What if every monthly forecast came with the anomalies already flagged, every staffing decision started with the predicted hours, and every adjustment carried the explanation written by the AI that reviewed it? Welcome to agentic forecasting in Domo. At Domo, we’re building AI agents that do more than visualize the past. They read what is actually happening across your business, flag what doesn’t fit, predict what comes next, and route every recommendation through the right human approval. In this livestream, you’ll see an Operations Forecasting Agent built on a national industrial distributor’s data: orders history, customer accounts, weekly submissions from sales reps, finance adjustments, and the labor schedule. For every customer, in every month, the agent assembles three perspectives: budget baseline, field rep’s submission, and the finance review. Each result is compared against seasonality, customer health, and recent trends. Every unusual pattern is surfaced with a written explanation. Every predicted labor shortfall is teed up for a one-click staffing decision. Every final number is tagged with where it came from. This pattern applies across industries: - Retail and CPG: Store managers submit sales forecasts, AI flags unusual sell-through vs. seasonal baseline, the labor model converts units to shelf-stocking and checkout hours per location. - Healthcare and hospital systems: Department heads submit patient volume forecasts, AI flags census anomalies vs. historical admissions, the staffing model converts predicted volume to nursing hours per unit. - Manufacturing: Plant schedulers submit production plans, AI flags deviations from run-rate and material consumption norms, the capacity model converts units to machine-hours and shift coverage gaps. - Utilities and energy: Regional ops submit demand forecasts, AI flags consumption anomalies (weather-adjusted), the crew model converts predicted load to line technician hours per substation area. - Construction and field services: Project managers submit milestone completion forecasts, AI flags schedule slippage, the labor model converts forecasted work to crew-day requirements per site. This is what becomes possible when real agentic capability sits behind the operational rituals your teams already run. The math, the agents, and the human approval loop are running on Domo, with data shaped like the operations you live in. You’ll come away with an answer to one question: when an agent does the boring parts (the watching, the comparing, the writing-it-up), what changes about how your operations team spends its day?

 117      1