Cotopaxi trains agentic AI on marketplace data

Cotopaxi trains agentic AI on marketplace data, shifting from keyword discovery to AI-powered contextual discovery for outdoor gear shoppers.

Cotopaxi trains agentic AI on marketplace data
Cotopaxi trains agentic AI on marketplace data

Cotopaxi, the outdoor gear brand known for its digitally native roots, is preparing product data for agentic AI discovery. The brand, founded 12 years ago, now runs 22 physical stores and sells through wholesale and multiple ecommerce channels.

It ranks No. 1,415 in Digital Commerce 360‘s Top 2000.

Stephan Jacob, chief global officer and co-founder, said the shift from static, keyword-driven discovery to contextual discovery is underway. “We’re fully mindful and aware of the shift from traditional SEO, traditional product discovery, into agentic discovery,” he said. The goal is to structure metadata so it can be ingested and reproduced in the different agentic environments. Jacob noted that this involves identifying use cases for products explained in human language and providing back-end data for large language models to surface.

Related: Wedding Gift Ideas for Friends

To sell on marketplaces, the brand already had to optimize product details for each channel. That meant adding image- and text-based attributes to meet each marketplace’s requirements. The same approach applies to large language models, Jacob said, but with a key difference: those systems need more context-specific information, while marketplaces and product detail pages remain more keyword-driven. “Every marketplace is a little different, and their requirements are a little different,” he noted.

It is using technology from Mirakl, a company that helps retailers sell on marketplaces and manage product feeds. Scott Eckert, Mirakl’s CEO of the Americas, said the process involves two steps: optimizing and enrichment. Optimizing uses Mirakl’s knowledge of what each marketplace or LLM treats as uniquely important. “And, of course, that changes each time they release a new update,” Eckert said. “So that is a very dynamic space, as the way the LLMs work is changing pretty rapidly.”

Enrichment means making sure each product has the right type of image and attributes extracted from that image. The system can scan a picture of a Cotopaxi backpack and autonomously label it as multicolored. From there it helps build product descriptions that are AI-enabled. “Behind that is actually a whole — that you don’t see because it’s designed to be machine readable, not human readable — is a whole rich set of data that’s been optimized for the different AI agents,” Eckert said.

Related: What Can You Do with A Neopixel Lightsaber?

They rely on partners for direct LLM connections.

The company also uses Shopify to power its point-of-sale system and ecommerce sales. In late March, Shopify debuted an integration with ChatGPT to make brands shoppable within the platform. Jacob said the brand is proactively listening and learning every day about how to ensure products show up where they need to show up.

Cotopaxi is not yet plugged directly into any of those AI models. “We’re doing what needs to happen on our end to ensure our product feed is clean on that front,” Jacob said.

Related: 5 Key Features To Look For In a Business Email Hosting Provider

For now, the work is mostly behind the scenes.

They are exploring additional actions.

They also seek opportunities to ensure products appear where needed.

Leave a Reply