The past year has seen an explosion in the capabilities of AI and automation, and a parallel explosion in hype. For designers working in fast-moving, resource-strapped product environments (like I do), the pressure to “embrace AI” is constant. But it’s not enough to bolt it on for the sake of innovation theatre.
Done right, AI can be a force multiplier for product teams, accelerating discovery, unblocking prototyping, and removing the grunt work that drags us away from meaningful problem-solving. But it takes experimentation, strong principles, and constant critical thinking to make it actually useful and safe in practice.
This blog series is my attempt to document how I’ve been integrating AI and automation into my work as a product designer and design leader, where it’s helped, where it’s failed, and what I’ve learned along the way.
1. Prototyping at the Speed of AI
How tools like Lovable help me build interactive prototypes in hours, not weeks, and why that speed comes with serious caveats.
Generative design tools have changed the way I demo, ideate, and validate ideas with clients and stakeholders. This post breaks down how I use them effectively, the risk of overpromising, and how to keep engineering, design, and delivery in sync.
2. Automating the Boring: Internal Process Wins with AI + n8n
How I used AI and automation to turn a 2.5 week onboarding task into a 2-hour workflow, saving thousands and keeping my team sane.
This post covers how I’ve used n8n and agentic AI to automate painful internal tasks like folder scraping, file matching, and document parsing — and how even basic automation can transform your team’s operating rhythm.
3. Using LLMs to Accelerate Research and Domain Understanding
Why I use AI as a “fast pass” to NHS domain knowledge — and how I avoid designing for the idealised version of reality.
LLMs have become my go-to starting point when working in highly complex domains like healthcare. I’ll share how I use them to reduce ambiguity, build trust with clients faster, and bridge knowledge gaps without relying on one SME.
4. Principles for Safe and Impactful AI in Design
Reflections, boundaries, and what it means to lead with AI in the loop, not in the driver’s seat.
In this closing post, I share the lessons and guiding principles I now follow when using AI in my work. From data security to design quality, this is how I stay grounded in reality while still pushing forward.