KnowledgeForge: mining gold from the ITSM ticket graveyard
AWS shows how to turn your ITSM ticket backlog into a self-curating knowledge base — no human librarian required.
Why it matters
A practical deployment pattern for turning unstructured operational data into searchable knowledge using LLMs and vector search. Useful for ops teams and knowledge-management practitioners looking to automate content creation and curation at scale.
The key facts
11 to knowUses Amazon Bedrock (managed LLM service) for mining and curation
Implements vector search with Amazon S3 Vectors for deduplication and quality scoring
Multi-tenant closed-loop pipeline architecture
Converts resolved incident tickets into knowledge base articles automatically
Focuses on ITSM (IT Service Management) use case — operational/support domain
Uses Amazon Bedrock for LLM inference
Amazon S3 Vectors for semantic search/deduplication
AWS Step Functions for multi-tenant pipeline orchestration
Solves duplicate knowledge-base articles through automated curation
Closed-loop system: resolved tickets → knowledge articles → quality scoring
Published as AWS reference architecture (blog post, not a product GA)
Go to the source
AWS Machine Learning Blogaws.amazon.com
Publisher excerpt: KnowledgeForge mines resolved ITSM incident tickets into new knowledge base articles and automatically curates the existing library by deduplicating, quality-scoring, and improving content, using Amazon Bedrock, Amazon S3 Vectors, and AWS Step Functions in a multi-tenant, closed-loop pipeline.