Mercado Libre (MELI) isn’t just Latin America’s largest ecommerce and financial platform—it’s becoming one of the most operationally complex digital businesses in the world.

With operations spanning 18 countries from Mexico to the Patagonia region, MELI processes trillions of behavioral events. But for MELI’s leadership, raw data volume was never the goal. They wanted something more transformative: making every employee, in every function, capable of acting on customer intelligence without becoming an analytics expert.

This is the story of how MELI uses Amplitude’s AI capabilities—agents, dashboards, and Model Context Protocol (MCP)—to shorten the time from sensing to deciding to acting.

The challenge: Analytics at continental scale

Running analytics for a company of MELI’s size presents challenges that most organizations never encounter. The geography alone includes delivery operations spanning a continent, from bustling urban centers to remote rural communities. Each region has its own logistics partners, regulatory requirements, and customer expectations.

This presented a new opportunity for MELI: shifting from generating insights to operationalizing them. As analytical demand increased, cross-functional coordination became more complex, and teams needed faster ways to move from discovery to action without adding friction.

In 2025, MELI scaled Amplitude to more than 10,000 employees, enabling them to answer their own questions without waiting in an analyst queue. MELI, powered by shared, governed data, uses Amplitude to scale its analytics across Finance, Marketing, Logistics, and everything in between.

But MELI didn’t stop at self-serve data. It unlocked new efficiencies by delegating analysis to AI Agents, which generated more valuable information than a human-only workflow could have produced. This has sharpened its execution capabilities and geographical challenges. With AI Agents, teams continually tune coverage and experience without adding more manual work.

The solution: A three-layered AI transformation strategy

MELI’s AI-native approach rests on three integrated layers, each building on the others.

The base layer is Amplitude’s behavioral analytics platform, including Amplitude Analytics. This gives teams a shared, trusted view of the full customer journey, from the first click to purchase to delivery.

The second layer uses Amplitude AI Agents to transform passive dashboards into active participants by:

• Monitoring funnels
• Identifying anomalies
• Summarizing findings
• Distributing insights to stakeholders

All without requiring human initiation.

The final layer is distribution, powered by Amplitude’s MCP server. With MCP, MELI’s employees access behavioral context through the AI tools they already use: Claude, Cursor, or their internally developed AI chatbot.

This AI-native approach means analytics isn’t just something employees do—it’s something that scales alongside their business. The dashboard remains the canonical source of truth, but AI Agents and MCP connections ensure that truth flows to wherever decisions are made.

To date, 70 MELI users have created 126 agents, with 71% completing value operations, such as sharing insights or triggering follow-up analyses. Agent-generated emails see a 52% open rate, suggesting that the insights are reaching people who actually use them.

Proof point: The Flex Shipments use case

Abstract transformation stories are easy to tell, but achieving concrete results is harder. MELI’s Flex Shipments demonstrates what AI-native analytics looks like in practice.

Flex is MELI’s flexible delivery program, enabling sellers to choose couriers that can reliably meet delivery service-level agreements (SLAs). The challenge was straightforward: When sellers unsuccessfully searched for an available courier, friction occurred. Those failed searches led to slower deliveries, frustrated sellers, and eventually churn.

Before Amplitude, identifying these coverage gaps required manual analysis and considerable time to pinpoint issues. Prioritizing and coordinating across region, product, business, and transport teams meant translating findings into multiple formats for different audiences.

MELI created an Amplitude dashboard that made demand visible at a granular geographic level. AI Agents would then operationalize that dashboard into automated, shared reporting.

The dashboard itself was the first breakthrough. By visualizing where sellers unsuccessfully searched for couriers (broken down by province and city), the team could quantify unmet demand and prioritize the highest-impact zones. Disparate teams could then use the same dashboard as a shared source of truth, eliminating the translation layer that had previously slowed efforts.

But the real transformation came from pairing dashboards with AI Agents. Agent-generated reports provided proactive, automated visibility into feature performance. Teams no longer had to request ad hoc analysis to spot regressions or new pockets of opportunity. This created a closed-loop optimization cycle: identify unmet demand, onboard couriers with stronger SLA performance in priority zones, monitor the impact, and continually refine the process.

The results?

• Dropoff reduction: Searches with no available courier decreased approximately 10% after targeting key areas of unmet demand.
• Feature adoption: 60% of Flex sellers in Brazil now complete shipments through the feature.
• SLA improvement: The SLA rate was improved by 2.5% as a result of using Flex.

This wasn’t just a one-time project. With dashboards and AI Agents working together, teams continually tune coverage and courier onboarding as demand shifts. The operating model changed from reactive discovery to continuous optimization.

The AI-native future with Amplitude

MELI’s transformation didn’t happen in isolation. Amplitude’s partnership with Minders, a martech agency specializing in analytics enablement, provided the operational arm for this rollout. Through executive business reviews, enablement sessions, and pilot programs, the Minders integration translates business priorities into concrete Amplitude workstreams.

This partner model proves essential for change management at scale. When training hundreds of people simultaneously on new ways of working, you need more than software—you need people who can bridge the gap between capability and adoption.

Looking ahead, MELI’s AI-native trajectory continues to evolve. The goal is “AI in the workflow, grounded in governed behavioral truth.” For MELI, being AI-native isn’t about novelty; it’s about being a part of the future. It’s about industrializing the time from insight to action until analytics becomes invisible—not because it doesn’t matter, but because it’s woven into how everyone works.