on Thursday 29 October at 10.15am. Rent paid on time apart from two late payments in 2024, ledger clear, bond intact, routine inspections fine apart from one carpet stain. Landlord is selling.3 |
| Volunteered by the previous agent | Tess also said police attended the unit in March 2025 after a domestic with Hannah’s former partner, and that neighbours had complained about noise. I did not ask. It has nothing to do with the rent or the care of the property, so it is not in my summary and I will delete this line when the file is closed.4 |
| Employers | Hannah: Fiona Nesbitt, practice manager, Harlow Veterinary Group, email on Thursday 29 October at 11.40am. Permanent since 2019, $84,000, “reliable”, and Hannah took six weeks of stress leave in 2025. Callum: Neil Arkwright, director, Arkwright Creative Pty Ltd, by phone at 2.05pm. Contract to March 2027, renewal likely but not signed, three days a week from December, so $61,000 becomes about $36,600.5 |
| Bank statements | Three months received on 26 October. Callum’s gambling transactions in September are on them. Not relevant to ability to pay and I am not weighing them. I asked Hannah on Thursday 29 October for savings-only statements and deleted the originals.6 |
| Tenancy database | Searched Thursday 29 October at 12.20pm. No listing for either applicant. The application told them a database would be searched.7 |
| Guarantor | Rosa Moretti, by phone on Friday 30 October at 9.30am. Will guarantee for 12 months only. Income $52,000 from part-time work, moving to the age pension in March. Asked me not to tell Callum she has doubts about the arrangement.8 |
| Other applicant | Natalie Norcott, received Tuesday 27 October. Single, hospital pharmacist, permanent, $132,000. References clean and she would sign for 12 months.9 |
| Assessment | Recommend Natalie Norcott. Moretti and Reid are a close second, but the guarantee is 12 months only, Callum’s hours drop in December and rent goes from about 25% of their combined income to about 30%. Angela Ferro said on Wednesday 28 October she wants “whoever is least likely to cause me trouble”. Sent to Angela on Friday 30 October at 3.10pm; she decides by Monday 2 November.10 |
An invented reference check record. The agency, the people and the employers are fictional and the telephone numbers are placeholders. Hover or tap any highlighted item for the analysis; the full list is below.
Reference check record preparer
An Agent+ that turns the property manager's call notes and replies into a tenant reference check record. It follows your own record template, keeps answers to the questions asked in one section, and flags unrequested remarks, such as personal or police detail, for the property manager to review against your own policy.
What it does
- Reads the call notes and written replies from referees
- Fills the record in your own template
- Flags unrequested remarks and gaps for the property manager
What stays with your people. The property manager decides what stays on the record and what is destroyed, and the owner chooses the tenant. The Agent+ prepares; it does not choose.
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 agency
- 1The property, the rent and the closing date
The address, the weekly rent and the date applications closed. The address and rent were on the advertisement for the rental and none of it is about a person, so little here depends on where it is sent.
Frontier Models (ChatGPT, Claude) Public rental details; nothing about a person Ermos Edge Not about where data goes Ermos Dominion Not about where data goes Use case Reference check record preparer. Records each reference check against your template, separating what was asked from what was volunteered, and flags unrequested details for the property manager to review. See the use case - 2The applicants, their birth dates and the authority
Two named people with dates of birth. Personal information. The authority they signed is what allows the checks, and it does not widen what the agency may keep or send on. NSW Fair Trading says only the minimum information reasonably necessary should be collected, and where the Privacy Act applies APP 3.2 limits collection to what is reasonably necessary for the agency’s functions or activities. Privacy Act guide.
Frontier Models (ChatGPT, Claude) Two applicants’ names and birth dates 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 Reference check record preparer. Records each reference check against your template, separating what was asked from what was volunteered, and flags unrequested details for the property manager to review. See the use case - 3The previous agent’s reference
A third party’s account of a named tenant’s payments, inspections and bond. Fair Trading lists a reference from a previous landlord or agent as an example of what is reasonably necessary. Where the Act applies, APP 3.6 says an organisation collects personal information about an individual only from that individual unless it is unreasonable or impracticable, so the agency should be able to say why the call was needed. Privacy Act guide.
Frontier Models (ChatGPT, Claude) A referee’s account of a named tenant 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 Reference check record preparer. Records each reference check against your template, separating what was asked from what was volunteered, and flags unrequested details for the property manager to review. See the use case - 4A detail the referee volunteered
A police attendance and a domestic dispute involving the applicant and a former partner who is not an applicant, offered without being asked. Fair Trading says unsolicited information that is not reasonably necessary should be destroyed as soon as possible, and where the Act applies APP 4.1 and 4.3 ask for a decision within a reasonable period and destruction or de-identification if it could not have been collected. Pasting it into a model makes a copy before that step happens. Privacy Act guide.
Frontier Models (ChatGPT, Claude) A domestic incident and a former partner transmitted before the line is deleted 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 Reference check record preparer. Records each reference check against your template, separating what was asked from what was volunteered, and flags unrequested details for the property manager to review. See the use case - 5The employer checks
Salary, tenure, a remark about leave and the co-applicant’s changed hours with a sum worked out from them. Income is personal information and Fair Trading treats it as part of showing the tenants can pay. A reason for leave can be health information, which is sensitive information, and APP 3.3 needs consent for it where the Act applies. The $36,600 is the manager’s own arithmetic on a contract that is not signed. Patient data guide.
Frontier Models (ChatGPT, Claude) Salaries, leave and a contract transmitted; a reason for leave can be sensitive Ermos Edge Stays on your instance in Australia and leaves only inside a permitted excerpt to the named provider; the sum on the new hours is still the manager’s to check Ermos Dominion Stays on the unit; the sum on the new hours is still the manager’s to check Use case Reference check record preparer. Records each reference check against your template, separating what was asked from what was volunteered, and flags unrequested details for the property manager to review. See the use case - 6The bank statements
Fair Trading says an applicant who has no payslips and gives bank statements instead should be encouraged to redact the daily transaction history and show evidence of savings. A statement with every transaction shows far more than the ability to pay, here a gambling pattern, and every line travels with the paste. APP 11.2 asks for reasonable steps to destroy personal information the agency no longer needs, where the Act applies. Privacy Act guide.
Frontier Models (ChatGPT, Claude) A gambling pattern from bank statements 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 Reference check record preparer. Records each reference check against your template, separating what was asked from what was volunteered, and flags unrequested details for the property manager to review. See the use case - 7The tenancy database search
A result tied to two names. Fair Trading says agents may search a tenancy database and that it is best practice to tell applicants. A tenant can be listed on a database only after the tenancy has ended, only if named on the agreement, and only for a debt over the bond or a Tribunal termination order (Part 11 of the Residential Tenancies Act 2010). A clear result is thin, but it is still information about named people.
Frontier Models (ChatGPT, Claude) A clear result is thin, but it ties a search to two names 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 Reference check record preparer. Records each reference check against your template, separating what was asked from what was volunteered, and flags unrequested details for the property manager to review. See the use case - 8The guarantor and her doubts
A third party who is not an applicant, her income, her pension plans and a confidence about one applicant. Personal information about someone who did not apply, given to the agency for one purpose. Privacy Act guide.
Frontier Models (ChatGPT, Claude) A guarantor’s income and a confidence transmitted without her knowledge 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 Reference check record preparer. Records each reference check against your template, separating what was asked from what was volunteered, and flags unrequested details for the property manager to review. See the use case - 9Another applicant’s details
The rival’s name, occupation, pay and references sitting beside the first applicants. Personal information about a person who is not part of this check, and one who would not expect it to be compared in an outside service. Privacy Act guide.
Frontier Models (ChatGPT, Claude) A rival applicant’s pay and references 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 Reference check record preparer. Records each reference check against your template, separating what was asked from what was volunteered, and flags unrequested details for the property manager to review. See the use case - 10The assessment and the owner’s wish
A ranking of people, the owner’s instruction and percentages worked out from the figures above. Fair Trading says it is unlawful in NSW to discriminate in providing accommodation on grounds that include race, sex, marital or partner status, age, disability, sexual orientation and gender identity, and that consideration should be given to whether any program or algorithm used by a third-party platform to assess an application could be assessing information in a discriminatory way. The recommendation is the property manager’s to make and explain, and the owner decides.
Frontier Models (ChatGPT, Claude) A ranking of people and the owner’s wish transmitted Ermos Edge Stays on your instance in Australia and leaves only inside a permitted excerpt to the named provider; the ranking is still the manager’s judgement and the owner’s choice Ermos Dominion Stays on the unit; the ranking is still the manager’s judgement and the owner’s choice Use case Reference check record preparer. Records each reference check against your template, separating what was asked from what was volunteered, and flags unrequested details for the property manager to review. 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 agency 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 property 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 real estate agencies.
Common questions
Do ChatGPT and Claude use the information in a tenant reference check record?
Can we use ChatGPT or Claude for a tenant reference check record if we remove the names?
Does deleting the chat remove a tenant reference check record from ChatGPT or Claude?
How can a property manager use AI for a tenant reference check record without sending it to ChatGPT or Claude?
What can a NSW agent collect to assess a rental application?
What should an agent do with information a referee volunteers?
Is there a standard rental application form in NSW?
See Dominion answering from your own documents.
A demonstration takes 30 minutes, uses no client data, and comes with no obligation.
Book a demo