ShipStation's Deckhand AI IT help desk on Bedrock AgentCore resolved 97.5% of queries
ShipStation Global's engineering team built Deckhand, an AI IT help desk agent that lives in Slack and runs on Amazon Bedrock AgentCore, answering routine IT and company questions, reading error-message screenshots, and creating or updating Jira Service Management tickets. The agent uses the Strands Agents SDK with Anthropic's Claude on Amazon Bedrock, exposes classification, ticketing, user resolution and image analysis as MCP tools through AgentCore Gateway, and draws on a Bedrock knowledge base indexing Confluence articles, intranet pages and Slack history. According to the co-written AWS/ShipStation post, it resolved 97.5% of incoming channel queries with a 96% positive feedback rating over three months; a DSPy recursive language model (RLM) pipeline mines resolved Slack threads into verified self-service steps, and the bot is designed to stay silent during human-to-human or social chatter.
It illustrates one enterprise pattern for embedding agents in existing workflows and mining historical chat as a knowledge base, though the results are vendor-reported.
This post is co-written with Kenneth Salmon, Edward Boswell, Jack Armstrong, Robert Banh, and Nick Ciubotariu from ShipStation Global.
Answering the same IT questions and clearing routine tickets drains time that IT teams could spend elsewhere. To reclaim it, the ShipStation Global Engineering team built Deckhand, an AI-powered IT help desk agent for Slack, on Amazon Bedrock AgentCore.
ShipStation Global is the leading intelligent shipping and logistics platform for small and mid-sized shippers, and it operates on a simple belief: the more efficient its teams are, the better it delivers for customers. Deckhand puts that belief to work. It answers routine IT and company questions from a curated knowledge base, reads error-message screenshots, and creates and updates Jira Service Management tickets.
In this post, we discuss how ShipStation architected Deckhand, which resulted in resolving 97.5 percent of incoming channel queries while earning a 96 percent positive feedback rating by employees (Figure 1).
Figure 1: 3-month channel coverage and positive feedback
Business challenge
The problem Deckhand solves is the one every IT team will recognize: the same questions are routinely asked, error messages are posted after business hours, and information needs to be gathered from different teams. At ShipStation Global, those conversations lived in a busy help desk Slack channel, where employees asked, and IT answered, one thread at a time. The answers usually already existed in a Confluence how-to article, on a company intranet page, or in a thread from eight months earlier. Finding them was the hard part.
#Deckhand#ShipStation Global#Amazon Bedrock AgentCore#Strands Agents SDK#Anthropic Claude#Slack#Jira Service Management#DSPy#Amazon Bedrock#AWS Lambda#Amazon DynamoDB#Confluence