Kinatex education committee masterclass · Montreal (online) · 24 October 2026
Masterclass
Overview
A four-hour online masterclass for clinicians in the Kinatex network, across the rehabilitation professions and mostly working in private clinics. Everything ran on free AI tools, and participants worked on their own practice throughout.
We started with what AI can now do, and with Bean and colleagues’ finding that the AI on its own named the right condition 95% of the time, while people using the same AI managed under 35%, mostly because of what they left out and how they asked. The rest of the day practised asking well, over four sessions: patient handouts and exercise programmes, checked against a guideline; research papers, guidelines and planning your own learning; admin, with patient data kept out of general AI tools; and business work, from a patient persona to a proposal for a new service. The last part turned to patients who bring their own AI into the clinic, and how we can help them use it well.
After the day
The habits I’d keep from the day are giving the AI context about you and your patients before asking for anything, and letting it interview you when you’re not sure what it needs. I’d also invent the patient, so real records stay in the tools your organisation has approved for them, and read, review, correct and approve whatever the AI gives you before it goes into a record or to anyone else. That last one is Kinatex’s rule for Plume, its clinical notes tool, and it works for any AI tool.
If you try one thing this week, take a task you do every week, do it once with AI, and keep the prompt that worked.
Handout
The one-page handout covers the four sessions, three concepts the day depends on (the context window, hallucination, and context sovereignty), four things to do next, and where to read more. It’s written for any clinician in private practice, so you don’t need to have been in the room to use it.
Further reading
- Context engineering for educators explains why what you give the model to work with matters more than how you phrase the request. It’s written for universities, and the point holds in a clinic.
- Building AI personas for professional practice is the longer version of the teach it your voice exercise.
- We’re comparing AI chatbot health advice to the wrong thing takes up the argument about patients’ own use of AI and the standards we hold it to.
- AI-powered practice growth, a full-day workshop for private practice owners in September, goes further into personas, content and business planning.
References
Anthropic. (2026, April 30). How people ask Claude for personal guidance. https://www.anthropic.com/research/claude-personal-guidance
Bean, A. M., Payne, R. E., Parsons, G., et al. (2026). Reliability of LLMs as medical assistants for the general public: A randomized preregistered study. Nature Medicine, 32(2), 609–615. https://doi.org/10.1038/s41591-025-04074-y
Brodeur, P. G., Buckley, T. A., Kanjee, Z., et al. (2026a). Performance of a large language model on the reasoning tasks of a physician. Science. https://doi.org/10.1126/science.adz4433
Brodeur, P., Koshy, J. M., Palepu, A., et al. (2026b). Conversational diagnostic artificial intelligence in ambulatory primary care: A prospective feasibility study. The Lancet. https://doi.org/10.1016/S0140-6736(26)01535-7
Epoch AI. (2025). LLM inference prices have fallen rapidly but unequally across tasks. https://epoch.ai/data-insights/llm-inference-price-trends
Evans, K., Papinniemi, A., Ploderer, B., et al. (2025). Impact of using an AI scribe on clinical documentation and clinician-patient interactions in allied health private practice: Perspectives of clinicians and patients. Musculoskeletal Science and Practice, 103333. https://doi.org/10.1016/j.msksp.2025.103333
Goh, E., Gallo, R. J., Strong, E., et al. (2025). GPT-4 assistance for improvement of physician performance on patient care tasks: A randomized controlled trial. Nature Medicine, 31(4), 1233–1238. https://doi.org/10.1038/s41591-024-03456-y
Howcroft, A., Bennett-Weston, A., & Khan, A. (2025). AI chatbots versus human healthcare professionals: A systematic review and meta-analysis of empathy in patient care. British Medical Bulletin, 156(1), ldaf017. https://doi.org/10.1093/bmb/ldaf017
METR. (2026). Time Horizon 1.1 [Data set]. https://metr.org/time-horizons
Michou, I., Fouras, A., Chrysanthakopoulou, D., et al. (2026). AI-powered physiotherapy: Evaluating LLMs against students in clinical rehabilitation scenarios. Applied Sciences, 16(3), 1165. https://doi.org/10.3390/app16031165
Office of the Privacy Commissioner of Canada. (2023). Principles for responsible, trustworthy and privacy-protective generative AI technologies. https://www.priv.gc.ca/en/privacy-topics/technology/artificial-intelligence/gd_principles_ai/
OpenAI. (2026, January 7). Introducing ChatGPT Health. https://openai.com/index/introducing-chatgpt-health/
Rossetti, S. C., Dykes, P. C., Knaplund, C., et al. (2025). Real-time surveillance system for patient deterioration: A pragmatic cluster-randomized controlled trial. Nature Medicine, 31(6), 1895–1902. https://doi.org/10.1038/s41591-025-03609-7
Tu, T., Schaekermann, M., Palepu, A., et al. (2025). Towards conversational diagnostic artificial intelligence. Nature, 642, 442–450. https://doi.org/10.1038/s41586-025-08866-7
Slides
Use arrow keys or click to navigate slides. Open slides in full screen