



Think of the most labour intensive, time-consuming parts of your job. Now imagine that you had a trustworthy, capable assistant who could do the grunt work for you — quickly and accurately. That’s what autonomous AI agents can do. For commerce teams, this means merchandisers won’t need to spend hours sifting through data to uncover trends and insights to build relevant offers and product bundles. Service agents won’t be buried under endless queries about order status or delivery timeframes. Instead, AI agents can take the wheel to move business forward at scale, so your teams can focus on more strategic, high value work. Here’s how commerce teams can use AI agents to increase sales, productivity and revenue.
First things first: What is Agentforce — and how is it different from traditional ecommerce AI?
You can think of Agentforce as a limitless extension of your workforce — available 24/7 and capable of massive scale. With Agentforce, your teams can quickly set up autonomous AI agents and work side-by-side with them to complete all kinds of tasks, from the mundane to the most complex. Using fillable forms and natural language, it’s simple for any business user to build an agent, assign them specific actions and give them the right context to perform the job. Some agent actions come out-of-the box and you can also build customised agents to fit your own unique business needs. Let’s take a look at the set up process and explore a few examples of how agents can help increase revenue, productivity and customer satisfaction.
Today, we’re already used to “predictive AI”-which analyses data to provide recommendations, forecasts and insights-and “generative AI,” which learns from data and uses patterns to seamlessly generate text, images, music and code. Agents go far beyond this. They can perform tasks independently, make decisions and even negotiate with other agents on our behalf. AI agents are easy to build and deploy, unlocking massive capacity.
Marc BenioffCEO, Salesforce
How easy is it to set up AI agents?
Setting up an AI agent with Agentforce is designed to be user-friendly and straightforward, even for users without extensive technical expertise. All you need to do is simply describe the project and any desired outcomes — no technical knowledge required! The process includes simple form fields and plain language instructions to ensure streamlined use. Here’s a look a t the steps involved.

1. Select or create an agent:
You can either choose a prebuilt agent or create a customised one using Agent Builder. For routine commerce tasks (ranging from creating a product bundle to managing inventory), select a pre-built agent. If you have a more specific business need that isn’t covered by a prebuilt agent, you can create a customised agent. The first step is to decide which type of agent you will use.
2. Define agent roles and data:
Next, assign and name your agent with its specific function using simple form fields. If you’re creating a customised agent, enter agent instructions in plain language based on data from back-end business systems, like Data Cloud, your CRM, ecommerce platform and more. For example, if your sales cycle involves a series of approvals from different stakeholders, you can create actions to alert each team member when it’s their turn for review.
3. Set up guardrails:
Use plain language to give your agent rules to follow, ensuring compliance and secure use of customer data. For example, a merchandiser might add this guardrail to agent instructions: “Ensure product recommendations are always in line with inventory levels. Never, ever promote an item that’s out of stock or in limited supply. Don’t offer any promotion that goes below minimum margin levels.”
4. Add source materials:
Upload or select relevant data from your CRM, such as product documents, FAQs and industry one-sheeters.
5. Test, deploy and go live:
Verify all inputs and confirm that the agent outputs are accurate. (This is what we call having a “human in the loop.) Test the agent or activate it to go live.
How do AI agents improve ecommerce?
If you can describe it, Agentforce can do it. Since the possibilities are vast, it’s best to start with a specific goal in mind. Do you want to increase your add-to-basket rate for a particular product category? Are you hoping to reduce your return rates by creating more detailed and thorough product descriptions? These are just a few examples of how agents can improve ecommerce. From merchandising to product discovery to order management, agent actions span the entire customer journey. Below are some out-of-the-box agent actions that can help you to meet your goals.

Agent actions for merchandising
Merchandising teams play a large role in ecommerce success. They’re the heroes who create and maintain product listings, monitor inventory levels, categorise every item and more. AI agents can help scale and optimise this work. That’s because Agentforce can analyse vast amounts of data from different systems around your business (like your CRM, ecommerce platform and other back office technologies) to quickly identify trends and patterns that help merchandisers make informed decisions. Then, AI agents can work with merchandisers to take action based on all the insights. Here’s how it works.
- Create a Personalised Promotion: In the past, merchandisers spent days (or weeks!) compiling data and building customer segments to activate personalised promotions. Now? Merchandisers can set up an AI agent to do the work in seconds. If your ecommerce and marketing platforms are integrated, you can launch a promotion and campaign with just one agent.
- Recommend a Product: Agentforce can aggregate and analyse browsing behaviour and purchase history across all of your customers — at both the individual and store level. Since Agentforce is also integrated with other parts of your business beyond ecommerce, personalisation is centralised and hyper-intelligent. With harmonised data from around your organisation, AI agents can recommend the right products to the right customers at the right time. The result? Higher conversion rates and average order size.
- Analyse Product Performance: Merchandisers spend weeks parsing through sales data, conversion and click-through rates, stock turnover and customer reviews. This information provides valuable insight a bout product performance and helps merchandisers determine which products to promote, when to adjust pricing and how to create targeted marketing campaigns. With a prebuilt AI agent for product performance analysis, the process is simple — and complete in minutes.
- Generate Product Descriptions: A good product description is the result of collaboration between several departments, from merchandising to marketing to SEO. The goal is to ensure that every description is accurate, persuasive, SEO-friendly and aligned with your overall brand voice. Creating just one successful product description takes time. And for businesses with large catalogues that are continuously updated, the resources involved are considerable. With an AI agent, you can update every item in minutes — including accurate specifications, the right brand voice, SEO metadata and more. That’s because Agentforce integrates with all systems and organisations involved in the task at hand, helping you to break down silos and create meaningful outcomes, fast.
- Create SEO Metadata: Every item, category and product listing page needs the right SEO metadata to ensure that search engines serve your products when users enter relevant queries. And, of course, this takes time — especially if you have a large or complex product catalogue. But when your teams have Agentforce in the loop, they can create and update metadata faster than ever.
- Boost and Bury Rules: Successful ecommerce involves continuously adjusting the visibility and placement of your products. For every promotion, new arrival, seasonal event and fluctuation in availability, merchandisers are hard at work with boost and bury strategies to get the right items in front of the right customers’ eyes. By utulising and analysing data from around your business (in seconds!), Agentforce makes this faster, easier and more accurate than ever. And that means more conversions and higher revenue.
- Build Product Bundles: Pairing related items together and offering a discount for the bundle is a tried and tested merchandising strategy. Agentforce can not only help create bundles, it can advise on pricing, audience segmentation and more.
Agent actions for order management
Simplify B2B and B2C buying with conversational assistance that helps locate products, check order status and reorder items with ease. AI agents for order management can empower your service reps to see the full picture and make decisions accordingly and automate order servicing capabilities. AI agents can automatically update order information like payment or delivering details, handle uneven exchanges or quickly communicate order status with customers on the channel they prefer.
- Order Management: According to most estimates, a single "Where Is My Order?" (WISMO) request can cost a business around $12 to resolve, with the primary cost being the time spent by a customer service agent searching for order information and responding manually. With Agentforce? The process is hands-off, automated and proactive. Out-of-the-box agent actions can automatically handle order status enquiries, provide tracking information, estimate delivery times and give updates on delays or issues. That’s a win/win for your bottom line and your customer experience.
- Initiate a Return or Exchange: Over eight in ten (84%) online shoppers would turn their back on a brand after a bad returns experience.That’s why Agentforce helps you to facilitate convenient, hassle-free returns for your customers with out-of-the-box actions that manage customer requests for returns, exchanges and refunds and guides shoppers through related policies and processes. Agents can even handle more complex requests, like uneven exchanges.
- Modify an order: Sometimes customers need to make a change. For example, they may want to edit their delivery date or address, add an item to an order or cancel their order altogether. The easier you make these processes, the better your shopper experience will be. With Agentforce, customers don’t need to wait on hold — an AI agent can assist them automatically with these order modifications so your service agents can focus on more strategic tasks. For critical peace of mind, agents are bound by your company’s written policies, so they don’t just provide self service — they offer compliant self service.

Agent actions for guided shopping
AI agents don’t just work behind the scenes. They can also act as helpful AI shopping assistants for your customers, making the ecommerce experience more convenient and enjoyable. Agents are available 24/7 to recommend products, answer questions and enhance the shopping experience. Here’s how they can help.
- Conversational Insights: Your typical chatbot doesn’t have advanced capabilities to reason, react and observe. With AI agents, the customer service experience is enhanced with features like natural language instructions and thoughts/reasoning. Imagine you're a customer initiating a conversation with an AI agent to return a product. Instead of just following a fixed script, the agent can ask clarifying questions like, "Is the product damaged?" or "Have you got the receipt?" This loop of reasoning, acting and observing ensures shopper requests are handled efficiently and accurately.
- Image Search: Customer behaviours are changing fast when it comes to product search. The keyword era is over: Shoppers no longer want to type features into an ecommerce site search bar to find what they want. Instead, they want to upload a photo and have AI do the work. With image search, a user can upload a photo of Taylor Swift and ask AI to “find me a dress that looks like this.” With out-of-the-box generative capabilities, Agentforce helps you to bring this innovative experience to your customers. In a crowded ecommerce market, these are the kinds of experiences that help you to win, from the first sale to lifetime loyalty.
- Add a Product to Basket: Making a purchase just got easier (ch-ching!) Every click eliminated on the path to the Buy button is one step closer to turning a casual browser into a paying customer. Agentforce makes this easy and convenient — for you and your shoppers. AI agents can leverage language and data to reduce the complexity and time of checkout, helping you to offer bespoke, conversational shopping experiences for your shoppers.
Improve ecommerce outcomes with Agentforce
From personalised customer interactions to automated inventory management and data driven insights, Agentforce can help boost sales and increase operational efficiency at scale. Agents offer an unprecedented opportunity to make every team more productive and every shopper more likely to buy. Out-of-the-box tools make it easy to put AI agents to work quickly so you reap fast rewards and a return on your investment.