Tech Meridian ← LIVE FEED
PROMY MERIDIAN RU

NEWS · COMPANIES · #3330

Walmart Global Tech deploys multi-agent LLM batch system for inventory forecasting

At QCon AI, Aditya Mulik of Walmart Global Tech described deploying multi-agent LLM workflows for nightly batch inventory forecasting across roughly 4,700 U.S. stores, using techniques like MCP grounding and loop agents to handle schema violations, cross-department data mismatches, and network drops. He reported shifting from PTUs to pay-as-you-go inference reduced cloud inference costs from over $100k to around $10k per month.

KEY POINTS

  1. At QCon AI, Aditya Mulik of Walmart Global Tech described deploying multi-agent LLM workflows for nightly batch inventory forecasting across roughly 4,700 U.S.
  2. stores, using techniques like MCP grounding and loop agents to handle schema violations, cross-department data mismatches, and network drops.
  3. He reported shifting from PTUs to pay-as-you-go inference reduced cloud inference costs from over $100k to around $10k per month.

WHY IT MATTERS

This is a concrete production example of scaling multi-agent LLM workflows with built-in resilience and major cloud-cost reductions for enterprise retail forecasting.

SOURCES & TIMELINE

1