Skip to content
context AI agents

Reactiv deployed a three-agent system on Amazon Bedrock AgentCore to automate mobile apps for Shopify merchants

only one source so far

According to its own figures, Reactiv reduced mobile app configuration time for Shopify merchants by 80 % using a three-agent system on Amazon Bedrock AgentCore that updates apps autonomously according to a schedule specified in natural language.

Reactiv, which operates a mobile commerce platform for Shopify merchants, deployed a system called AI Scheduler to autonomously update mobile apps according to a predefined schedule. A merchant enters a request in natural language, such as regularly refreshing the home page with best-selling products, and the system carries out the update on its own without further human intervention.

The system is built as a three-agent architecture on the Amazon Bedrock AgentCore platform using the Strands Agents SDK. According to Reactiv, the deployment reduced the time needed for configuration by 80 % and accelerated the path to production by 33 %; the agents were deployed in production within a few weeks. The company used specific AgentCore components – a runtime for running agents in isolated microVMs, persistent memory across sessions, and the Identity module for authentication between services. According to the description, the memory is divided into three layers: summaries of previous tasks, tracking merchant preferences for proposed layouts, and extracting facts about the store, such as product categories, best-selling items or brand guidelines, with data from individual merchants isolated from one another.

The architecture also uses Amazon EventBridge for scheduling through cron rules, AWS Lambda as a task trigger with 17 tool functions, Amazon DynamoDB for storing results for merchant approval, and Amazon Redshift for analytical queries through text-to-SQL. The company says it unified interactive and scheduled update modes on a single platform with shared memory. Details can be found in the source article.

What changed

Why it matters

According to the company, for Shopify merchants running mobile apps, this means less manual content management and a faster response to promotions. For development teams, it provides a concrete example of deploying the Amazon Bedrock AgentCore platform for production multiagent systems with persistent memory and isolation between individual customers, which may serve as a reference architecture when designing similar solutions.

Relevant practical impact

What this means

01

For a business

According to Reactiv, deploying a three-agent system on Amazon Bedrock AgentCore reduced mobile app configuration time by 80 % and accelerated deployment to production by 33 %, indicating potential time and cost savings when automating repetitive processes using AI agents with persistent memory and tenant isolation.

Development
What to decide Evaluate Amazon Bedrock AgentCore as a possible platform for custom multiagent systems requiring persistent memory and isolation between individual customers.
More business impacts →
Amazon Bedrock AgentCore Automatizace mobilní e-commerce Reactiv Shopify Strands Agents SDK

Check the original

Event sources

only one source so far · 1 publisher, 0 independent. We count feeds from the same owner only once.

1
AWS Machine Learning Blog primary source · first detected How Reactiv automates mobile commerce 80% faster with Amazon Bedrock AgentCore