LLM Prototype for Fintech Product Discovery

Blinko AI was an early-stage London fintech startup exploring how AI and gamification could support personal finance products for younger customers. I was contacted by the CTO to help evaluate whether Large Language Models could become part of a B2B product direction for banks and fintech teams.

Problem: The team needed a realistic view of what LLMs could and could not do in a regulated financial context. The main concerns were hallucination risk, privacy constraints, integration with existing product knowledge, and whether the cost profile made sense for a startup-stage product.

Technical scope: I researched the available LLM integration strategies, compared provider tradeoffs, and helped translate broad AI ideas into concrete product constraints. The work focused less on hype and more on what could be demoed, explained, and defended in front of potential customers.

Prototype: I built a functional demo that showed how an LLM-assisted finance experience could work inside the product. The demo was designed for stakeholder conversations rather than long-term production operation, so the emphasis was on feasibility, product clarity, and risk surfacing.

Outcome: The prototype helped the startup progress conversations with a potential fintech customer, but the process did not convert into a signed contract. I keep this project in the portfolio because it is a useful signal of early LLM product work: prompt design, feasibility analysis, and the discipline of separating demo value from production readiness.