You type a research question into your AI tool, get back a perfectly serviceable answer, and still feel like something's missing. The output isn't wrong, exactly. It just didn't quite hit the mark. The culprit, more often than not, is the prompt you started with.
The good news: there's a smarter way to approach this, and it doesn't involve becoming a prompt engineering expert.
In this How I AI episode, Neo and I walk through the agent Neo reaches for more than any other he has built: the Research Prompt Builder. We get into how it works, when to use it with a thinking model instead of deep research, and how pairing it with NotebookLM can get you genuinely well-briefed in a fraction of the usual time.
What you'll learn in this episode:
Why your research prompt matters more than the tool you use
How Neo's Research Prompt Builder actually works before any research begins
When a thinking model is a better choice than deep research
How to go from a raw research output to a proper briefing using NotebookLM
Practical AI tools for productivity and focus
Real-world AI workflows used by high performers
How to use AI at work without burning out
Smart shortcuts for managing time and mental load
Connect with Neo Aplin on LinkedIn (https://www.linkedin.com/in/neoaplin/) and via inventium.ai (https://inventium.ai), where he leads Inventium's AI training and upskilling work with organisations and teams.
And here are links we promised:
Download the Research Prompt Builder agent here: https://amantha-imber.kit.com/41cec7c48c
NotebookLM (notebooklm.google.com) - Google's learning tool that lets you upload up to 50 sources and generate a podcast episode, ask questions, and get cited answers from your own documents.
How I AI with Dr Amantha Imber and Neo Aplin explores how high performers are using AI at work to boost productivity, make better decisions and reduce overwhelm.
Want more practical ways to put AI to work? You can now follow How I AI separately on Spotify or Apple Podcasts so you never miss an episode.
A small dose of big thinking.
Every week, I share my favourite science-backed hacks, ideas, and strategies to make work (and life) a little better. Join 40,000+ readers who like their advice practical, proven, and easy to steal.
Promise: No spam. No selling your data for a packet of Tim Tams.