Dark theme
WELCOME TO QQUANTUM

Let Qubi show you around.

Choose how you’d like to explore.

Don’t agreeGo to yourOS instead ↗

Both choices allow Google Analytics, so we can see which pages help.

Sound is your choice. Essential cookies keep the site working. Continuing either way also allows Google Analytics (visits and pages viewed).

Read our Terms, Privacy and Cookies.

Change your choices anytime from the footer.

Getting Qubi ready.
Real Estate & PropTech

Listings written
from the facts.

An AI listing description is only as good as the record behind it. We draft from the floor plan, the energy certificate and the measured areas, flag anything the record cannot support, and leave the agent to approve.

All Real Estate & PropTech →
Pixel illustration for Listings & Valuation: a small printing press producing a family of different page layouts.

The real problem

An AI listing description generator takes a few bullet points and returns three fluent paragraphs. That is the easy part, and it is where the risk starts. A model asked to make a flat sound appealing will happily add a sea view, a garden or a recently renovated kitchen that the record never mentioned, because those words usually appear in listings like it.

For a brokerage or a portal, that is a misdescription problem. In England, National Trading Standards guidance sets out the material information a listing must carry. In the US, the Fair Housing Act prohibits language that signals a preference for or against a protected group. In Spain, consumer rules on property advertising require the information to match the property. A listing has to be both readable and defensible.

What it handles and what it refuses

01

Descriptions from the record

Copy drafted only from structured fields, the floor plan, the energy performance certificate and agent notes. Every feature in the text maps to a source field, and the agent sees which.
02

Claims it cannot support

Anything the record does not back (a view, a renovation date, a school catchment) is flagged for the agent rather than written. Missing material information is listed before publishing.
03

Valuation evidence packs

Comparable sales and lettings assembled from your data feeds, adjusted inputs laid out with their sources, and lease terms pulled in for investment stock. The valuer starts from evidence, not a blank page.
04

Not: the valuation figure

The system does not sign or set a value. A formal valuation is the work of a qualified valuer under the RICS Red Book or your national standard, and an automated estimate is shown as an input, labelled as one.

How a listing is produced

LISTING PATH
  1. 01
    Property record

    CRM fields, floor plan, EPC, photos

  2. 02
    Fact sheet

    what the record supports, with sources

  3. 03
    Draft

    house style, portal length limits

  4. 04
    Compliance screen

    fair housing terms, missing material information

  5. 05
    Agent approves

    edits tracked, then published to the portal feed

  6. 06 · Branch / escalation
    Back to the agent

    any claim the record cannot support

Solid: the drafting pathDashed: unsupported claims returned for a human decision
The model drafts only from what the fact sheet contains. A claim with no source is a question for the agent, not a sentence in the listing.

How we validate it

We test against your own past listings and their records, deliberately including properties with thin data. The measure that matters is unsupported claims per listing, and the target is none reaching the agent unflagged. Readability and house style come second.

Output goes where your listings already go: the CRM, the RESO Web API for MLS feeds in the US, or the Rightmove, Zoopla or Idealista feeds in Europe. Nothing is published without an agent pressing approve.

Questions

Questions about Listings & Valuation.

Can AI write real estate listing descriptions?

Yes, and well, provided it writes from the property record rather than from what listings usually say. Our drafts use only structured fields, the floor plan and the energy certificate, show the source for each feature, and flag anything unsupported. The agent edits and approves. Without that grounding, a model will invent appealing details, which is a misdescription risk for the brokerage.

How does it avoid fair housing problems?

Every draft passes a screen for terms that describe people rather than the property, such as words implying a preferred household type, age, religion or nationality, which the US Fair Housing Act and equivalent rules elsewhere restrict. Flagged terms go back to the agent with the reason. The screen reduces risk; responsibility for what is advertised stays with the brokerage.

Is an AI property valuation the same as a valuation?

No. An automated valuation model produces an estimate from comparable data. A formal valuation for lending, financial reporting or a dispute is signed by a qualified valuer, in the UK under the RICS Red Book. We build the evidence pack a valuer works from, with every comparable and adjustment sourced. The opinion of value is theirs.

Which systems does it connect to?

Whatever holds your listings: a brokerage CRM, an MLS through the RESO Web API, or portal feeds such as Rightmove, Zoopla and Idealista. For valuation evidence it reads your own transaction data and any licensed data source you already subscribe to.

Shipped & in build

Real work. Check it yourself.

What we built, what stage it is at, and a link to the live thing wherever there is one.

The updated yourOS homepage: Roxy’s open ring surrounded by bento cards for calls, voice, translation, building, design, apps and more.
The yourOS homepage on a phone, with its compact navigation, welcome film button and bento cards.
youros.tech — the homepage bento hero
Our own · coming soon

yourOS

yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.

What we built
  • Operating system
  • Roxy
  • Agent crew
  • Voice calls
  • App store
  • Website
Meet yourOS →
The Sonora homepage on desktop: a full-bleed dune landscape behind the headline “Transform Your Life with Sound”, with App Store and Google Play download buttons.
The Sonora homepage on a mobile viewport, showing the same hero reflowed to a single column.
sonora.com — homepage, 1440×900
Live · iOS · Android

Sonora

Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.

What we built
  • Website
  • Backend
  • App assets
Read the case study →
The updated Podswap homepage on desktop: “Grow on Instagram and TikTok for free, with real engagement from creators your size”, beside a tilted wall of exchange, tool and guide cards on a violet gradient.
The updated Podswap homepage on a phone, with its floating navigation, Instagram and TikTok engagement headline and tilted tool cards.
podswap.app — homepage, 1440×900
Five platforms

Podswap

Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.

What we built
  • Brand
  • Website
  • Prototype
  • Apps on five platforms
  • AI backend
  • Algorithm pipeline
Read the case study →
The unOpen.AI homepage introducing Roxy, a private AI assistant that remembers who you are.
The unOpen.AI homepage on a mobile viewport.
unopen.ai — homepage, 1440×900
Prototype · closed beta

unOpen.AI

In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.

What we built
  • Brand
  • Site
  • Product
  • Backend
  • Conversational design
Read the case study →
coherence.com on desktop, headed "Intelligence that moves in phase with people".
coherence.com on a mobile viewport, reflowed to a single column.
coherence.com — homepage, 1440×900
Live

Coherence

Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.

What we built
  • Brand identity
  • Motion system
  • Live website
  • Agent work — in build
Read the case study →
The new Domain Booth homepage on desktop: the headline “Premium Domains. Serious Buyers. Proven Results.” beside the animated DB monogram.
The new Domain Booth homepage on a phone, reflowed to a single column.
Our build of the Domain Booth homepage — 1440×900
Live

Domain Booth

Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.

What we built
  • Animated mark
  • Every page redesigned
  • Designed mobile layouts
  • Custom CMS
Read the case study →
Who we have built for

Twenty-one years. Names you know.

See all of our work →
  • BBC Good Food logo
  • Charities Aid Foundation logo
  • GAME logo
  • NatWest logo
  • Next logo
  • NSPCC logo
  • Tesco logo
  • Worldpay logo
  • Samsung logo
  • Sony logo
  • Land Rover logo
  • UAP Limited logo
  • Netflix logo
  • Amazon Prime Video logo
  • Mercedes-Benz dealerships logo
  • San Miguel logo
  • Biovene Barcelona logo
  • Seventy7 logo
  • Littlewoods logo
  • Smile logo
  • The Co-operative Bank logo
Let’s talk

Write only
what is true.

Send us twenty past listings and their records. We will show you how many unsupported claims a generic tool adds.

30-minute technical call · no deck