CirrusHQ: AI-Ready Data Lakehouse & Vector Store on AWS
CirrusHQ Ltd · Intelligence & Research
Certification per AWS Marketplace.
Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
"CirrusHQ builds the governed data foundation that AI, analytics and BI workloads depend on. Many UK organisations want to adopt generative AI or modern BI but their data is fragmented across line-of-business systems, legacy warehouses and on-premises databases, ungoverned, and not indexed for retrieval. This engagement fixes that first, so AI initiatives don't stall on data readiness.
The reference architecture lands raw data in a bronze/silver/gold Amazon S3 lakehouse, catalogued with AWS Glue Data Catalog and AWS Lake Formation for fine-grained, row- and column-level access control. Amazon Redshift Serverless and Amazon Athena serve as the query layer for analytics and BI, with Amazon QuickSight for embedded dashboards and natural-language queries. Amazon SageMaker Lakehouse provides a unified access layer so machine learning and analytics workloads read the same governed data without duplication, and Apache Iceberg tables on Amazon S3 give an open table format for interoperability. Amazon Kinesis Data Streams, Amazon Managed Streaming for Apache Kafka and Amazon Kinesis Data Firehose bring real-time telemetry, application logs and engagement data into the platform for operational intelligence.
Show the rest of the publisher’s description (6 more lines)
Where source systems sit on Oracle, Teradata, Netezza, SQL Server or Snowflake, CirrusHQ migrates and modernises onto Amazon Redshift Serverless and Amazon Aurora PostgreSQL using AWS Schema Conversion Tool and AWS Database Migration Service, ending expensive legacy licensing.
Critically for AI readiness, the engagement builds the vector store layer using Amazon OpenSearch Serverless, the same retrieval-augmented generation pattern CirrusHQ uses in its Amazon Bedrock generative AI builds, so the lakehouse doubles as the private knowledge base for RAG chatbots, copilots and agentic workflows. Amazon Bedrock Knowledge Bases can be layered on directly once the foundation is in place.
For customers with document-centric knowledge bases or relationship-heavy data, the platform extends to Amazon DocumentDB as a JSON-native store behind chat and search experiences, and Amazon Neptune for GraphRAG and graph-based retrieval over entity and relationship data. These are delivered as a scoped reference pattern once a specific customer use case is confirmed.
Every engagement includes a governance and access model via AWS Lake Formation and AWS IAM Identity Center, a data quality and lineage baseline, UK data residency in eu-west-2 London, encryption via AWS KMS, and full audit logging through AWS CloudTrail and Amazon CloudWatch, aligned to ISO 27001 and Cyber Essentials.
Typical use cases include unifying student, patient or citizen records for reporting and AI, replacing legacy warehouse spend with Redshift Serverless, standing up self-service BI for registries, finance and operations teams, and preparing a private governed knowledge base ahead of a generative AI pilot.
Delivered by CirrusHQ as an AWS Premier Tier Services Partner with the AWS Education Competency, Well-Architected and DevOps designations, available via AWS Marketplace, G-Cloud 14 and Crown Commercial Service frameworks. Contact CirrusHQ for a scoped Statement of Work."
Highlights
Highlighted by the publisher on AWS Marketplace.
Governed lakehouse in weeks: Amazon S3, AWS Glue and AWS Lake Formation replace siloed spreadsheets and legacy warehouses with one catalogued, access-controlled data platform serving BI, analytics and AI from a single source of truth.
AI-ready from day one: a built-in Amazon OpenSearch Serverless vector store makes your data instantly usable for Amazon Bedrock RAG, chatbots, copilots and agentic workflows without additional data preparation.
Exit legacy database costs: schema conversion and cutover from Oracle, Teradata, Netezza, SQL Server or Snowflake onto Amazon Redshift Serverless and Amazon Aurora PostgreSQL using AWS SCT and AWS DMS.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Sources
Linked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.