The Recommendation Engine for Commodity Traders — Anekha Sokhal, Moshi
10. The Recommendation Engine for Commodity Traders — Anekha Sokhal, Moshi
Open the permanent podcast page
Show: Latent Space
Focus: Agents for Everyone
Date: October 22, 2026
Duration: 27:00
Summary: Anekha Sokhal explains Moshi’s attempt to turn fragmented commodity-market data and analyst routines into source-aware recommendations. The interview covers Bloomberg workflows, document extraction, trusted-source selection, task-oriented dashboards, customer discovery and the limits of automating decisions in high-stakes trading contexts.
Why it matters: Knowledge-work teams can borrow the source-selection and workflow-discovery method without copying the product claim: observe real decisions, identify trusted inputs, extract bounded evidence and keep a human accountable for consequential recommendations.
Coverage: Selected for this edition.
Listen / watch: Latent Space