WithSecure Built Luminen, an AI Cybersecurity Assistant, on Amazon Bedrock
Cybersecurity company WithSecure built Luminen, a generative AI assistant on Amazon Bedrock, to help organizations detect and respond to security events faster, minimizing damage and reducing downtime. WithSecure provides cybersecurity solutions for mid-market companies, prioritizing privacy, data sovereignty, and regulatory compliance in the European Union. Luminen integrates with WithSecure Elements and includes a Security Awareness Assistant that analyzes complex data tables to provide a 7-day security status overview, and an Investigation Assistant that analyzes technical data on identified security issues to build a narrative. Development began in December 2023, a public beta released in May 2024, and Luminen launched in September 2024. WithSecure also uses Amazon Neptune to build knowledge graphs storing relationships between security events.
Overview
Cybersecurity company WithSecure built Luminen, a generative AI assistant on Amazon Bedrock, to help organizations detect and respond to security events faster, minimizing damage and reducing downtime. WithSecure provides cybersecurity solutions for mid-market companies, prioritizing privacy, data sovereignty, and regulatory compliance in the European Union. Luminen integrates with WithSecure Elements and includes a Security Awareness Assistant that analyzes complex data tables to provide a 7-day security status overview, and an Investigation Assistant that analyzes technical data on identified security issues to build a narrative. Development began in December 2023, a public beta released in May 2024, and Luminen launched in September 2024. WithSecure also uses Amazon Neptune to build knowledge graphs storing relationships between security events.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
WithSecure wanted to make it simpler for customers to understand their organizational security status and make informed decisions faster. Its flagship product, WithSecure Elements, provided extensive security data in structured, tabular views, and the need to convert that data into a narrative, in customers' local languages, led WithSecure to explore generative AI, while keeping data privacy and data sovereignty at the forefront given its European lineage.
The solution
WithSecure built Luminen, a generative AI assistant integrated with WithSecure Elements, using Amazon Bedrock to choose among and switch between foundation models without the complexity of self-hosting. Development began in December 2023 with an internal hackathon, a public beta released in May 2024, and Luminen launched in September 2024. Luminen comprises a Security Awareness Assistant that analyzes complex data tables to produce a 7-day security status overview, and an Investigation Assistant that analyzes technical data on identified security issues to build a narrative. WithSecure uses a second, stronger large language model in the background to validate Luminen's output quality and minimize hallucinations, and uses Amazon Neptune to build knowledge graphs storing relationships between security events.
Reported business value
Customers use Luminen's analysis to remediate security issues on their own, reducing the need to involve the Elements team, and WithSecure reports customers say they can understand and react to security events much more quickly. Luminen can localize its output in 10 languages.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other cybersecurity entries in the register.
Abnormal Security detects email attacks with behavioral AI on Databricks
Abnormal Security migrated from a legacy Hadoop system to the Databricks Data + AI Platform on AWS, using Delta Lake and Databricks SQL to stream threat signals from Kinesis Firehose and power behavioral AI models analyzing over 50,000 signals to detect email attacks, achieving a 20% reduction in successful email attacks, a 40% reduction in infrastructure costs, and a 30%+ increase in productivity.
Vega's cyber defense platform returns 67% of analysts' time with Claude
Vega, an agentic cyber defense platform used by Fortune 200 companies, global banks and healthcare providers, built an agentic detection-triage-investigation-optimization loop that runs Claude directly on security data where it lives, avoiding costly SIEM ingestion, delivered via Amazon Bedrock including an EU-resident deployment in Frankfurt for GDPR compliance. Across production deployments, customers reclaim roughly 67% of analyst time, complete investigations up to 44 times faster at 82% lower cost than legacy SIEMs, and one Fortune 500 insurer cut mean time to triage from 25 minutes to under 3 minutes.
CyberArk combines Apache Iceberg and Amazon Bedrock AI agents to cut support case resolution time up to 95%
CyberArk redesigned its technical support pipeline using AWS Fargate, PyIceberg and Amazon Bedrock (Claude 3.7 Sonnet) to auto-generate grok patterns for parsing diverse vendor log formats into Iceberg tables, and built autonomous AI agents that query Athena and CyberArk's knowledge base to perform root-cause analysis from natural-language questions. The system cut case resolution time by up to 95% (complex cases from up to 15 days to 2-4 hours), let engineers handle up to 4x more cases per day (from 2-3 to 8-12), and made logs queryable within minutes instead of hours or days.
Cyera scales agentic AI across 1,500 employees with Claude Enterprise
Cyera, an AI data security platform, rolled out Claude Cowork company-wide to all 1,500 employees in 17 days, connecting it to 40 tools including Slack, Salesforce, Asana, Google Drive and Notion, plus a governed Snowflake semantic layer of 40 documented tables built by its data engineering team. Weekly active usage of Claude reached 88% across the company. A scheduled task now triages Cyera's internal Ask Claude Slack channel, cutting daily triage from five-to-six hours to about 30 minutes, and the legal team launched a Cowork plugin with 20 playbooks that pre-reviews inbound vendor NDAs against Cyera's negotiating positions.
CyeraClaude Enterprise · Claude Cowork · Claude CodeWas this helpful?
Your feedback helps us improve our use case database