Managed retrieval-augmented-generation and search service: indexes content from R2 buckets or crawled websites with hybrid (vector plus full-text) search and OCR, queried from a Workers binding, REST API or MCP. Launched as AutoRAG, renamed AI Search in September 2025, GA October 2026.
FluffyStack toolsJurisdictional exposure
Attributes
- Ga Year
- 2026
Sub-services (3)
Indexing
Ingest content from R2 buckets, websites, or Workers KV into the vector index
Natural-Language Query
Retrieve relevant chunks from a Worker binding, REST API, or MCP server
Evaluation
Built-in eval metrics for retrieval and generation quality
Compliance & Certifications
This service is attested for the following frameworks. Always verify with the provider before relying on a specific compliance posture.
Where this runs
Commercial regions (29)
Europe (10)
- Paris
- Frankfurt
- Dublin
- Milan
- Amsterdam
- Warsaw
- Madrid
- Stockholm
- Zurich
- London
North America (4)
- Toronto
- Ashburn
- Chicago
- San Jose
South America (2)
- Buenos Aires
- São Paulo
Asia (6)
- Hong Kong
- Mumbai
- Tokyo
- Singapore
- Seoul
- Taipei
Oceania (2)
- Sydney
- Auckland
Middle East (2)
- Tel Aviv
- Dubai
Africa (3)
- Lagos
- Cape Town
- Johannesburg
Tags
Equivalent services on other platforms
Generative AI assistant family spanning software development (Q Developer, formerly CodeWhisperer), enterprise knowledge retrieval (Q Business), low-code app generation (Q Apps), and contact-centre augmentation (Q in Connect) with grounded answers against your own data
Managed enterprise search — natural-language question-answering over documents in S3, SharePoint, Confluence, Salesforce, RDS, and 40+ other sources with connectors, semantic ranking, and no ML expertise required
Agentic AI workspace for business users combining chat agents over company data, deep research, Flows and Automate for workflow automation, Spaces for shared knowledge, and Quick Sight BI. AWS's successor to Amazon Q Business.
Enterprise search-as-a-service (formerly Azure Cognitive Search) with vector, hybrid, and semantic ranking, built-in AI skills for OCR and NLP enrichment, first-class integration with Azure OpenAI for RAG workloads, and 90+ data-source connectors including SharePoint, OneDrive, and Salesforce
Enterprise AI-agent platform combining Gemini reasoning with unified search across Workspace, Drive, ServiceNow, Jira, Salesforce, and custom sources — agents can act on tools + APIs on the user's behalf, with governance controls for what each agent may access
AI Studio (optionally with Le Chat and Vibe agent tooling) delivered on dedicated 8x H200 GPU capacity in the SecNumCloud cloudgouv-eu-west-1 region, giving access to a library of sovereign LLMs; sold on quotation
Fully managed AI and ML service offering hosted LLMs, vector search, and ML functions inside Snowflake SQL