Innumerable AI agents can overwhelm. Can Walmart’s ‘super agents’ come to the rescue?

For the last few months, Walmart has been rolling out an army of AI agents to assist its workers, according to global chief technology and development officer Suresh Kumar. These AI systems help with tasks like pricing items, stocking shelves, or requesting time off. However, the growing number of individual agents has become overwhelming for users.

“If you build individual agents for every use case, it very quickly becomes overwhelming for the end user,” Kumar said.

To address this, Walmart is reorganizing its AI capabilities under four “super agents.” These enhanced personas can route queries to dozens of sub-agents within their scope, simplifying interactions. The four super agents focus on distinct groups:

• Shoppers
• Store associates
• Suppliers and advertisers
• Developers
Already live is Sparky, a shopping assistant that helps plan around occasions, summarizes reviews, and sets up recurring household orders. Another, Marty, assists merchants with ad campaigns and item listings. The internal super agents for employees and developers remain unnamed.

“The agent knows that you are a merchant. The agent knows that you are a store manager. The agent knows that you work in people services. And it also knows all our sub-agents that are there. It can coordinate,” Kumar explained. “We will have tons and tons of sub-agents underneath as we start automating more capabilities, as we start addressing more use cases.”

The power of multi-agent systems

Experts have long predicted that AI agents will evolve from isolated tools into orchestrated networks of task-specific entities. Babak Hodjat, CTO of AI at Cognizant, told us earlier this year:

“The dominant discourse in modern LLM-based agents is still leaning heavily toward building large single agents as one-stop shops, and I don’t think that scales. Multi-agent systems hold the key to leveraging AI in ways that can balance and analyze often conflicting needs to deliver higher value impact.”

Trust and governance challenges

Despite the promise, most companies are still early in adopting AI agents. A recent EY survey found only 14% of companies have fully implemented agents, with cybersecurity and data privacy concerns as the biggest barriers. Walmart has established a framework to govern access, security, and compliance. In many cases, a human remains in the loop to evaluate responses and fine-tune models when necessary.

“[We] realize that this is a journey, just like all of these other businesses,” Kumar said. “So it’s not like we are going to start on day one giving full access and full delegate authority and full capabilities to any single agent, even the super agent.”

Interoperability and future vision

Walmart is building its agents to coordinate with data sources through Anthropic’s Model Context Protocol (MCP), an open-source framework that standardizes how agents connect with external systems. The goal is full interoperability — for example, Sparky could continue a shopping journey started on another site, or the associates’ super agent might communicate with an Aetna AI agent about health insurance benefits. Kumar envisions a future shopping experience that integrates multiple media modes, from TikTok videos to photos of home decor.

“If I’ve already decided on a particular decor for my living room, what is the particular painting that I want to hang on the wall? This is not something that you can…do through search keywords,” he said. “No, you actually take a picture and you let the agent go, ‘Ah, now I understand what it is that you are trying to do: Here, let me suggest a bunch of stuff.’ So I think that is the future.”

---

Originally published at Emerging Tech Brew on August 4, 2025.

Frequently Asked Questions (FAQ)

Walmart's AI Super Agents

Q: What is the main purpose of Walmart's AI "super agents"? A: Walmart is introducing "super agents" to consolidate its AI capabilities, aiming to simplify interactions for users by having these enhanced personas route queries to numerous specialized sub-agents. This approach is designed to combat the overwhelming nature of managing individual AI agents for every task. Q: How many "super agents" is Walmart deploying? A: Walmart is organizing its AI functions under four distinct "super agents." Q: What are the focus areas for each of Walmart's super agents? A: The four super agents are designed to serve specific user groups: Shoppers, Store associates, Suppliers and advertisers, and Developers. Q: Are there already any named super agents in operation? A: Yes, "Sparky" is a live super agent for shoppers, assisting with tasks like occasion planning, review summarization, and recurring orders. "Marty" is another super agent, supporting merchants with advertising campaigns and item listings. The super agents for store associates and developers are currently unnamed. Q: What is the benefit of a multi-agent system approach, according to experts? A: Experts suggest that multi-agent systems are crucial for scaling AI by allowing for the orchestration of task-specific entities. This approach can help balance and analyze conflicting needs, leading to higher value impact, as opposed to relying on large, single agents. Q: What are the main barriers to AI agent adoption for companies? A: According to an EY survey, cybersecurity and data privacy concerns are the primary barriers. Additionally, only 14% of companies have fully implemented AI agents, indicating that widespread adoption is still in its early stages. Q: How is Walmart addressing trust and governance challenges with its AI agents? A: Walmart has established a framework for governing AI agent access, security, and compliance. They are also keeping a human in the loop for evaluating responses and fine-tuning models, indicating a gradual rollout of agent capabilities rather than immediate full delegation of authority. Q: What technology is Walmart using to ensure interoperability between its AI agents and external systems? A: Walmart is utilizing Anthropic’s Model Context Protocol (MCP), an open-source framework designed to standardize how AI agents connect with external systems, aiming for seamless interoperability.

Crypto Market AI's Take

Walmart's strategic shift towards "super agents" reflects a broader trend in AI development, moving from disparate, single-purpose AI tools to more integrated and collaborative multi-agent systems. This approach to AI management is highly relevant in the rapidly evolving landscape of artificial intelligence, much like how sophisticated AI is transforming the cryptocurrency market. At Crypto Market AI, we leverage advanced AI and machine learning for market analysis, providing insights into trends, predictions, and automated trading strategies through our AI-powered trading bots and AI analysts. This mirrors Walmart's goal of creating more efficient and user-friendly AI interactions, ensuring that AI serves as a powerful amplifier of human capability, whether in retail operations or financial markets.

More to Read:

• Walmart bets on AI super agents to boost e-commerce growth
• AI agents capabilities, risks, and growing role
• The AI gig economy is here and it pays in crypto
• How AI-driven crypto trading tools reshape market strategies