Demand forecasting typically requires data scientists and weeks of work. Small businesses can't afford that but still need to avoid stockouts and overstock.
Built a multi-agent system using CrewAI. Three specialized agents — Forecaster (analyzes data), Risk Analyst (flags anomalies), Narrator (writes executive summaries) — collaborate to produce actionable forecasts.
Agent orchestration — each agent's output feeds the next, chain failures cascade
Confidence band calibration across different product categories
Narrative generation that's specific enough to be actionable, not generic summaries
Handling sparse data for new products with limited history