Aerospace & DefenseManufacturingSoftware Engineering

Blue Origin Builds AI Agent Platform for Lunar Hardware Design

BOBlue Origin

Blue Origin deployed 2,700+ AI agents with 70% company-wide adoption, achieving a 90% reduction in hardware development time using Amazon Bedrock.

Outcomes

2,700+AI agents deployed
70%Company-wide adoption
3.5 millionMonthly interactions
90%Hardware dev time reduction
6x fasterAnalysis workflow acceleration
10x improvementAI app development speed

Tools & Technologies

1AO
Amazon OpenSearch
Managed search and analytics engine for log analytics, application monitoring, and RAG knowledge bases.
2AL
AWS Lambda
Serverless compute service that runs code in response to events.
3SA
Strands Agents SDK
AWS SDK for building model-driven AI agent orchestration systems.
4AE
Amazon EC2
Scalable cloud computing instances including GPU-accelerated P5 and G5 for AI workloads.
5AE
Amazon EKS
Managed Kubernetes service for running containerized applications
6AB
Amazon Bedrock
Fully managed service for accessing foundation models from leading AI companies via AWS.

AI Categories

Search & Vector Database
Cloud Infrastructure
Developer Tools
ML Platform
Large Language Models

Challenge

Specialized aerospace knowledge was siloed in expert minds, and traditional development cycles took years. Base LLMs lacked training in industrial manufacturing and specialized domains.

Solution

Built BlueGPT, a secure LLM gateway and multi-agent orchestration platform using Amazon Bedrock, Strands Agents SDK, EKS, OpenSearch, and GPU-accelerated EC2 instances.

Full Story

Blue Origin, the aerospace company founded by Jeff Bezos, needed to accelerate lunar hardware development while overcoming siloed specialist knowledge and traditional development cycles that took years. Standard LLMs lacked training in industrial manufacturing, thermal battery design, and regolith extraction.

Access 454+ AI use cases, 426+ tools, and adoption signal rankings.

Source

AWS
January 2025
Original case study ↗

Similar Cases

1P
How Petrobras Uses Generative AI to Uncover $120M in Tax Savings
Petrobras
$120MTax savings identified
2J
How JAKALA Cuts Campaign Cycles from 7 Days to 24 Hours with Claude Agents
JAKALA
Under 24 hours, down from 5–7 working daysCampaign optimization cycle
3T
How Tabnine Uses Claude to Improve Conversions 20% and Reduce Churn 30%
Tabnine
50%Improvement in response times
4LM
How Lockheed Martin Uses IBM watsonx to Unify 46 Data Systems into One AI Platform
Lockheed Martin
50%Reduction in data and AI tools
5O
How O3sigma Builds AI Factory Optimization Models to Generate $100K+ in New Revenue
O3sigma
2 weeksModel fine-tuning time to global top-3 ranking
6C
How CACI's DarkBlue Uses Elasticsearch and Claude to Accelerate Dark Web Criminal Investigations
CACI
Seconds per query regardless of data age or volumeCriminal investigation acceleration
7F
How FURUNO Uses Elastic to Cut Vessel Incident Resolution Time by 94%
FURUNO
94%Mean time to knowledge reduction
8WV
How West Valley Construction Cut Safety Events 97% with Samsara AI Dash Cams
West Valley Construction
97%Safety events reduction
9O
How Omnicom Uses AWS to Cut Infrastructure Costs 90% and Build an AI-Powered Marketing Platform
Omnicom
90%Reduction in compute infrastructure costs
10H
How Hexion Uses Celonis Process Intelligence to Reduce Supply Chain Disruption and Improve Working Capital
Hexion
50%Reduction in supplier financing days to pay
See all use cases →