Artificial Intelligence For Ambulance Dispatch
Not a Large Language Model*
Weewoo is a machine learning algorithm purpose built for emergency dispatch that is consistent, near-instant, and reliable. Because Weewoo is deterministic, it cannot hallucinate.
WEEWOO
Requested by industry. Built for industry. Proven by industry.
9.0%
Faster Avg. Response
7.5%
Less Fleet Travel
4.5%
Less Run-on*
Run-on: the hours a paramedic involuntarily works beyond their scheduled shift end.
Overtime: the hours a paramedic voluntarily works in excess of their scheduled shifts.
Overtime: the hours a paramedic voluntarily works in excess of their scheduled shifts.
Scroll
AI optimised to
Consistent · Near-instant · Reliable
The Challenge
The stakes
are real
are real
Arriving at critically ill patients seconds faster has a meaningful impact on outcomes.
However, paramedics suffer from high burnout, and demand for ambulance services is growing internationally.
Consequently, it is hard and expensive to improve response times.
However, paramedics suffer from high burnout, and demand for ambulance services is growing internationally.
Consequently, it is hard and expensive to improve response times.
10,120 lives*
The U.S. Federal Communications Commission estimated that reducing the average national ambulance response time by sixty seconds would save 10,120 lives per year in the U.S.
Est. cardiac patients saved p.a. in the U.S. / min
3.1 weeks*
Each minute in which treatment fails to occur, the brain loses as many neurons as it does in almost 3.1 weeks of normal aging.
Est. aging avoided for stroke patients / min
~7 years*
Including three years of training, translating to ~14% paramedics remaining in the workforce a decade post-registration. For context, this statistic is ~73% for doctors and ~71% for nurses in New Zealand.
Avg. professional paramedic lifespan in N.Z.
~4%*
Roughly speaking, the number of emergencies attended by paramedics increases 4% each year. This is a global trend attributable to many factors, including aging populations, increased health awareness, and the expanding scope of paramedics.
Increase in ambulance demand p.a.
How we fit
The Weewoo
approach
approach
Weewoo integrates with existing Computer Aided Dispatch (CAD) infrastructure via a secure API to either assist or automate decision making within existing emergency workflows.
Weewoo is not a Large Language Model, but a Machine Learning algorithm purpose built for ambulance dispatch that cannot hallucinate.
Weewoo is not a Large Language Model, but a Machine Learning algorithm purpose built for ambulance dispatch that cannot hallucinate.
Ambulance Service
Our API
01Caller
02Call Centre*
Call-takers perform primary triage from a call centre, often supported by Clinical Paramedic Advisors that perform secondary triage. Weewoo does not impact triage (primary or secondary).
03Dispatch Centre*
Currently, dispatchers allocate ambulance resources to emergencies in real-time. This is where Weewoo sits, providing resource allocation recommendations to dispatchers.
04Weewoo
05Crew & Vehicle*
The person driving the ambulance determines the route taken to get to an emergency. Weewoo does not impact routing.
06Incident
Weewoo's Operational Impact
Engineered
for the field
for the field
Externally Validated
Weewoo has been validated by a trusted industry third-party on real-world data. Contact us for details.
Improved Response Times
Weewoo reduces the average and 90th percentile response times to every emergency urgency class, saving lives.
Improved Paramedic Wellbeing
Weewoo improves every paramedic wellbeing KPI, from utilisation to break attainment and run-on rates, reducing burnout.
Reduced Fleet Travel
Weewoo reduces total fleet travel, reducing burnout and vehicle running costs.
Weewoo improvements over one year of historical data
Avg. P1 Response Time (n=726)
-7.6%
Avg. P2 Response Time (n=22,356)
-2.2%
Avg. P3 Response Time (n=27,130)
-11.9%
Avg. P4 Response Time (n=5,805)
-9.1%
Efficient Model Inference
~5ms per decision.
Weewoo's Social Impact
Real change
real lives
real lives
Third-party analysis shows that Weewoo reduces the average response time to both cardiac and stroke patients, having a tangible effect on patient outcomes.
~80 lives
Est. cardiac lives
saved by Weewoo
saved by Weewoo
p.a. in New Zealand
~85 years
Est. stroke patient
aging saved by Weewoo
aging saved by Weewoo
p.a. in New Zealand
The above statistics are estimates for the New Zealand population only. Contact us for a localised estimate.
Our Values
Built with patients
front of mind
front of mind
01
Reliable
Every second counts. Weewoo aims to minimise the average response time to all emergencies, not just those most urgent.
02
Intelligent
Assigning the right unit(s) is key. Weewoo follows your existing business rules when determining an appropriate response.
03
Transparent
Every dispatch decision is auditable and explainable. Humans stay in command and can override decisions, always.
04
Resilient
Systems that fail when they are needed most are worse than no system. Weewoo is built with observability and failover in mind.
The Team
People who've
been there
been there
Weewoo
Research
JM
Jordan
MacLachlan
MacLachlan
CEO & Co-Founder
A patient of 10+ years that wants to give back. PhD in Machine Learning for Emergency Dispatch.
SM
Scott
MacLachlan
MacLachlan
COO & Co-Founder
Ex-CFO of several Kiwi startups. One of four that started Kiwibank.
NC
Neil
Clayton
Clayton
Head of Engineering & Co-Founder
Three decades of shipping systems that don't break with experience you only get from learning hard lessons.
RH
Rob
Higgs
Higgs
Head of Applied Research & Co-Founder
Software engineer in machine vision & compression. Critical to achieving third-party validation.
JR
Joe
Robertshaw
Robertshaw
Research Engineer
Honours student, Research Assistant, first non-founder team member.
YM
Yi
Mei
Mei
Professor
Primary PhD Supervisor, Lead Researcher. AI/ML for Optimisation and Decision Making.
FZ
Fangfang
Zhang
Zhang
Senior Lecturer
Secondary PhD Supervisor. AI/ML for non-stationary combinatorial optimisation problems.
MZ
Mengjie
Zhang
Zhang
Professor
Tertiary PhD Supervisor. Director of the Centre for Data Science and Artificial Intelligence.
AT
Alan
Teesdale
Teesdale
Research Assistant
Masters student with strong PhD prospects.
Our Supporters
Backed by those
who get it
who get it
Research & Industry Partner
Ambulance Service
Ambulance Service
Research Partner
Research Partner
REDACTED
Industry Partner
REDACTED
Industry Partner
REDACTED
Ambulance Service
The Roadmap
From concept
to deployment
to deployment
2027
Deploy
- Parallel Run (Q1/2).
- Weewoo dispatch recommendations live in New Zealand.
- Onboard the first overseas ambulance service.
2026
Build & Test
- PhD finalised (Q1).
- Phase One investment received (Q2).
- Integrate with CAD (Q3/4).
2025
Validate
- Company Founded.
- Completed API with third-party simulation engine.
- Social and operational benefits higher than expected.
- Developed several industry partnerships.
2024
Develop
- Presented results to an Australian service and the WFA Board.
- Starting to understand social and operational opportunity.
- Third-party validation requested by Te Whatu Ora - Health New Zealand.
2023
Research
- Research Team receives NZ$1m research grant.
- Intellectual Property secured.
- 10x efficiency improvement.
- First experiments on historic data.
2022
Partner
- First experiments on randomly generated data.
- Partnership with Wellington Free Ambulance (WFA).
- 10x efficiency improvement.
2021
Start
- Research Team Founded.
- Jordan started his PhD at Te Herenga Waka - Victoria University of Wellington in Machine Learning for Emergency Medical Dispatch.
Get in Touch
Let's talk about
saving lives
saving lives
Whether you're an emergency service looking to deploy our system, an investor interested in our mission, or a researcher exploring dispatch optimisation — we'd love to hear from you.
© 2026 Weewoo Holdings Ltd. All rights reserved.