# AI listing description drafting.

URL: https://levystreet.com/industries/real-estate/listing-description-drafting/
Updated: 2026-10-19

AI listing description drafting for NZ real estate agents: portal copy from a verified fact sheet, Fair Trading Act limits, and the checks before publishing.

## Short answer

AI listing description drafting turns a verified fact sheet for a property (title details, floor area, rooms, zoning and the agent's notes) into portal copy, a headline, brochure text and social posts. Every sentence must trace to a fact on the sheet. In New Zealand the licensee checks each claim and the vendor approves the copy, because the Fair Trading Act and REA rules treat it as the agency's representation.

- The model writes only from a fact sheet; anything not on the sheet stays out of the copy.
- Do not publish vendor claims you cannot verify, such as subdivision potential.
- Price wording comes from the agency agreement, never from the model.
- A second automated pass flags any sentence without a matching fact before review.

## What the workflow drafts, and from what

AI listing description drafting produces the words for a new listing: the portal description, a headline, brochure text, social posts and the short summary agents read at open homes. The difference between a useful system and a risky one is the input. A model given "3 bed brick, great sun, handy to schools" will fill gaps with what similar homes usually have. A model given a fact sheet, and told to write only from it, cannot.

The fact sheet is the real work product. Each field holds one claim and its source: land area and legal description from the record of title, floor area from a measured plan, zoning from the district plan, chattels from the vendor's list, and agent observations from the appraisal visit. Vendor statements carry a flag: verified, or not. REA's [marketing guidance](https://www.rea.govt.nz/real-estate-professionals/industry-guidance-and-information/listing-a-property/marketing-and-advertising/) says that if a vendor claim cannot be verified, such as that the property can be subdivided, "we recommend you do not make the claim". Unverified fields never reach the model.

## How the workflow runs


- **Inputs**: The fact sheet with sources, the agent's notes and voice memo from the appraisal visit, selected photo captions, the agreed method of sale and price wording from the agency agreement, and the agency's style guide and banned-claims list.
- **Systems**: The sales CRM ([MRI Vault](https://www.mrisoftware.com/nz/products/vault/) or Rex), the document store holding title and LIM, the portal feed, and a model API.
- **Steps**: Check the fact sheet for missing required fields; draft each format; run a second pass that maps every sentence to a fact field and flags any that do not match; insert price wording verbatim from the agency agreement; queue for the agent with flags shown inline.
- **Human review**: The listing agent checks each flagged sentence and the overall impression, the vendor approves the final copy in writing, and the branch manager or supervisor oversees it before it is published.
- **Outputs**: Approved copy for each channel, a record of which fact supported each claim, and the vendor's sign-off on file.
- **Measures**: Agent minutes per listing, flagged sentences per draft, unsupported claims found after publishing (target zero), and vendor change requests.
- **Risks**: Invented features, price wording that drifts from the agreement, claims about zoning or permitted use, and copy left live after facts change.


## Illustrative example: a Nelson agency listing 18 homes a month

Illustrative example, synthetic numbers: an eight-salesperson agency in Nelson lists about 18 properties a month. Writing the portal description, headline, brochure text and three social posts, then reworking them after vendor comments, takes about 70 minutes a listing.

| Measure | By hand | With fact-sheet drafts |
|---|---|---|
| Listings a month | 18 | 18 |
| Minutes per listing | 70 | 25 to check, edit and send for sign-off |
| Hours a month | 21 | 7.5 |
| Model fees a month | None | about US$2 |

The fee line assumes 30,000 input tokens (fact sheet, notes and 15 photo captions or images) and 3,000 output tokens for the drafts, plus a checking pass of 10,000 input and 500 output tokens, on Claude Sonnet 5.5 at US$2 per million input and US$10 per million output tokens, as listed on [19 October 2026](https://platform.claude.com/docs/en/about-claude/pricing). That is about US$0.12 a listing. Building fact sheets adds time at first; the saving comes once agents fill them at the appraisal visit.

## New Zealand rules the copy must meet

- **No misleading claims.** Rule 6.4 of the [Code of Conduct](https://www.legislation.govt.nz/secondary-legislation/pco-drafted/2012/413/en/latest/) bars misleading customers or withholding information. Section 14 of the [Fair Trading Act 1986](https://www.legislation.govt.nz/act/public/1986/121/en/latest/) bars false or misleading representations about land's characteristics, price, location or the use it "may lawfully be put" to.
- **Reasonable grounds at the time.** Under s 12A, a claim is unsubstantiated if you lacked reasonable grounds when you made it, even if it later proves true. REA gives the example of "home and income" used where a restrictive covenant prevents it.
- **Price.** Rule 10.4 says an advertised price must clearly reflect the pricing expectations agreed with the client, and rule 10.9 bars advertising on terms the client did not authorise.
- **Approval.** REA says the client should pre-approve all advertising and a supervisor should oversee it, and that new contrary information means withdrawing and correcting material immediately.
- **AI responsibility.** REA's [generative AI guidance](https://www.rea.govt.nz/assets/2024-Uploads/REA-Generative-AI-Guidance-for-Real-Estate-Licensees_November-2024.pdf) says licensees must fact-check AI material and that an AI error is no defence.
- **Photos.** REA's chief executive told [RNZ](https://www.rnz.co.nz/life/lifestyle/home/how-far-can-real-estate-agents-go-with-enhancing-photos) in July 2026 that photos should be "a true representation" of the property. REA calls it best practice to label aerial boundary lines "only indicative of the boundary".

## Where listing drafts go wrong

- **Plausible extras.** Heat pumps, double glazing and "sunny all day" appear because comparable homes have them. The checking pass is the control, not the prompt; our lesson on [checking AI answers against sources](/learn/checking-ai-answers-against-sources/) shows the method.
- **School zones and walking times.** A zone can change, and "walk to school" depends on which school. Treat both as claims that need a source.
- **Room counts.** A sleepout or study becomes a bedroom. Use the counts on the fact sheet and the agent's description of any unconsented space.
- **Superlatives that read as fact.** REA accepts obvious puffery but warns it is risky. "Best views in the street" invites a complaint.
- **Te reo place names.** Models drop macrons and misspell suburbs. Keep a checked list of local names for the region you sell in.

Listing copy feeds the other two sales workflows: [buyer enquiry handling](/industries/real-estate/buyer-enquiry-handling/) answers from the same fact sheet, and [appraisal preparation](/industries/real-estate/appraisal-preparation/) produces the evidence behind the price conversation with the vendor. The [real estate sector guide](/industries/real-estate/) covers the wider rules, and our [AI workflow automation](/services/ai-workflow-automation/) and [document processing](/services/ai-document-processing/) services cover building fact sheets from titles and LIMs.

## Questions people ask

### Is it allowed to use AI to write property listings in New Zealand?

The Real Estate Authority's November 2024 guidance lists drafting documents, including marketing scripts, among the ways generative AI is already used in real estate. It is clear about responsibility: the licensee answers for the content, and an AI tool's error is no defence. Treat AI copy as a first draft that the agent checks claim by claim before the vendor signs it off.

### Do we have to tell buyers a description was written with AI?

We found no REA or Commerce Commission rule that requires a label on AI-drafted text. What the rules require is that the copy is accurate, substantiated and not misleading, whoever or whatever wrote it. Images are different in practice: label virtually staged or AI-edited photos, because a buyer who sees one forms a view of the property itself.

### Can the model read the LIM and describe the property from it?

It can list items from a LIM with page references, which is useful for building the fact sheet. REA's guidance specifically warns about relying on generative AI to summarise LIM or builder reports, because the output can sound right and be incomplete. A licensee should read the source document and decide what goes into the copy and what needs disclosure.

### Should we use the AI feature in our CRM or build our own?

Start with what you have. MRI Vault advertises an AI description generator, and Rex has announced ad content generation for Rex AI. Test them on 20 past listings against your fact sheets. Build or configure something custom only if you need checks the built-in tool lacks, such as rejecting claims with no source, enforcing a banned-claims list or logging which facts each sentence used.


## Sources

- [Generative AI Guidance for Real Estate Licensees](https://www.rea.govt.nz/assets/2024-Uploads/REA-Generative-AI-Guidance-for-Real-Estate-Licensees_November-2024.pdf)
- [Marketing and advertising](https://www.rea.govt.nz/real-estate-professionals/industry-guidance-and-information/listing-a-property/marketing-and-advertising/)
- [Real Estate Agents Act (Professional Conduct and Client Care) Rules 2012](https://www.legislation.govt.nz/secondary-legislation/pco-drafted/2012/413/en/latest/)
- [Fair Trading Act 1986](https://www.legislation.govt.nz/act/public/1986/121/en/latest/)
- [How far can real estate agents go with enhancing photos?](https://www.rnz.co.nz/life/lifestyle/home/how-far-can-real-estate-agents-go-with-enhancing-photos)
- [MRI Vault (formerly VaultRE)](https://www.mrisoftware.com/nz/products/vault/)
- [Coming soon: Rex AI](https://www.rexsoftware.com/nz/articles/coming-soon-rex-ai)
- [Claude API pricing](https://platform.claude.com/docs/en/about-claude/pricing)

Published by Levy Street (https://levystreet.com), Wellington, New Zealand.