How ShipStation Global built an AI IT help desk on Amazon Bedrock AgentCore
ShipStation Global's engineering team built Deckhand, an AI IT help desk agent for Slack on Amazon Bedrock AgentCore. It answers routine IT questions from a curated knowledge base, reads error-message screenshots, and files Jira tickets. In its first three months it resolved 97.5% of channel queries with a 96% positive feedback rating.
This post details how ShipStation Global's Engineering team developed Deckhand, an AI-powered IT help desk application for Slack, using Amazon Bedrock AgentCore. ShipStation Global is a leading intelligent shipping and logistics platform for small and mid-sized companies. Deckhand aims to improve efficiency by quickly answering routine IT and company questions using a curated knowledge base.
When Deckhand cannot find an answer, it converts the conversation into a fully contextualized ticket in Jira Service Management, reducing the need for employees to file tickets manually. The post explains the architecture of Deckhand, consisting of four main components: Slack service, Agent service, tools and knowledge, and operations and feedback.
When an employee posts a question in a channel where Deckhand is present, the Slack service assembles the conversation history and user context, then sends the request to the AgentCore runtime API. The agent searches the knowledge base and calls tools as needed. If it finds an answer, it provides a self-service solution; otherwise, it asks for clarification or creates a ticket.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
Also reported by 1 other outlet
- Build long-horizon agents with Grok 4.7 on Amazon Bedrock aws.amazon.com
