Build multi-agent teams that remember every customer with Amazon Bedrock AgentCore

Описание и применение

Создайте команду мультиагентов, которые запоминают каждого клиента, используя Amazon Bedrock AgentCore и n8n. Один хранилище памяти обслуживает четыре специалиста, каждый из которых обрабатывает разные типы запросов, сохраняя контекст беседы.

Задача

Customers need a support bot that can handle multiple types of queries (configuration, calculation, architecture, general) while preserving conversation context across agents without building separate vector stores or deploying multiple agents.

Результат

The workflow demonstrates how to build a multi-agent support team with shared memory, reducing duplication and operational cost. It handles different query types, preserves context across agents, and returns answers in Slack with specialist tags.

Рабочий процесс

• Connect AWS and Slack credentials in n8n
• Set Customer Context node to create Actor ID and Session ID
• Triage Agent classifies incoming question and returns category JSON
• Read Triage Decision parses the category
• Route To Specialist sends question to the matching specialist agent
• Each specialist agent runs with tools granted per call (Code Interpreter, AWS skills catalog, shell)
• Format Reply unwraps the answer
• Post Answer To Slack posts the answer tagged with the specialist

Доказательства

AgentCore’s Managed memory is scoped by actor and session, so an Actor ID that identifies the customer rather than any single agent gives every specialist the same history to read and write

Источник

The workflow creates one harness for all four agents rather than one each

Источник