In this episode, I’m kicking off a special 10-part Building With AI series where I take you behind the scenes of what’s really been happening in my business. For the past 24 months, my team and I have been running an internal AI Lab — experimenting, building and iterating on real AI products and workflows.
Why I Started Talking About Building With AI
People know what you do by the work they ask you to do. And when I looked at the enquiries coming into my business, I noticed a gap — people were asking me to train their teams, advise on AI strategy and speak at events, but nobody was asking me about building with AI. That made me stop and think: do people actually know what’s been happening behind the scenes?
So I decided to open the doors to my internal AI Lab and show you exactly what applied AI looks like in practice — not theory, not tools demos, but real builds solving real problems.
What My Internal AI Lab Actually Looks Like
My AI Lab runs on a rolling work plan of ideas we want to test, build and improve. Some of those ideas are designed to make our own operations better. Some could become products. And others start with a problem I’ve spotted for a client or a sector.
My rule is simple: I start internally. I want the freedom to experiment, get things wrong, build for a while, come back to it and improve it — before I ever suggest someone else should use it. That matters because building with AI is not the same as opening a chatbot and typing a question.
What Building With AI Actually Means
I’m not claiming I sit down and manually write every line of code. I use AI tools for that, and I have an AI development team for testing, implementation and guardrails. My role is to:
- Understand the problem and shape the idea
- Provide the domain knowledge and design how the system should work
- Test what it produces and keep iterating until it reaches the standard I need
- Sometimes build the entire thing through natural language and vibe coding
The judgement about what should exist and whether it’s good enough always begins with me.
The Harvard Moment That Reinforced Everything
Before I went to Harvard in July 2025, I had the idea for GovComms.ai. While studying AI and public policy, I developed the first iteration — PolBot — and had the chance to present it. A few of my professors validated the idea, and I was one of only three people in a cohort of 74 selected to present a custom assistant. That experience reinforced something I say in my book, AI Playbook: AI is not about coding, it’s about communication.
What’s Coming in This 10-Part Series
Over the next 10 episodes, I’m going to share the custom assistants, voice agents, agentic workflows and products I’ve been building — including:
- AI Rulebook
- A misinformation and disinformation monitoring MVP
- The AI ROI Calculator
- Voice Studio
- GovComms.ai
Some are working today, some are still in development, and all of them have taught me something real about what applied AI means. My training is informed by what I build, test and sometimes break — and that’s exactly what I’m here to share with you.
If you want to build your AI literacy and skills, I can help
📚 Grab AI Playbook on Amazon, the perfect podcast companion.
📰 Subscribe to Human in the Loop, my LinkedIn Newsletter
🎓 Take the CPD Accredited AI Playbook Diploma
📞 Book a call at digitaltraining.ie
Key Statistics
– Joanne and her team have been building with AI for 24 months inside their internal AI Lab.
– She was one of only 3 people selected to present a custom assistant from a cohort of 74 at Harvard.
– She attended Harvard in July 2025 to study AI and public policy.
– The 10-part Building With AI series covers 5 named builds including GovComms.ai and the AI ROI Calculator.
About the Podcast Host
AI and Communications Specialist | Author | Podcaster | International Speaker
Joanne Sweeney is a recognised leader in digital marketing and digital transformation, specialising in the practical application of AI to enhance communication strategies. The founder of Digital Training Institute, Joanne, empowers leaders and communications professionals to leverage AI responsibly and effectively, ensuring transparency, trust, and tangible results.
She completed the Harvard Kennedy School Executive Programme in AI and Public Policy this summer before launching her fourth book AI Playbook, in September. Joanne has also published two editions of Public Sector Marketing Pro, which were preceded by her first title, Social Media Under Investigation Law Enforcement and the Social Web.
Her books have become go-to resources for governments, public sector and policing agencies, as well as marketing and communications professionals, all navigating the challenges of the changing Internet.
Joanne is the host of the AI SIX Podcast, a daily six-minute podcast that provides actionable insights, expert interviews, and practical advice to help professionals navigate the new world of work.
