ABN AMRO
Designing a conversational AI search strategy
Summary
A modular approach to conversational AI search, creating a seamless, personalized central entry point for millions of banking customers.
We partnered with ABN AMRO to design their modular approach for conversational AI search. The goal was to create a seamless and personalized experience for customers, increasing their autonomy and reducing support costs, by unifying the bank's Search and Help capabilities through a single, conversational interface.
Services
Industry
The Challenge
Moving beyond scripted chatbots toward a unified, conversational banking experience.
ABN AMRO had experience with conversational AI, having launched and iterated on both customer- and employee-facing chatbots. However, the release of advanced multi-modal models presented an opportunity to progress beyond scripted interactions and build a more intuitive, natural experience. They sought to create a strategy that unifies the experience of Search and Help with the support of conversational AI while leveraging their newly adopted modular design approach.
Problem 01
Fragmented customer touchpoints
- ▪Search and Help existed as separate experiences
- ▪Customers navigated multiple channels for simple tasks
- ▪Scripted chatbot limited to predefined conversation flows
- ▪No unified entry point across digital services
Problem 02
New technology, unclear integration path
- ▪Advanced LLMs created new conversational possibilities
- ▪Need to balance innovation with banking-grade reliability
- ▪Modular design approach required integration strategy
- ▪Solution needed to scale across all customer segments
The Approach
We worked closely with ABN AMRO's internal conversational design team to create a modular approach for conversational search through a structured, iterative process.
01
Customer experience audit and competitive analysis
We began by evaluating the existing customer experience, identifying available channels, and exploring how leading competitors offered search and help functionalities. Stakeholder workshops aligned goals, outcomes, and priorities.
02
Concept design and user testing
We generated a range of design concepts based on market analysis, process mapping, and internal data collection. User testing with bank customers played a critical role in validating our assumptions.
03
Technical assessment and strategy roadmap
Parallel sessions assessed feasibility and technical implications of the proposed solution. The resulting strategy incorporated insights into an evolutionary approach, gradually building upon existing capabilities toward more advanced conversational experiences.
Impact
An omni-channel, omni-present central entry point for digital banking, combining the speed of search with the natural dialogue of conversational AI.
Natural Language Entry
Enables convenient capturing of customer intent in a natural way, allowing customers to express themselves freely without being constrained to banking terminology.
Reduced Support Load
Customer reliance on human assistance decreases as most queries can be handled through the conversational search interface, reducing support costs at scale.
Modular and Scalable
A composable approach that allows new capabilities to be added without rebuilding existing features, blending the most advanced language models with proven interaction design patterns.
Methods
A structured design and strategy approach combining customer research, concept validation, and technical assessment.
Customer experience audit
Competitive analysis
Stakeholder workshops
Goal alignment
Concept design
User testing
Prototyping
Process mapping
Technical assessment
Architecture review
Feasibility analysis
Strategy roadmap
Evolutionary approach
Modular design