#221 Building an AI tutor with Google DeepMind with Bibi Groot (Eedi’s Chief Impact Officer)

<p>In this episode of the Mr Barton Maths podcast, Craig sits down with Bibi Groot, behavioural scientist at Eedi, to unpack the rigorous research behind their ed-tech work. Bibi traces her journey from the UK&#39;s Behavioural Insights Team — where she applied frameworks like EAST (Easy, Attractive, Social, Timely) to public policy — to becoming Eedi&#39;s first behavioural scientist after a stint completing a PhD at UCL and having twins. The conversation builds methodically from the fundamentals of randomised control trials (and why they&#39;re so notoriously difficult to run well in schools) through the headline results of Eedi&#39;s two-year, 20-school RCT showing that students using the platform gained the equivalent of two to four extra months of progress, before diving into the much-publicised Google DeepMind collaboration. That study, run with LearnLM and a human-in-the-loop safety net, found that an AI tutor matched a human tutor on immediate question success and actually outperformed humans on short-term transfer questions — likely because the AI was relentlessly Socratic where time-pressured human tutors tended to short-circuit students&#39; metacognition. Bibi closes by previewing Eedi&#39;s much larger four-arm follow-up trial (running until July 2026) testing whether deep student context beats strong pedagogy alone, plus exciting new pilots bringing DQR and WhatsApp-delivered AI tutoring to learners in Guyana, India, and Sub-Saharan Africa. Visit the show notes here: <a href="https://podcast.mrbartonmaths.com/221-building-an-ai-tutor-with-google-deepmind-with-bibi-groot-eedis-chief-impact-officer/" target="_blank" rel="noopener noreferer">podcast.mrbartonmaths.com/221-building-an-ai-tutor-with-google-deepmind-with-bibi-groot-eedis-chief-impact-officer</a></p>