Blockchain technology creates the possibility for developing knowledge-intensive goods. Only a few studies in Affordance theory deal with investigating blockchain. This paper aims to discover affordances in blockchain when designing an AI-based financial recommendation system as a decision support system. The design thinking methodology was extended with machine learning and business process modelling to discover financial offerings, digital objects to be tokenised, advantages gained from the tracing affordances and consensus mechanism, and the role of smart contracts for each persona. The implementation of discovered blockchain-based applications requires a multichain framework to meet the requirements of design affordances.