Generative AI could be far easier to manipulate than businesses realise, with a simple hidden instruction potentially tricking an AI system into doing something it was never supposed to do, leaving property managers and clients exposed.
On The Property Management Excellence (PMX) Podcast, Alex Whitlock is joined by Michael Johnson from Agile Market Intelligence to unpack why AI can be so easily manipulated and what happens when businesses start giving it access to sensitive information and systems.
The pair look at prompt injection and “jailbreaking”, including the techniques used to bypass AI safeguards and convince systems to follow instructions they should have rejected.
The risks become even harder to spot when malicious instructions are hidden inside emails, webpages, or other content AI has been asked to read, potentially turning an everyday task into a security threat.
The conversation then turns to how businesses can limit their exposure, from restricting what AI systems can access and treating external content as untrusted to requiring human approval before sensitive actions are taken.
Make sure you never miss an episode by subscribing to us now on Apple Podcasts
Did you like this episode? Show your support by rating us or leaving a review on Apple Podcasts (REB Podcast Network) and by liking and following Real Estate Business on social media: Facebook, Twitter and LinkedIn.
If you have any questions about what you heard today, any topics of interest you have in mind, or if you’d like to lend a voice to the show, email
Want to see more stories from trusted news sources?Make Real Estate Business a preferred news source on Google.
