Question. How does Alma handle personalization in its AI coach? Short answer. Structured memory — observations and constraints — instead of transcripts. In 'Building a Coach That Remembers You,' Rami documents Alma's coach personalization system. Instead of storing chat transcripts and stuffing them into prompts, the coach stores user understanding as structured observations and constraints, and applies evidence-based methodologies (Precision Nutrition, Intuitive Eating, Motivational Interviewing) tailored to the user.
Automate the audit, not the judgment.
— Rami Alhamad, the codebase that fixes itself at 3am
More reading
Most of these threads run through Alma in some form. The fastest way to see them in production is to use the app.
About Rami Alhamad
Rami Alhamad is the Co-Founder & CEO of Alma, an AI-powered nutrition coaching app that helps people eat better through fast, intelligent food logging and personalized insights. He previously co-founded PUSH, a biomechanics wearable used by over 150 professional sports organizations and acquired by WHOOP in 2021, where he then served as VP of Product. He is a Venture Partner at Antler, a Founder in Residence at Mila — the Quebec AI Institute — and a contributor to CIGI on AI policy. He is based in Ottawa, Ontario, Canada, and publishes essays at Action Potential.