From Problem to Production: What I Learned Building an AI Product That Delivered Real Commercial Value
About this session
What happens when you start with a time intensive manual business process, experiment with AI to solve it, and end up designing, building and deploying a production AI product? Coming from a research and insights rather than an engineering background, I set out to automate a market intelligence workflow that was taking my function around 30 hours each month. What began as experimentation developed into an AI-powered product now used by 30+ colleagues (and continuing to scale) across multiple business functions. For my function alone, the original process has reduced from around 30 hours to approximately one, alongside wider measurable business value. Getting from prototype to production, however, exposed lessons I hadn't anticipated: data reliability, APIs and integrations, prompting and debugging, model selection, token economics, automation frequency, testing, monitoring and the less visible infrastructure behind the user experience. Deployment created new questions too. As adoption grew, the volume and ways in which people used the intelligence expanded beyond some of my original expectations, creating new user needs and opportunities to iterate. This session shares the practical realities of a first time AI product build: what worked, what broke, what I would do differently, and why successful AI products require as much thought about the problem, users, economics, measurement and ongoing value as the technology itself.
Speaker
Key takeaways
- Start with the problem, not the AI. Learn how applying a product mindset (understanding the problem and user needs, testing whether a solution can work in practice, considering the value it could create, and designing for different users) provides the foundations for useful AI products before the technology is built.
- The prototype is only the beginning. Learn what changes when a first time, non-technical AI builder moves from experimentation into production, including prompting AI to investigate before changing code, debugging systematically, testing for unintended consequences, choosing appropriate models, managing token costs, connecting data and APIs, monitoring reliability, and building the less visible infrastructure required to keep a product working.
- Design measurement into the product, not as an afterthought. Learn why production AI needs visibility of both cost and value, from token consumption and operational performance to user engagement, adoption and feedback, and how those signals can inform ROI, expose emerging user needs and guide what you build next.