Klaviyo has launched two AI agents designed to work from the same real-time customer profile, as the company looks to help consumer brands connect marketing, service and revenue activity inside a single CRM platform.
Composer, the CRM vendor’s AI marketing agent, is moving into public beta, alongside expanded capabilities for Customer Agent, its AI-powered service platform.
Klaviyo said the two agents share intelligence across marketing and customer service. The aim is to address a common problem in customer engagement, in that marketing and service teams often operate from different systems with different data, creating fragmented customer experiences and leading to missed revenue opportunities.
“Businesses aren’t struggling because they lack AI tools—they’re struggling because most AI can’t act on the context that matters,” said Jamie Domenici, Klaviyo’s Chief Marketing Officer. “The next era of consumer experiences will be defined by companies that can combine AI with deep customer understanding to move faster, personalize better, and turn customer insights into growth.”
The launch reflects a shift in CX and RevTech as AI agents are increasingly being positioned as systems that need access to shared customer context to operate effectively, rather than as standalone tools.
Klaviyo’s pitch is that Composer and Customer Agent can strengthen each other because they work from the same real-time customer profile. When Customer Agent resolves a service interaction, it can write preferences, product interests and intent signals back to the customer record. Composer can then use those signals to build more targeted campaigns. Similarly, when Composer launches a campaign, engagement data can inform how Customer Agent personalizes future service interactions.
This shared-context model addresses the handoffs between teams and tools that can cause customer frustration if they fail to work together closely.
Paul Adams, Chief Product Officer at Fin, formerly Intercom, made a similar point in a recent CX Today interview, warning that customers do not think in terms of internal departments.
“For a customer, it’s a company, it’s a brand, it’s a product, and they don’t care about your internal issues or whether one department talks to the other.”
Adams added that fragmented AI agents can recreate the same disconnected experiences that have long frustrated customers.
“If you have multiple agents—one for sales, one for service, one for success—especially if these agents come from different companies… They don’t share the same context. They have different customer history, different memory. And it’ll end up being a big mess.”
Klaviyo is attempting to avoid that problem by anchoring both agents in the same customer record.
Composer Moves Into Public Beta
Composer is designed to help marketing teams identify revenue opportunities, build campaigns, and execute work more quickly.
According to Klaviyo, users can ask Composer where to focus, and the agent will audit live campaigns, flows and segments to identify ranked revenue opportunities. These might include an underperforming abandoned cart flow, a welcome journey where customers drop off before first purchase or a lapsed segment of high-value buyers.
Once an opportunity is selected, Composer recommends actions and builds the campaign across email and SMS, including audience, content and channel execution. Klaviyo said the agent draws on 14 years of customer context and patterns from nearly 200,000 brands, as well as each brand’s own performance data.
The company emphasized that campaigns are prepared for review and launch, but do not go live without approval.
Customer Agent Expands AI Service Capabilities
Klaviyo is also advancing Customer Agent, which is designed to use the same customer data that powers Composer.
Many AI service tools lack visibility into what a customer bought, what is in their cart or which marketing messages they have received. Klaviyo argues that Customer Agent can provide more relevant support because it is informed by the full customer profile, including purchase history, marketing engagement, preferences and intent signals.
That idea aligns with a recurring theme across CX technology discussions—AI service tools become more useful when they are connected to customer data and backend systems, rather than operating as isolated chatbots.
Dani Wanderer, Chief Marketing Officer at Ada, described this distinction in a CX Today interview.
“Leaders invest in system integration. They give their AI agents both read and write access to the backend systems. So whether it’s CRM or order management, billing systems, that’s what enables the AI to do things for consumers, not just answer questions.”
Klaviyo said that Customer Agent can now be configured to create new service experiences with a prompt. For example, a retail brand could describe a product-finding quiz and have Klaviyo AI generate the questions, logic, and product recommendations.
The agent is also designed to take action through connectors and APIs. Klaviyo said Customer Agent can complete returns, apply loyalty points, and operate across web chat, email, SMS, WhatsApp and custom surfaces.
Customer Context Becomes a Revenue Issue
The announcement comes as vendors across CRM, customer service and marketing automation increasingly frame customer context as central to AI performance.
Rather than treating service interactions as separate from marketing and revenue, Klaviyo is positioning support conversations as a source of commercial intelligence. A resolved service interaction may reveal product interest, dissatisfaction, purchase intent, or churn risk — signals that can inform future campaigns and customer journeys.
The launch also highlights how AI agents are moving beyond simple productivity use cases. Composer is intended to identify revenue opportunities, recommend actions and build campaigns as well as generate marketing content, while Customer Agent can resolve service interactions and write new signals back to the customer profile in addition to answering questions.
That creates a feedback loop between customer service and revenue activity, so that a service issue can influence future marketing and a campaign interaction can shape future support. Over time, the agents become more effective because each interaction enriches the data available to the other, Klaviyo said.
The approach is especially relevant for consumer brands, where repeat purchases, loyalty, product discovery, returns, and post-purchase support are closely linked.
Composer public beta is available now. Customer Agent is available as a full AI-powered service platform, with additional functionality scheduled to roll out throughout 2026.
