<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/the-recommendation-engine-for-commodity-traders-anekha-sokhal-moshi-krrfw50ar" -->

---
title: The Recommendation Engine for Commodity Traders — Anekha...
description: Anekha Sokhal, CEO of Moshi, describes building an AI recommendation engine for commodity and energy traders. Moshi processes structured market data,...
canonical: https://daily.dev/posts/the-recommendation-engine-for-commodity-traders-anekha-sokhal-moshi-krrfw50ar
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: The Recommendation Engine for Commodity Traders — Anekha Sokhal, Moshi | daily.dev
og:description: Anekha Sokhal, CEO of Moshi, describes building an AI recommendation engine for commodity and energy traders. Moshi processes structured market data,...
og:url: https://daily.dev/posts/the-recommendation-engine-for-commodity-traders-anekha-sokhal-moshi-krrfw50ar
og:image: https://api.daily.dev/og/posts/krRFw50ar.png
og:image:alt: The Recommendation Engine for Commodity Traders — Anekha Sokhal, Moshi
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# The Recommendation Engine for Commodity Traders — Anekha Sokhal, Moshi

**[Latent Space](https://daily.dev/sources/latentspace)** · 26 min read · 0 upvotes · 0 comments

## Summary

Anekha Sokhal, CEO of Moshi, describes building an AI recommendation engine for commodity and energy traders. Moshi processes structured market data, fundamentals, news, social posts and users' private data to surface what matters to a trader's book. She says it learns about 300 new data points in the four seconds it takes to say a sentence. Sokhal calls it a mix of Bloomberg, Claude and Netflix, built around a graph-based recommendation system rather than dashboards. The team built its own vision language model for messy PDF data instead of using third-party document processors, partly to avoid sending client data elsewhere. A job posting drew 2,500 applicants in four days.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.latent.space/p/the-recommendation-engine-for-commodity>

## Questions this post answers

### What does Moshi do for commodity and energy traders?

Moshi is an AI platform that provides real-time insights for financial traders, starting with commodity, energy and macro markets. It processes structured time series data, fundamentals, news, alternative data like social posts, and the user's own private data and subscriptions, then runs a built-in recommendation system that surfaces connected market signals, such as how an equities move might indirectly affect oil, before a trader would notice it in a news stream.

_Those tracking new AI tools built specifically for trading workflows can follow coverage like this on daily.dev._

### Why did Moshi build its own vision language model instead of using a third-party document extraction tool like Reducto?

Moshi built its own vision language model for processing messy PDF data partly because clients don't want their data sent to a third party, and partly because Moshi's team, many of whom have worked with NASA, had the engineering capacity to do it themselves. The company notes that teams without dedicated engineers are often better off using an off-the-shelf document processing vendor instead.

_Developers weighing build-versus-buy for document processing can track real examples like this on daily.dev._

## Similar posts on daily.dev

- [Solving retail’s cold-start problem: Malachyte's recommendation reinvention](https://daily.dev/posts/solving-retail-s-cold-start-problem-malachyte-s-recommendation-reinvention-8tnuhwbus) · Google Cloud · 0 upvotes · 0 comments
- [AI Search and Discovery: Building Smart Product Recommendations](https://daily.dev/posts/ai-search-and-discovery-building-smart-product-recommendations-5pw13b1o1) · Netguru · 0 upvotes · 0 comments
- [AI optimization: How we cut energy costs in social media recommendation systems](https://daily.dev/posts/ai-optimization-how-we-cut-energy-costs-in-social-media-recommendation-systems-aui3bciak) · InfoWorld · 0 upvotes · 0 comments

---

Tags: [#llm](https://daily.dev/tags/llm), [#fintech](https://daily.dev/tags/fintech), [#recommendation-systems](https://daily.dev/tags/recommendation-systems)

[View this post on daily.dev](https://daily.dev/posts/the-recommendation-engine-for-commodity-traders-anekha-sokhal-moshi-krrfw50ar)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"The Recommendation Engine for Commodity Traders — Anekha Sokhal, Moshi","url":"https://daily.dev/posts/the-recommendation-engine-for-commodity-traders-anekha-sokhal-moshi-krrfw50ar","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-recommendation-engine-for-commodity-traders-anekha-sokhal-moshi-krrfw50ar"},"datePublished":"2026-10-22T14:06:44.971Z","dateModified":"2026-10-22T14:11:49.616Z","description":"Anekha Sokhal, CEO of Moshi, describes building an AI recommendation engine for commodity and energy traders. Moshi processes structured market data,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/14bde1e3b891bc4a71ac68eb666eb1a9?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/14bde1e3b891bc4a71ac68eb666eb1a9?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Latent Space","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Latent Space","logo":"https://media.daily.dev/image/upload/s--DnJ9laFj--/f_auto,q_auto/v1780213196/logos/latentspace?_a=BAMAMiWQ0","url":"https://daily.dev/sources/latentspace"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-recommendation-engine-for-commodity-traders-anekha-sokhal-moshi-krrfw50ar","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,fintech,recommendation-systems","timeRequired":"PT26M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Latent Space","item":"https://daily.dev/sources/latentspace"},{"@type":"ListItem","position":3,"name":"The Recommendation Engine for Commodity Traders — Anekha Sokhal, Moshi"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/the-recommendation-engine-for-commodity-traders-anekha-sokhal-moshi-krrfw50ar#faq","mainEntity":[{"@type":"Question","name":"What does Moshi do for commodity and energy traders?","acceptedAnswer":{"@type":"Answer","text":"Moshi is an AI platform that provides real-time insights for financial traders, starting with commodity, energy and macro markets. It processes structured time series data, fundamentals, news, alternative data like social posts, and the user's own private data and subscriptions, then runs a built-in recommendation system that surfaces connected market signals, such as how an equities move might indirectly affect oil, before a trader would notice it in a news stream. Those tracking new AI tools built specifically for trading workflows can follow coverage like this on daily.dev."}},{"@type":"Question","name":"Why did Moshi build its own vision language model instead of using a third-party document extraction tool like Reducto?","acceptedAnswer":{"@type":"Answer","text":"Moshi built its own vision language model for processing messy PDF data partly because clients don't want their data sent to a third party, and partly because Moshi's team, many of whom have worked with NASA, had the engineering capacity to do it themselves. The company notes that teams without dedicated engineers are often better off using an off-the-shelf document processing vendor instead. Developers weighing build-versus-buy for document processing can track real examples like this on daily.dev."}}]}
```

