Research & development

We research what doesn't exist yet, then run it in production.

RealViu runs an active research and development programme across new projects and the products already in the field. Every programme starts from a technological uncertainty we could not resolve with existing tools, and ends with a documented result, whether it shipped or was stopped.

Why we do it

Real estate software in Canada has problems that nobody has solved: matching staged furniture across four angles of one room, answering a buyer from live listing data without crossing a board licence, or telling a serious enquiry from a curious one in three text messages. We investigate them systematically, and we keep the record.

New projectsExploratory work before a product exists

Feasibility studies, model experiments and prototypes for capabilities we have not built before, such as generating floor plans from photographs.

Existing productsExperimental development inside live software

Advancing the AI, imaging and automation already in RealViu, Realview Hub and Furnio.ai, where the remaining problems are the hard ones.

MethodHypothesis, experiment, measurement

Each programme states the uncertainty, the hypothesis, the experiments run and what was measured. Results are recorded whether the work ships or stops.

OwnershipBuilt, run and evaluated by the same team

Because we operate the products, experiments are evaluated against real usage and real Canadian constraints, not a synthetic benchmark alone.

Active programmes

Six lines of investigation, all in progress.

Each card names the product the work feeds, the technological uncertainty we are working on, our approach, and where it stands today. Detailed programme records are available to funding bodies and reviewers on request.

Programme 01 · Existing productActive

Grounded conversational AI over licensed listing data

An assistant that answers buyers from a brokerage's own listings and content, on our own fine-tuned model and GPUs, without ever pulling data from a board the brokerage isn't licensed for and without sending conversations to a public model.

Uncertainty
How to keep a generative model's answers tied to live, licence-gated listing records while it still reads naturally and never pretends to be a person.
Approach
Retrieval over brokerage content vectored in Redis, a licence check enforced before retrieval, and answer sanitisation on the frontend before anything is shown.
Status
In production as the AI Assistant. Ongoing work on valuation explanations and hand-off to the right agent.
RealViuAI AssistantIn-house model
Programme 02 · Existing productActive

Matched multi-view virtual staging

Staging one room photographed from two to four angles so that the same furniture, materials and light appear in every view, instead of four unrelated renders.

Uncertainty
Generative image models have no built-in notion that four photographs are the same room. Cross-view consistency of geometry, objects and lighting is unsolved for real-estate sets.
Approach
An anchor photograph sets the furniture story; a shared brief is carried across views; every result keeps the original beside it for review. Camera position and architecture are declared out of scope.
Status
Shipped as a Furnio workflow. Ongoing experiments on consistency across wider angle changes.
Furnio.aiGenerative imaging
Programme 03 · Existing productActive

Computer vision for listing media production

A suite of eight models that work on every photograph a media agency delivers: virtual staging, 3D floor-plan generation, photo tagging, room measurements, listing descriptions, feature extraction, twilight conversion and exterior enhancement.

Uncertainty
Deriving floor plans and room dimensions from ordinary listing photography, without a scanner or a measured survey, at an accuracy agents can use.
Approach
Models trained and evaluated on real shoot sets, with output landing in the delivery portal so agencies can review and sell it as an add-on.
Status
In production inside Realview Hub. Measurement and floor-plan accuracy remain active research.
Realview Hub8 models
Programme 04 · Existing productActive

Lead intelligence and multi-channel automation

Turning inbound SMS, email and site chat into an assigned, qualified lead with a recorded consent trail, and following up on the brokerage's own number and domain.

Uncertainty
Reliably judging intent and readiness from very short, informal messages, and deciding when a human should take over, without creating false urgency or breaching CASL.
Approach
Conversation processing on our own GPU with retrieval from Redis, rule-based assignment the brokerage designs, and every action logged against the lead.
Status
In production as the Automated AI Lead Engine. Calls are the next channel under development.
RealViuLead Engine
Programme 05 · Existing productActive

Licence-aware listing data platform

Serving MLS listing data to hundreds of brokerage sites while guaranteeing that a listing only ever reaches a site whose brokerage holds the board agreement for it.

Uncertainty
Enforcing per-board data rights at feed, API and database level simultaneously, across a multi-region database with automated failover, without slowing search.
Approach
A licence gate at ingestion and an allow-list check at the API, both backed by the same database record; primary in Canada with two replicas and tested failover.
Status
In production. Ongoing work on replication latency and sold-data history.
RealViuData platform
Programme 06 · New projectActive

Disclosure and provenance for AI-edited property images

Making it impossible to forget that an image was virtually staged: a disclosure label that starts switched on, is composited in the browser at download, and never produces an unlabelled server copy.

Uncertainty
Keeping provenance attached to an edited image through download, resizing and MLS sizing, on the client side, without a second upload or a trusted server step.
Approach
Client-side compositing at export, originals stored as separate objects, and a written evidence standard for demonstrations.
Status
First version shipped in Furnio. Research continues on provenance that survives re-encoding.
Furnio.aiProvenance
How a programme runs

Systematic, documented, and judged against production.

The same four steps apply whether the work is a new prototype or an advance inside a live product. The record is written as we go, not reconstructed afterwards.

  1. 1State the uncertainty

    What we cannot achieve with known methods, and why the answer is not already available. This is the test for whether something is R&D at all.

  2. 2Form a hypothesis

    A specific, falsifiable proposal: a model change, a data approach, an architecture. Scoped to what can be measured.

  3. 3Run the experiments

    On our own infrastructure, against real shoot sets, real listings and real conversations, with results recorded whether they support the hypothesis or not.

  4. 4Ship or stop, and write it down

    Work that clears the bar goes into production behind the same team that ran the experiment. Work that doesn't is closed with its findings kept.

What each programme record contains

Kept per programme, available to funding bodies, auditors and reviewers on request.

  • The technological uncertainty, in plain terms
  • Hypotheses tested and the reasoning behind them
  • Experiments run, data used and how results were measured
  • Time and people attributed to the work
  • Outcomes, including negative results
  • What shipped, and how it is evaluated in production
Who does the work

Nineteen people. Three of them do nothing but research.

R&D is not a separate building. The researchers and the machine-learning engineer sit with the developers who ship, the analysts who measure, and the designers who make the results usable.

26 years

Our founder started his first software company 26 years ago and has since reformed the business into RealViu. The habit of building, running and supporting software for real customers comes from that history.

  • 8Developers
  • 3Research & development
  • 2Data analysts
  • 2UI/UX developers
  • 1Machine learning / LLM engineer
  • 3Operations, support and the people who hold the team together

6

Active programmes across language, imaging and data infrastructure.

3

Live products that serve as test beds, so results are judged against real use.

8

Computer-vision models already in production in Realview Hub.

7

Purpose-built imaging workflows shipped in Furnio.ai, each with declared limits.

Funding bodies, reviewers and research partners

Ask us for the programme records.

We will share programme documentation, walk your reviewer through the technical uncertainties on a call, and discuss collaboration with boards, universities and funding programmes.

Get started Assist Call