AI Agents in Retail: 
How GAIA Automates Decision-Making Processes at OTTO

Artificial intelligence has long since moved beyond its role as merely a chatbot or analytical tool in businesses. Increasingly, AI agents are taking on specific tasks within complex processes: They link data from various systems, prepare decisions, identify deviations, and trigger follow-up actions. As a result, AI is evolving from a mere assistance tool to an active participant in processes.

The potential is particularly great in retail and e-commerce. Dynamic markets and the close interdependence of product assortments, pricing, inventory, campaigns, and operational management create a high degree of complexity. AI agents can help consolidate information, reveal connections, and prepare decisions in a more targeted manner.

This is precisely where one of our current projects at OTTO comes in: With the GAIA Cockpit, we are developing a management tool for the AI agent GAIA (GEMA AI Assistant), which supports the cross-departmental GEMA meeting (GEMA stands for “Joint Market Development”). This meeting brings together key metrics, trends, and areas requiring action to prepare data-driven decisions more efficiently.

Before we dive into the GAIA Cockpit, we’d like to briefly introduce the team behind the project. We at OTTO’s Team Inc(AI) (“Inc” stands for “Incubator”) are a team of data scientists and machine learning engineers. We support the initial implementation of AI solutions for a wide variety of use cases at OTTO and guide the teams through the process from brainstorming sessions to prototype development.

OTTO’s GEMA Meeting takes place every two weeks and brings together decision-makers from all relevant platform areas.

The GEMA Meeting serves to analyze past trading activities across departments and coordinate future management strategies. The focus is on quickly identifying necessary actions, defining common goals, and establishing a shared understanding.

Precisely because so many different departments come together at the biweekly meeting, the manual effort required for preparation and follow-up is very high.
The high complexity of the topics and the interdependence of the individual organizational units also make it difficult to analyze problems quickly and clearly.
To reduce this effort, the AI agent GAIA comes into play.

GAIA is not designed as an isolated AI prototype, but rather as an expandable system for specific work processes. The following sections show how this system is technically structured and how it can be put to practical use.

Our technical foundation is Snowflake Cortex AI. Snowflake is primarily known as a database provider, but it also offers an integrated way to deploy AI agents. Snowflake’s agents are powered by common LLMs such as GPT or Anthropic models. These can access the data stored in Snowflake. A prerequisite is that the agent is granted the appropriate access rights for each data source. The data is made accessible to the agent through natural-language descriptions of the table columns—so-called “semantic views.” The agent can thus generate and execute appropriate SQL queries.

Figure 1: The GAIA agent in action in Snowflake Intelligence.

Figure 2: The GAIA Cockpit's knowledge base aggregates relevant information and makes it available to the AI agent.

The app includes the following key components:

• The ability to provide the agent with unstructured data directly via a simple file upload function, such as definitions of KPIs, economic knowledge, business logic, or minutes from GEMA meetings
• Scheduling of asynchronous agent tasks: the agent receives tasks that it is to execute at a specified time, either once or on a recurring basis. The tasks can be defined manually in the app or automatically extracted from the GEMA minutes.
• Notifications via MS Teams: Upon completion of a task, a message is sent to the GAIA Teams channel implemented via a webhook.
• Skills enable the definition of recipe-like sequences of actions to provide the agent with guidance for more specific tasks and, if necessary, support it with executable code.
• Evaluation function: Users can directly label the agent’s responses to prompts as correct or incorrect. The labeled data then serves as training data for the agent’s continuous improvement.