● Covered by 1 source · 1 reportLow impact1 neutral
AWS details KnowledgeForge, a solution for ITSM knowledge base management using generative AI
Key points
- KnowledgeForge extracts information from resolved ITSM tickets.
- It uses Amazon Bedrock for content generation and improvement.
- Amazon S3 Vectors are used for duplicate detection in knowledge bases.
- AWS Step Functions orchestrates the entire process.
Addressing ITSM Knowledge Gaps
KnowledgeForge is designed to address common issues in IT Service Management (ITSM) knowledge bases. Many resolved incident tickets contain valuable information about symptoms, root causes, and fixes that often remain locked within ticket histories, making it inaccessible for future reference. Conversely, existing knowledge bases can become disorganized with duplicate or outdated articles, reducing their effectiveness.
Automated Knowledge Extraction and Curation
The solution works by mining resolved incident tickets to generate new knowledge base articles. Simultaneously, it curates existing knowledge bases by categorizing articles, identifying and removing duplicates, assessing content quality, and rewriting weaker content. A knowledge manager reviews and approves the generated and improved content before it goes live, ensuring human oversight.
AWS Building Blocks
KnowledgeForge is built using several AWS services. Amazon Bedrock is utilized for generating new content and improving existing articles. Amazon S3 Vectors, a capability of Amazon S3, handles the detection of duplicate articles. AWS Step Functions orchestrates the workflow of the entire document-processing pipeline. The solution also leverages AWS Lambda, Amazon ECS on AWS Fargate, Amazon DynamoDB, Amazon SQS, Amazon Bedrock guardrails, and AWS KMS.
Implementation Requirements
To deploy and use KnowledgeForge, users need an AWS account with access to Amazon Bedrock, specifically enabled for Anthropic Claude Sonnet 4.5 and Amazon Titan Text Embeddings V2 models. Required permissions include creating various AWS resources such as S3 buckets, S3 Vectors indexes, Step Functions state machines, Lambda functions, ECS services, DynamoDB tables, SQS queues, Bedrock guardrails, and KMS keys. Familiarity with the AWS Cloud Development Kit (CDK), Amazon Bedrock, AWS Step Functions, Amazon ECS, and vector embeddings is also necessary. The solution's code is available in the aws-samples/sample-knowledgeforge repository.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Primary sources
GitHub aws-samples/sample-knowledgeforgeReporting from
AWS released details on KnowledgeForge, a solution that uses generative AI to extract knowledge from resolved IT Service Management (ITSM) tickets and improve existing knowledge base articles. This solution helps organizations automate the creation of new knowledge base content and maintain the quality of their existing documentation.