# ShipStation Global resolves 97.5% of IT queries with Bedrock agent

Digest AI · Enterprise & Industry · published 2026-10-13T15:54:49Z

Canonical: https://digestai.news/story/shipstation-global-resolves-97-5-of-it-queries-with-bedrock-agent

## Summary

ShipStation Global built Deckhand, an AI-powered IT help desk agent for Slack, using Amazon Bedrock AgentCore and Anthropic's Claude. The tool addresses the burden of repetitive IT support by answering routine questions from a curated knowledge base, reading error screenshots, and creating Jira tickets. It launched in April 2026 and has handled 1,935 messages in its first three months, resolving 97.5% of incoming channel queries. Employees gave the agent a 96% positive feedback rating by June, up from 82% in April after prompt and knowledge base refinements.

The architecture uses a Strands agent on AgentCore runtime, with tools exposed via Model Context Protocol (MCP) through AgentCore Gateway. A key feature is the mining of historical Slack threads using DSPy’s Recursive Language Model to extract verified fixes, creating a high-quality knowledge base. The agent is designed to stay silent on social messages or when humans are already assisting, ensuring it does not disrupt natural conversations. It also handles after-hours queries, answering 94% of those that arrive outside US business hours.

This case study highlights how companies can use AWS infrastructure to automate internal support. By integrating with existing tools like Slack, Confluence, and Jira, ShipStation Global reduced operational friction. The system uses strict validation and access controls to ensure security, such as requiring explicit confirmation for ticket creation and restricting image analysis to Slack-hosted files. The result is a self-service option that frees IT staff from repetitive tasks while improving employee experience.

## Key points

- Deckhand resolves 97.5% of IT queries with a 96% positive feedback rating.
- Built on Amazon Bedrock AgentCore using Anthropic's Claude and Strands Agents SDK.
- Mines historical Slack threads using DSPy Recursive Language Models for knowledge base.

## Why it matters

Demonstrates a practical, secure pattern for deploying AI agents in enterprise Slack channels to automate IT support, reduce ticket volume, and improve employee satisfaction using AWS Bedrock AgentCore.

## Sources

1. [How ShipStation Global built an AI IT help desk on Amazon Bedrock AgentCore](https://aws.amazon.com/blogs/machine-learning/how-shipstation-global-built-an-ai-it-help-desk-on-amazon-bedrock-agentcore) (AWS Machine Learning Blog, 2026-10-13, primary source)

Part of the developing story: [Amazon Bedrock Becomes Enterprise AI Operating System](https://digestai.news/thread/amazon-expands-seller-assistant-from-chatbot-to-operating-system-for-merchants) (10 stories)

## Cite

Digest AI, "ShipStation Global resolves 97.5% of IT queries with Bedrock agent", 13 October 2026, https://digestai.news/story/shipstation-global-resolves-97-5-of-it-queries-with-bedrock-agent

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/shipstation-global-resolves-97-5-of-it-queries-with-bedrock-agent.json