Skip to content
WEB APPLICATION / AUSTRALIAN WOOL NETWORK

NEXUS Foundation | AWN: From Weekly to Real-Time Livestock Valuations

AWN needed to know whether AI could keep its valuations current before committing to a build. We proved it on AWN's own data against a target agreed on day one, then AWN took it live.

The question they were asking: Should we invest in AI to value a market that moves faster than our model?

Book a Discovery Session
  • Client
    AWN
  • Project type Web Application
  • Industry Agriculture
NEXUS Foundation | AWN: From Weekly to Real-Time Livestock Valuations
Meet AWN

AWN connects woolgrowers and livestock producers with brokers and buyers across Australia's wool supply chain. Prices move every sale week, so a stale valuation isn't a rounding error: it's a grower selling below the market, or a buyer paying above it.

What a week of waiting cost AWN

Expert time

Est. 12 hrs / week

Valuers re-running and checking the weekend batch instead of pricing stock.
Stale prices

Up to Est. 7 days

How old a valuation could be by the time a grower or buyer acted on it.
Peak season

Est. 3-day backlog

Appraisal queues at shearing and sale peaks.

12 hours a week × $90 × 46 sale weeks ≈ $50k a year

in batch re-runs alone, before a single decision made on a stale price.

How Foundation answered the question

AWN's engagement predates NEXUS. Each step is what Foundation now delivers as standard, named in its tag.

Stage 01

Discover

Mapped where AI could help AWN's valuation team and ranked each idea by value. Keeping valuations current came out on top.

NEXUS: AI Opportunity Register

Stage 02

Design

Tested AWN's auction and fibre data. The data held up; the model's memory was the gap, so we chose retrieval over retraining.

NEXUS: Data & Readiness Assessment

Stage 03

Deliver

Built the working model on AWN's own data and measured it weekly against the day-one target, using recent auction results.

NEXUS: 800+ valuation data points in a working AI solution

Stage 04

Operate

AWN's General Manager approved production on the results. Valuations now update as sales land, with valuers approving.

NEXUS: Stakeholder Investment Case + Production Roadmap

The machine retrieved. People decided.

Foundation keeps three decisions with people. At AWN, each one became a deliverable the business kept.
icons-cash-bag
Data & Readiness Assessment

Only lots with a real price

AWN's valuers and our engineers chose what the model learns from. Passed-in and withdrawn lots were left out: no clearing price, nothing true to learn.
kanban
ROI Disqualify List

No price goes out unchecked

A fully automated price feed to growers made the list, then came off it: one bad price would cost more trust than the hours it saved. The model recommends; a valuer approves.
icons8-web-accessibility-1
Stakeholder Investment Case

Go-live was AWN's call

AWN's General Manager accepted the valuations against auction clearing prices before any reached a customer.
icons8-user-groups-1-1-2
“Will it replace our valuers?”

No. It gives them their week back.

The model does the searching. A valuer approves every price before it goes out, and every override is logged.
★   The lesson  
The algorithm wasn't wrong.
It was answering last week's question.

Results against the day-one target

Foundation fixes the target before work starts. These are AWN's results on AWN's data; yours start from your own baseline.
Metric Before After  ·  EB Pearls
Appraisal time est. 40 mins
60% fasterAverage minutes per appraisal, 4 weeks before vs after go-live
Valuation accuracy est. 82%
94%Against: auction clearing price, within ±5%
Valuation freshness Weekend batch
Real timeSystem timestamps
Business translation 48 appraisal hours a week
$200k a year120 appraisals × 24 min saved × $90 × 46 sale weeks

Same Monday. Different job.

Before

The valuations still reflect last week's sales. Appraisers pull the auction reports, re-check outliers by hand, and queue the hard lines for a senior valuer.

After

The weekend's sales are already priced in. The model has matched the closest past lots; appraisers sign off the flagged ones and move on. No peak-season bottleneck.

Proof first, then production. AWN approved the build on the results. AWN also put brokers, clients and internal teams on one platform. Platform phase: 30% more transaction volume year on year, 20% more active clients.

C. 3 images in body for portfolio (5)

Is a workload growing faster than your team, and you're not yet sure AI is the answer?

NEXUS Foundation proves where AI creates value on your own data, and delivers a working AI solution in eight weeks, before you commit to a bigger build.
Book Your Free Discovery Call
1 Your Information
2 Book Meeting
3 Confirmation

Tell us about your app. We'll take it from there.

Share a few details about your project and what you need help with. Once you submit the form, you’ll be able to book your free discovery call.
Contact EB Pearls
What to expect on your call

What to expect

  1. 1 Share a few details
    Complete the form with your contact details and what you need help with.
  2. 2 Book your free discovery call
    Once you submit the form, choose a time that suits you for your discovery call.
  3. 3 Privacy comes first
    Sign an optional NDA to ensure the highest privacy level and protection of your idea.
  4. 4 Discovery call
    We’ll discuss your goals, the support you need and answer your questions. If we’re a good fit, we’ll outline the next steps.

What to expect

  1. 1 Share a few details
    Complete the form with your contact details and what you need help with.
  2. 2 Book your free discovery call
    Once you submit the form, choose a time that suits you for your discovery call.
  3. 3 Privacy comes first
    Sign an optional NDA to ensure the highest privacy level and protection of your idea.
  4. 4 Discovery call
    We’ll discuss your goals, the support you need and answer your questions. If we’re a good fit, we’ll outline the next steps.