Food and beverage companies are increasingly turning to artificial intelligence as a tool to develop and scale new ingredients and finished products more quickly, though ingredient suppliers and innovation leaders emphasize that human judgment must remain central to the process.
AI as a formulation accelerator
AI helps food developers work through complex reformulation challenges by running scenario analyses before physical prototyping begins. Thom King, chief innovations officer at Icon Foods in Portland, Oregon, described how AI can identify potential problems early in the development process. "Instead of slogging through one-variable-at-a-time bench work, we can now run scenarios before we even crack a bag of ingredients. AI can flag solubility issues, temporal gaps, off-notes, even stability risks before you burn time and money," King said.
In sugar reduction work, for example, AI can show how changing one ingredient affects multiple system properties. King noted that reducing sugar is not just about replacing sweetness: it also involves monitoring water activity, freezing point, browning, texture and mouthfeel. "Pull one lever, three others move. AI is very good at seeing those connections fast," he said. Instead of running 30 bench trials, he said teams can now run five that matter most.
Automating lab testing at scale
Tate & Lyle operates ALFIE, an Automated Laboratory for Ingredient Experimentation in Singapore that combines robotics, predictive modeling and data analytics. According to Veronica Cueva, senior vice president for research, development and solution innovations at Tate & Lyle, ALFIE can run characterization testing roughly 10 times faster than conventional methods, allowing teams to move from concept to prototype more quickly and affordably. This speed matters especially for mouthfeel work, where small formulation changes can shift texture, creaminess or stability.
Ideation and cross-company collaboration
Cargill uses an AI-enabled tool called "AskEmma" that draws on internal concept libraries, trend data and consumer insights to help teams develop buyer personas, identify needs and generate idea starters. Abhishek Roy, senior director for global digital and AI at Cargill, said the tool compresses formulation cycles from months to days, enabling teams to explore more options before costly bench prototyping. ALFIE also enables scientists in Singapore, North America and other labs to collaborate in real time, sharing data and experimental results.
Keeping humans in the loop
Ingredient suppliers stress that AI works best when paired with experienced chemists and food scientists who direct its use. Nicholas Ferraro, director of commercial and global differentiated services at Ingredion Inc., said AI must stay human-led, turning data into insight without displacing creativity. Icon Foods' King treats AI like "a junior formulator who still needs a bit of supervision," feeding it real formulation data and using it to build starting frameworks and stress-test ideas before taking concepts to the bench. Cargill relies on its experts for final analysis and application, and Roy emphasized that work that once took weeks can now happen in a fraction of the time, enabling teams to focus on refining and advancing the strongest ideas.
Expanding into upcycling and sensory science
AI also plays a role in identifying valuable compounds from waste streams. MeNow Ltd., an Israeli company, showcased technology at Vitafoods Europe 2026 that uses AI to identify potential active compounds from natural sources including waste streams. Hilla Ben-Hamo, chief executive officer and co-founder, said the approach accelerates finding compounds that address specific health or functional goals. Cargill is using AI-enabled ingredient informatics and sensory science tools to predict sweetener blend performance and sensory perception across applications, further compressing prototype validation cycles.