Microsoft Consumer Goods Global Company newsroom

Unilever

Unilever's Lifebuoy brand needed a more engaging and scalable way to teach children correct handwashing habits across many countries, languages, and local contexts so hygiene education would drive stronger behaviour change.

100% of children taking part in our tests expressed a desire to learn more about handwashing with soap at school
28% more children used a correct handwashing technique
8x improvement in their awareness of critical handwashing occasions

Reported impact

Business outcome

In early testing, the personalised experience substantially improved awareness of key handwashing moments, increased correct technique, and raised children's interest in learning more, while giving Lifebuoy a scalable and cost-effective education tool that also supports brand equity.

  • Customer Experience
  • Scalability

Solution

Unilever built Lifebuoy's AI-Teacher Hippo as a personalised hygiene education experience for children and used Microsoft as the primary external AI platform provider. The experience takes child-specific inputs such as name, favourite colours, favourite foods, and location, then uses Azure Open Enterprise APIs to generate AI-driven content in multiple languages for each child. Lifebuoy combined that generation layer with Aircards' AI and AR capabilities so the lessons could become interactive rather than static. The resulting experience is served on smartphones or tablets and lets children choose formats such as a handwashing song, game, or digital colouring book. Unilever says the system was designed for use across 11 markets and five languages. The source does not identify a separate storage product or database, but it clearly describes the ingestion of personalisation inputs, AI content generation, AR-enhanced delivery, and school/community deployment at scale.

Data flow

A child accesses AI-Teacher Hippo on a smartphone or tablet, where the experience uses inputs such as the child's name, favourite colours, favourite foods, and location. Azure Open Enterprise APIs generate the personalised multilingual content, AR elements make the lesson interactive, and the finished experience is delivered as songs, games, or a digital colouring book for use in schools and communities.

Solution architecture

2 components · 2 layers
  1. Compute
    • Azure Open Enterprise APIs Provide the technical foundation used to generate personalised, AI-driven content in multiple languages for each child.
  2. Serving
    • AI-Teacher Hippo Delivers a personalised handwashing education experience that adapts content to each child's name, preferences, and location.

Architecture clues

  • Compatible with smartphones or tablets; a back camera is required.
  • Rolled out across 11 markets: India, Indonesia, Vietnam, South Africa, Ethiopia, Bangladesh, Singapore, Malaysia, Saudi Arabia, UAE and the UK.
  • Supports five languages: English, Hindi, Bahasa Indonesian, Vietnamese and Amharic.
  • Uses AI plus augmented reality to create real-world interactions for children.

Evidence from the source

"100% of children taking part in our tests expressed a desire to learn more about handwashing with soap at school after experiencing AI-Teacher Hippo."
"Aircards brought their expertise in AI and AR to create real-world interactions, making hygiene education captivating for kids."
"Children are empowered to choose their own learning experience, from a handwashing song or game to a digital colouring book."
"Lifebuoy's AI-Teacher Hippo tool creates a personalised handwashing education experience for every child."
"Microsoft provided the technical foundation with Azure Open Enterprise APIs, helping us generate personalised, AI-driven content in multiple languages for each child."
"That was very apparent when we tested the AI-Teacher Hippo tool with children and saw an 8x improvement in their awareness of critical handwashing occasions"
"This is the first time we've used AI to create a personalised educational tool for children, and the first time we've integrated these experiences into multiple languages at this scale."
"We found that 28% more children used a correct handwashing technique"
Transparency Evidence & methodology 100/100 reference value · 94% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    3 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence94%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    8 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Unilever

    Unilever customer story

    First-party
    https://www.unilever.com/news/news-search/2024/behind-lifebuoys-personalised-ai-powered-tool-designed-to-change-handwashing-habits/
    Source type
    Customer-published story
    Published
    Dec 3, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Dec 3, 2024 · Unilever · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.