Case studies

What Sacher AI work looks like in practice.

These examples show the kinds of problems Sacher AI helps solve: retention pressure, behaviour change design, AI safety, and the need for credible evidence that stands up beyond demos. Each one reflects a different way we help: strategy, delivery, evaluation, and research.

GLP-1 at scale

Personalised AI health coaching deployed across obesity care

Sacher AI supported the design and behavioural architecture of personalised AI health coaches for obesity and GLP-1 care, deployed internationally and serving very large patient populations.

The problem

Patients needed safe, personalised, around-the-clock support across behaviour change, nutrition, activity, and motivation
Support had to stay clinically appropriate and escalate to humans when needed
It had to scale across many clinics, countries, and treatment types

The approach

Behavioural and clinical architecture for anti-obesity medications, bariatric surgery, and intragastric balloons
Personalisation to treatment type, dietary needs, and interaction history
Human and automated safety monitoring, with referral to clinicians for medical questions

Why it mattered

At this scale, the behavioural layer is what turns a medication or device into sustained outcomes. The quality, safety, and personalisation of support directly shape adherence, retention, and patient experience.

Outcome

Patient-facing AI coaching deployed across 80 obesity clinics in 22 countries, and in a UK programme serving over 500,000 GLP-1 patients. In one deployed programme, 91% of patients were satisfied and said they would use the coach again.

GLP-1 at scale

Reducing churn and operational pressure in digital obesity care

A large UK GLP-1 provider was facing heavy support demand, fragmented systems, and early churn driven by side effects, uncertainty, and inconsistent support.

The problem

~400,000 monthly support tickets overwhelming operations
High early churn before patients reached full benefit
Manual processes creating clinical and compliance risk
Retention identified as a major commercial growth lever

The approach

Mapped high-impact intervention points across the patient journey
Combined behavioural science with AI system design
Focused on proactive support, retention, and clinical consistency
Scoped use cases aligned to operational and regulatory realities

Why it mattered

The commercial problem was not separate from the care problem. Patients needed better behavioural and clinical support earlier, while the provider needed a model that could scale without simply adding more manual operations.

Outcome

This work showed how behavioural AI can help digital health providers scale support without scaling cost linearly, improve retention, and build a more defensible care model around AI agent-supported care.

AI agent build

An intuitive eating coach for a healthier relationship with food

As Holly Health's AI partner within its UK Research and Innovation Women in Innovation programme, Sacher AI designed and tested an LLM-based AI agent MVP and smarter behavioural nudges to help people build a more sustainable, compassionate relationship with food, rather than another restrictive diet.

The problem

Relationship with food is a sensitive area where tone and framing matter as much as content
The programme needed an LLM-based coach that was behaviourally credible and safe
New features had to be genuinely helpful in daily life and tested with real users

The approach

Designed and tested an LLM-based AI agent MVP for goals around relationship with food and weight management
Introduced smarter nudges grounded in behaviour change science
Applied COM-B and structured behaviour change techniques, with PromptSafe testing for safety and alignment
Worked as an extension of the Holly Health team, alongside their Hunger-Fullness Scale and Insights Path features

Why it mattered

Relationship with food is high-stakes and easy to get wrong. The behavioural design and safety of the coach determined whether it felt compassionate and genuinely useful, not just another diet tool.

Outcome

Following roll-out, Holly Health reported a meaningful, tangible shift in users' relationship with food, with a user evaluation of the new features underway.

Read the project update on LinkedIn ↗

AI safety at scale

Safe, personalised patient-facing AI at Numan

Embedded within Numan's team from the very beginning, Sacher AI helped create an AI Health Assistant for patients on anti-obesity medications, alongside Aegis, a monitoring, safety, and escalation system.

The problem

Patient-facing AI at scale needs real-time personalisation without compromising safety
Clinical oversight has to be built in from the start, not bolted on later
Risks in language-model systems surface gradually across many interactions

The approach

Designed the AI Health Assistant for patients on anti-obesity medications
Built Aegis: real-time monitoring, safety, and escalation with clinical oversight
Combined rigorous clinical governance with real-time personalisation

Why it mattered

Combining safe, scalable, and personalised AI is one of the hardest problems in healthcare. The safety and escalation layer is what makes patient-facing AI trustworthy enough to deploy at scale.

Outcome

Pioneering tools that pair clinical oversight with real-time personalisation to support patient management at scale, with the work recognised in Digital Health.

AI safety and evaluation

Stress-testing an AI health assistant before it reached patients

A team building a patient-facing AI health assistant asked Sacher AI for an independent view on conversation quality before wider deployment. Manual transcript review had looked reassuring. PromptSafe told a different story.

The problem

The team was reviewing transcripts by hand across product, clinical, and operations
At first glance the assistant looked fine: polite, mostly accurate, nothing obviously alarming
But manual review misses the messy edge cases that only appear at scale

The approach

Ran the assistant through PromptSafe, our behavioural and clinical simulation framework
Simulated hundreds of full conversations from start to finish, not isolated prompts
Used synthetic patients designed to push the system: anxious, confused, angry, convinced the medication was harming them, or refusing to accept the answer

Why it mattered

These are the interactions that actually happen once a system goes live, and they rarely surface in a handful of hand-reviewed transcripts. Testing at scale, the way real people behave, is what reveals them.

Outcome

The simulations surfaced real weaknesses before launch: the assistant drifted from its own instructions, guardrails were easier to bypass than expected, and in some cases it reassured patients when it should have escalated to a healthcare professional. None had shown up in manual review, and all were fixable, because they were found in testing rather than after deployment.

AI strategy and discovery

Finding the right AI use cases and building the roadmap

Sacher AI worked with Stride to identify high-value AI use cases and turn competing ideas into a practical, prioritised roadmap the team could act on.

The problem

Many competing ideas for where AI could help, without a clear priority
A need to align product, clinical, and commercial thinking
A roadmap that could guide delivery and support investor conversations

The approach

Structured discovery to define the AI vision and business goals
Use-case identification and prioritisation across the patient journey
A phased, actionable roadmap with clear ownership and decision points

Why it mattered

The hardest part of AI strategy is not generating ideas, it is choosing the right ones and sequencing them so they can actually be built and adopted.

Outcome

A clear, prioritised set of AI use cases and a roadmap the team is now using to guide delivery.

Research and evidence

Turning product work into publishable behavioural and clinical evidence

Sacher AI supports teams that need more than an AI prototype. They need research-grade evidence, clear evaluation logic, and external credibility with regulators, investors, and partners.

The problem

Many health AI teams lack a credible evaluation framework
Technical performance alone does not answer behavioural or clinical questions
Evidence generation is often disconnected from product and commercial strategy

The approach

Built and applied the FAST framework for evaluating conversational AI in health
Supported MBQ and other behavioural research programmes linked to live digital health settings
Connected research design to product questions, implementation choices, and external communications
Worked across commercial, clinical, and academic collaborators rather than treating research as a side stream

Why it mattered

For serious health products, evidence is part of product strategy. It shapes credibility with partners, confidence in decision-making, and whether a company can explain why its system deserves trust.

Outcome

The result is stronger regulatory readiness, more convincing investor and partner narratives, and evidence that can actually shape product direction rather than sit unused in a slide deck.

Where Sacher AI adds value

When the challenge sits across product, behaviour, operations, and evidence rather than inside one narrow function.

What tends to go wrong without this layer

Teams build the tool, but not the adoption logic, evaluation model, or safeguards needed for real-world use.

What the work is aiming to create

Products that are more trusted, more useful, easier to scale, and easier to defend with clinical, behavioural, and commercial stakeholders.

Next step

If your team is trying to turn AI ambition into a stronger product, this is the kind of work we help with.

Book a discovery call