Anthropic created an LLM agent to run a vending machine in their San Francisco office. This is one of the simplest operations possible: buy products, manage inventory, set prices, talk to customers and try to turn a profit. After the month-long experiment, Anthropic concluded that their agent “made too many mistakes to run the shop successfully”. Specifically, their agent lacked basic business sense, hallucinated critical information, and failed to learn from its mistakes

Demand Forecasting is a hard problem. It’s tempting to think a tool like ChatGPT could make a planner’s life easier.

In reality, a chat interface powered by LLMs (Large Language Models) is not built to solve this problem. It uses the wrong training data, wrong training methods and won’t provide proactive, adaptive intelligence.

When your product sales are growing rapidly, it's great news for the business – but a tough challenge for demand planners.

With Omnifold, you can plan and re-plan instantly, using a self-improving model that understands the complexities of your operations and forecasts down to the finest level of granularity.

Maggie is a growth marketer at ACME. She wakes up to an email from ACME’s CMO:

“Our biggest competitor just announced huge price cuts across the board. 

I will get you 10% more budget for the rest of the month…but you’ll need to guarantee to me that this will hit our numbers. 

Please prepare a proposal for our exec review later today…