29-05-2025
From prompts to prototypes: How to build with AI like the pros
Building your first AI assistant doesn't require a CS degree. All you need is a laptop and a few good prompts.
That was the takeaway from the 'AI Tools Basics' workshop at the 2025 Builders Conference, where Jason Michael Perry of PerryLabs and the University of Pennsylvania's Jeremy Gatens led a hands-on session showing how to turn generative AI from a novelty into a practical productivity partner.
'Today's AI is the worst AI you're ever going to use,' Perry said, noting that the technology is evolving quickly.
Perry walked the classroom-sized crowd through how to customize ChatGPT by using what's known as agentic AI. Giving the model more detail about yourself yields dramatically more relevant, useful and human-like results. As he demonstrated, agentic AI can not only generate text but also act as a sounding board, content strategist, and even campaign composer.
It's a reminder that the key to AI is not just what you ask, but also what the system knows about you when you ask it.
'I can tell it if I have kids, where I live, my neighborhood, and by giving it this information, ChatGPT starts to get context,' Perry said. 'It starts to become a little bit more aware of who I am.'
That setup paves the way for a suite of other generative tools, Perry demonstrated. He created a campaign-ready song using Suno, an AI-powered music generator, and built a competitive media plan using Perplexity's research capabilities.
AI is for builders, not just technologists
Gatens, who heads IT for Penn's Division of Human Resources, focused on how to apply the same logic to building applications using a generative AI platform designed to transform written requirements into working prototypes. He emphasized the importance of thoughtful preparation: feeding an AI builder better inputs leads to better outputs.
Gatens also shared a prompt-building workflow rooted in the RACE framework (Role, Action, Context, Expected outcome), moving ideas from vague to actionable in just a few steps, with the help of generative AI tools Claude and Gemini. This process makes products like Loveable not only more effective but also more accessible to non-developers, he said.
'We could start with Loveable — we could have done all this in Loveable,' Gatens said. 'But by refining the idea with good technical requirements, it gives you a better chance to be successful.'
For all the technical details, the session's bigger message was about redefining the relationship between people and machines. Perry described his AI assistants like creative colleagues — with personalities, perspectives, and specific jobs to do.
How we got here and what's next
This year's Builders Conference leaned into the practical applications of AI, and the 'AI Tools Basics' session was one of the clearest examples. Perry, a longtime technologist and CTO, has built a reputation for demystifying AI through accessible frameworks and real-world use cases. Gatens brings a user-focused perspective rooted in public-sector IT and workforce development.
Both emphasized the importance of play and experimentation. The session was lively, filled with audience interaction, live demos and even original music. The point wasn't just to teach tools, but to spark ideas.
Both presenters fielded questions about AI's role in education, the future of AGI (artificial general intelligence) and the need for workplace readiness. Perry warned that most organizations aren't structurally ready to take full advantage of AI, with legacy systems and data silos creating major hurdles.
But he also framed it as an opportunity.
'I always like to remind folks that we are in the AOL days of AI,' he said. 'That's how early this is.'
That accessibility and sense of possibility seemed to resonate with the crowd. As the session ended, attendees clustered around Perry and Gatens, eager for links, prompts and follow-ups.
'It's not crazy to think that we're going to have ChatGPT-style AI and robots roaming the world in households under $20,000 within the next two to three years,' Perry said. 'We're about to see much more transformation in ways that we may not be expecting, quicker than we expect.'
