Horse racing database and racing data platform
Results, sectionals, sale records and ratings for every Australian race since the 1980s, queried in plain English and served to apps.
See the work →Custom software, AI and computer vision · Australia
Moose Consulting designs and builds custom web platforms, mobile apps, AI tools, computer-vision systems and data pipelines for businesses that have outgrown spreadsheets and off-the-shelf products. A senior team, end to end: from the first conversation to a system running in production. We specialise in sectors where off-the-shelf software does not fit: horse racing and breeding, building compliance, sport and education, and agribusiness.
Where we go deep
We do not try to be everyone's software company. We work in a handful of industries where generic products do not fit, learn how the work is actually done, and build systems people use every day. Five of these are running in production for real businesses in Australia. The sixth is being scoped now.
Results, sectionals, sale records and ratings for every Australian race since the 1980s, queried in plain English and served to apps.
See the work →Horse locations, owner billing, staff hours and daily schedules for large training operations, on iOS, Android and the web.
See the work →Custom pose-estimation models that measure stride, balance and conformation from ordinary sale and barn video.
See the work →Tens of thousands of clauses from codes, standards and regulations, searchable with citations and version history.
See the work →Rosters, session plans, crew boards, boat care and daily messaging for a school rowing program, built as an installable app.
See the work →Livestock records, per-mob profit and loss, cameras and sensors, and an offline-first paddock app. In scoping now.
See the work →What we build
Every engagement is a working system, not a slide deck. These are the kinds of software Moose Consulting designs, builds, hosts and supports.
Operations platforms, internal tools and bespoke web applications that replace spreadsheets, shared inboxes and off-the-shelf products that never quite fit.
Learn more →Natural-language assistants over your own data, LLM tools with real guardrails, vision-language reading and machine-learning models that are tested before they are trusted.
Learn more →Object detection, tracking, custom pose-estimation models and measurement pipelines that turn ordinary video into numbers you can act on.
Learn more →Crawlers, scheduled pipelines, reconciled databases and read-only APIs that turn scattered public and private sources into one clean, queryable platform.
Learn more →Native iOS and Android apps, and installable web apps with push notifications, built alongside the backend so the phone is a first-class way to run the business.
Learn more →Xero, payroll, Google Sheets, vendor portals without an API, email inboxes and weather feeds, connected to one platform so staff never re-key data.
Learn more →Live KPI dashboards, per-unit profit and loss, occupancy forecasts and wall-mounted display boards, with every number traceable to where it came from.
Learn more →Fast, secure marketing sites and landing pages on Cloudflare, with waitlists, unlisted share pages, locked reports and automated publishing when you need them.
Learn more →Independent, vendor-neutral advice on what to build, what to buy and what to stop paying for, from people who also write the code.
Learn more →Selected work
Client names are kept private. The problems, the architecture and the outcomes are described in full on each case study.
A multi-site thoroughbred training business had its money in Xero, its horses in a stable-management product, its staff in an HR platform and no way to see per-horse profitability. Now it has one reconciled view, on the web and on the phone.
Read the case study →A 545-horse, three-site stable ran its daily training from a 52-tab Google Sheet with no validation, access control or audit trail. It now runs from a rules-checked scheduling platform with TV boards, reports and a rider app.
Read the case study →A building surveying firm needed every clause of the Building Act, Regulations, NCC and regulator guidance searchable with a citation. The core corpus of 463 documents and 45,000 clauses went live in about two days.
Read the case study →Sixteen coaches, forty boats, a weekly roster in a spreadsheet and the week's plan in WhatsApp. Now one installable hub with rosters, session plans, a 300-drill library, crew boards, erg results and live lake conditions.
Read the case study →A dozen sources, seventeen scheduled jobs, 489,000 races and 2.2 million results reconciled into one database with a fast web front end, a read-only API, a native iOS app and an AI query tool that backtests its own answers.
Read the case study →A custom 45-point pose model applied to 37,800 yearling parade and breeze-up videos, with repeatability gates, measurement of stride, reach and conformation, and validation against millions of race results. Live on public horse pages.
Read the case study →Two barn cameras, a Raspberry Pi, cloud storage, serverless scanning, GPU pose estimation and vision-model brand reading, built as a modular pipeline to compare each horse's walk with its own history. A working pilot, honestly reported.
Read the case study →A weekly-retrained ranking model, an explainable scorer that writes its own reasoning lines, a resilient price feed, consumer apps and a public scoreboard that shows the losses as well as the wins.
Read the case study →Give it a JSON spec and it returns a finished 1080p video: presenter clips, themed cards, AI narration fitted to a time cap, music, sound effects, subtitles and an end card.
Read the case study →An in-house platform now being scoped for livestock and mixed farming enterprises: paddock and mob ledgers, per-mob profit and loss reconciled to Xero, weigh and NLIS data, camera and sensor monitoring, and an offline paddock app. Built on patterns proven in racing.
Read the case study →Why Moose Consulting
Most software projects fail in the gaps: between the person who understands the business and the person writing code, between the demo and production, between launch and the first month of real use. Moose Consulting removes the gaps by having the same senior team own the whole thing: discovery, data model, backend, front end, mobile app, hosting, security and support.
The work spans racing operations platforms that reconcile accounting, billing and payroll to the dollar; a legal compliance knowledge base with 45,000 cited clauses; a rowing coaching hub used by a school every day; a horse racing database of 2.2 million results; and computer-vision pipelines that measure how a horse moves from ordinary video.
Different industries, the same approach: understand the real workflow, build the smallest thing that works, put it in front of users, then harden it.
Technology
Chosen for reliability, low cost and how easy it is for your own team to take over later.
Python, FastAPI, Django, PostgreSQL, SQLAlchemy, DuckDB, materialised views, scheduled jobs.
Anthropic Claude API, LightGBM, YOLO, ByteTrack, SAM, custom pose-estimation models, OpenCV.
SwiftUI (iOS), Flutter (Android), progressive web apps with push, server-rendered HTML, static sites.
Render, Cloudflare Pages and Workers, Google Cloud Storage and spot GPUs, Modal, Vast.ai, Raspberry Pi.
Industries
Stable operations and scheduling platforms, racing data with stride and sectional telemetry, vision measurement of yearlings and breeze-ups, and barn monitoring.
Racing and breeding →Cited search across legislation, codes and guidance, mapped to the services, forms, inspection stages and referral bodies a practice actually uses.
Construction and compliance →Coach rosters, session plans, drill libraries, crew boards, equipment registers and live conditions, delivered as an installable phone app volunteers will actually use.
Sport and education →Paddock and mob records, per-mob profit and loss reconciled to the accounts, camera and sensor monitoring, feed and water budgeting and an offline paddock app. In-house platform in scoping.
Agribusiness →Operations platforms, Xero-reconciled reporting, internal tools, AI assistants over your own data and independent build-versus-buy advice for businesses that have outgrown spreadsheets.
Professional services and SMEs →How we work
A short, concrete discovery with the people who do the work. We write down the real rules, including the unwritten ones.
A working slice in days, on real data, behind real logins. Enough to react to, not enough to be precious about.
Production from the first release. Features arrive weekly. Reconciliations, tests and monitoring arrive with them.
Security review, backups, alerts, documentation. You own the code and the hosting. Support on a simple monthly basis.
Tell us the problem, the systems you already use and what a good outcome looks like. You will get a plain-language reply within one business day, usually with a first sketch of how we would build it.