In May, PepsiCo announced a collaboration with Amazon Web Services to enhance its in-house generative AI platform, PepGenX. The partnership gives PepGenX access to various multimodal and agentic AI models on AWS.

“This strategic collaboration will strengthen our mature cloud strategy and unlock new levels of agility, intelligence and scalability across the company,” Athina Kanioura, chief strategy and transformation officer at PepsiCo, said in a statement.

The partnership spans PepsiCo’s lines of business globally. The changes include the following:

• Moving applications and workloads to the cloud.
• Giving in-house developers access to different multimodal AI models and agentic AI capabilities to enhance PepGenX, via AWS.
• Enabling insights into real-time advertising performance, audience segmentation, hyper-personalized content and targeted marketing capabilities across Amazon’s customers.
• Collaborating to transform digital supply chain capabilities, including predictive maintenance for manufacturing and logistics.

On the heels of this alliance, PepsiCo announced last month that it would deploy Salesforce’s Agentforce AI agents to manage “key functions,” enhance customer support and operational efficiency, and empower the sales team to focus on growth and deeper client engagement.

“Embracing an AI-first world means reimagining an enterprise where humans and intelligent agents don’t just coexist, they collaborate,” Kanioura said in a statement.

Humans and AI agents will be able to work together to respond faster to customer service inquiries, enable more targeted and automated marketing campaigns and promotions, and more.

In April, at Nvidia’s GTC conference, Pepsico showcased a digital twin of a warehouse using AI to simulate and optimize operations. The model incorporates generative AI and computer vision to test scenarios before deploying changes to physical facilities.

The June PYMNTS Intelligence report “AI at the Crossroads: Agentic Ambitions Meet Operational Realities” found that virtually every large organization is embracing generative AI to enhance productivity, streamline decision making and drive innovation. They are also using generative AI to improve the services and goods they offer to customers.

However, the next iteration — AI agents that autonomously perform tasks — is giving chief operating officers pause, according to the report. More than half of COOs are concerned about the accuracy of AI-generated outputs. Even narrow tasks like coding still require at least some human oversight.

See also: CPG Marketing Embraces New Business Models for Digital Transformation

Unilever, Nestlé and Coca-Cola Jump In

Unilever, the maker of Dove, Knorr, Ben & Jerry’s and more, has several AI initiatives. One of the more recent developments is the creation of digital twins of its products to add depth to their images, slated for ads.

Using Real-Time 3D, Nvidia Omniverse and OpenUSD, these 3D replicas add a “level of realism” the company has never achieved before, helping the products stand out in a sea of ads, Unilver said.

Unilever’s creative staff can also use a single product shot to change wording, languages, backgrounds, formats and other variants quickly for different channels such as TV, digital commerce and the like.

“Our product twins can be deployed everywhere and anywhere, accurately and consistently, so content is generated faster and on brand,” Unilever Chief Growth and Marketing Officer Esi Eggleston Bracey said in a statement. “We call it creativity at the speed of life.”

The use of digital twins not only cuts costs but enables Unilever to bring products to market faster, the company said.

For example, its beauty and wellbeing brands were the first to use digital twins, and the company is now expanding the tech to include TRESemmé, Dove, Vaseline and Clear.

Unilever said it is seeing 55% in savings and a 65% faster turnaround in content creation. These images also elicit higher engagement with customers, holding their attention three times longer than traditional images, and doubling their click-through rates.

In another use of AI, Unilever can gather insights across its global operations to do forecasting and inform channel strategy.

For example, advanced modeling powered by AI can help sales representatives predict what a retailer is likely to buy. As such, sales teams can now personalize their engagement strategies, customize their loyalty programs and plan more targeted promotions.

Using AI and image processing, photos of in-store displays become a key data source for sales teams. They can get insights into stock levels to better advise retailers on product placement and merchandising.

Other CPG firms are following suit. In June, Nestlé also launched digital twins of its products for marketing purposes. These 3D virtual replicas let creative teams revise product packaging, change backgrounds and make other changes to adapt to local markets.

“This means that new creative content can be generated using AI, without having to constantly reshoot from scratch,” according to a company blog post.

As such, Nestlé can respond quicker in a fast-moving digital environment where ad campaigns on social media often require six or more different ad formats to be successful and product packaging changes constantly.

The company worked with Accenture, Nvidia and Microsoft on the initiative.

This month, Nestlé said its R&D team is working with IBM to invent a new generative AI tool that can find new types of packaging materials. Nestlé said it is moving away from the use of virgin plastic toward alternative materials such as recyclable and paper-based packaging.

Nestlé wants to find packaging materials that not only protect its content but also are cost-effective and recyclable.

The Coca-Cola Company is also actively using AI. In May, the company announced a partnership with Adobe to embed AI in design at scale. Project Fizzion, a design intelligence system, learns from designers and encodes their creative intent to automatically apply brand rules across formats, platforms and markets.

This encoded intent, StyleID, acts as a real-time guide to Coca-Cola teams and creative partners to generate hundreds of localized ad campaign versions for faster execution.

However, Coca-Cola has had an early misstep in using AI. Last year, consumers criticized its AI-generated Christmas promotion video as “soulless” and “devoid of any actual creativity,” according to NBC News.

For all PYMNTS AI coverage, subscribe to the daily AI Newsletter.

Read more: