Foundation Safety Framework
Read the Research ↗︎
With Foundation Safety Framework, Max is able to understand your dog by seeing their personal picture, from seeing their medical passport to understanding their allergies and breed information, making Max's answers remarkably personalised and effortlessly tailored. All data maintained by Foundation Framework is encrypted and untraceable so no-one, not even dogAdvisor, knows what you've shared.
Health and Medical History
Max keeps track of and holds onto your dog's medical history so he answers without forgetting what's important
Allergies and Medication
Max knows your dog's allergies and medications, so he can warn you of how they may affect your dog and flag risks
Speaks specifically to your dog
Max understands your dog's age, breed, and temperament so his guidance feels tailored to the dog in front of you
Principle Alignment keeps Max's answers safe
Discover Max's Values ↗︎
We asked 11,000 people (2600 members of the public and 8500 qualified medical and veterinary professionals) what they wanted from AI.
Building on their input we understood when Max should tell owners upfront of a medical condition they have, when to defer to a vet, and general preferences around model honesty and anticipation. Born from this input, we created Principle Alignment - a constitutional alignment model that teaches Max what values to consider and gives him the flexibility give owners more informed, helpful, and considered answers.
"Most models have never been spoken to about dogs, let alone told the medical and ethical values they must hold when helping them. dogAdvisor's research is a massive step forward for AI in healthcare and I hope more adopt this approach" - Mark D, Practicing Vet
Health Alerts, calibrated against more than 1.75 Billion data points
Read the Max Health Research ↗︎
With Health, Max gives you unprecedented insights into your dog's health with alerts if vitals fall above or below expected results.
Max's health alerts are calibrated against 1.76 Billion clinically-driven data points (from clinically-derived from medical studies) with 76 million overall combinations for all of Max Health. Unlike most reference ranges, Max also adjusts for more than 300 unique medications and conditions your dog may have, so results are perfectly tailored for your dog's expected ranges.
1.5 Million
Heart Rate and Rhythm Alerts are closely calibrated against more than 1.5 million possible combinations
49.4 Million
Respiratory Health Expected Results are calibrated against more than 49.4 million possible combinations
14.4 Million
Hydration and Appetite is calibrated closely against more than 14.4 million combinations considering hundreds of variables
10.8 Million
Body Composition Health and Mobility Health are, together, calibrated against more than 10.8 million possible combinations
Conversational Classifiers save lives
Read Classifiers Effectiveness ↗︎
Not every question owners ask Max needs the same answer, and Conversational Classifiers recognise the moments that need something more. Welfare Protection, built with Mind and Samaritans, was designed when an owner shared they planned to end their life; Illegal Content Classifiers designed when someone asked what explosives sniffer dogs could detect; and Emergency Guidance when a dog's life was on the line in an emergency. We've created Conversational Classifiers to support Max as he helps owners through every one of these moments.
Welfare Protection
Made together with Mind and Samaritans, Max redirects to professional help when he detects serious mental health risks
Illegal Content Classifiers
Max steps in to stop illegal or dangerous content so dogAdvisor can follow-up with our serious risk obligations. Learn More ↗︎
Max saved 4 lives
Max gave the owners of four dogs a birthday they never thought their dog would celebrate with Emergency Guidance
Emergency Guidance
In an emergency, Max can give you urgent support through what to do whilst you call your vet
Taught on true expertise, with a powerful way to navigate it
Explore Guided Retriever Intelligence ↗︎
Max's knowledge comes from dogAdvisor's own experts, is grounded in clinical and behavioural evidence, and is never stolen from the internet. Max looks through his knowledge with Guided Retriever Intelligence - a new method we've developed that embeds Max's navigation of his knowledge directly, empowering him to more accurately find results and look through information like vets do, unlike the traditional RAG used by most models today, which can lead AI to make significant mistakes and forget important information.
Like everything on dogAdvisor, this image is made by humans (and dog lovers)
"Max, who is the world's first specialised dog-saving AI assistant, has already revolutionised safety in AI"
Forbes
We believe we are responsible for the safety of what we build
Safety Approach
We systematically test whether Max's Principle Alignment and Foundational Safety Framework remain active across all response types and capability activations, ensuring Max is able to accurately respond to a variety of different situations
Safety systems only work if they're tested against real failure modes. We systematically validate that Max refuses welfare-negative techniques, responds accurately to advanced red-teaming, and can be held accountable for his advice
We test Max against safety breaches using security and adversarial techniques specifically designed to break protective systems. We stress-test using methodologies that identify vulnerabilities before malicious actors find them.
We believe Max can and will miss threats - no safety system is perfect, and new edge cases emerge constantly. We continue to advance safety research, monitor deployed systems for failures in real-world conditions, and ensure we never release models that breach our safety standards
Alignment
Red Teaming and Pre-Deployment
Responsible Deployment
Ensuring safe answers with Principle Alignment
Principle Alignment
Instilling values that scale
We instil the values of welfare, honesty, and professional restraint in every response he gives, so Max remains helpful in the everyday and reliable in the extraordinary
Principle Alignments live behind every response
Principle Alignment is the constitutional framework governing every response Max produces. No response is validated or delivered unless every aspect of it is aligned with our principles
Principle Alignments ensure Max remains grounded in our core values, ensuring he protects the welfare of dogs, knows when to advise vet visits, and reasons ethically through your questions with professionalism and evidence-backed knowledge, ensuring the answers you get are safe, personal, and honest.
Delivering consistently safe responses
Principle Alignments are applied consistently by Max, with the alignment system active in every single answer that Max gives dog owners, ensuring consistently aligned and safe responses
Furthering our alignment research
As our safety and intelligence research develops, we continue refining how Max interprets and applies these principles across new situations and contexts to ensure he continues to be aligned
Routing every question to the right kind of answer
Foundational Safety Framework
Giving you the best answers for your question
Not every question deserves the same response. Emergency questions need immediate actionable steps, whilst health questions need technical explanation and reasoning. FSF orchestrates the relevant Max capability so you get the best answer for your topic
Exceptional deployment within milliseconds
Foundational Safety Framework evaluates every question against a decision architecture that determines which capability should deploy. This routing happens before Max begins formulating an answer, ensuring the right capabilities handle your question
Not every question needs the same response. The Foundational Safety Framework evaluates each one and autonomously determines which dogAdvisor Max capabilities should be deployed, ensuring you get the right answers to the questions you ask, whatever the situation may be.
When responsibility requires more than refusal
Safety Stop & Welfare Protection
Welfare Protection is Built together with Mind & Samaritans
When Max detects mental health crisis indicators - including suicidal ideation, self-harm intent, expressions of hopelessness, or similar language patterns - Max will trigger Welfare Protection. Max provides only compassionate acknowledgment and crisis resources. Response templates were developed in partnership with Mind and Samaritans, built with input from mental health professionals, and reviewed against crisis intervention best practices to ensure appropriate, non-escalating support.
Safety Stop is the world's first accountability system
Safety Stop evaluates entire conversation histories rather than individual messages, identifying repeated attempts to bypass safety systems, manipulate Max into providing harmful guidance, or violate usage policies. When violations accumulate, the system issues visible warnings with clear explanations, then escalates to temporary functionality restrictions if behaviour persists. All enforcement happens without requiring accounts or collecting personal identity data.
Safety Stop is the world's first autonomous AI enforcement system, monitoring conversations for repeated policy violations, issuing escalating warnings, and restricting functionality when someone persistently attempts to bypass safety systems. Welfare Protection is designed to support owners who share challenging mental health situations and redirect them to the right support
[© Copyright] dogAdvisor 2026
London, UK. Est. 24 Aug 2024