SWIRL AI Search
swirlaiconnect.com
What it is
SWIRL AI Search provides federated search across enterprise systems, querying source systems as each signed-in user and applying permissions there. The maker says searches do not copy, index, or move source content; retrieved text is held for the request. Its three-pass ranking uses keyword/BM25, E5-Large-V2 embedding re-ranking with hybrid fusion, and an MS-MARCO cross-encoder. SWIRL can generate cited answers from retrieved sources and flag claims unsupported by them. It lists more than 150 connectors, including Microsoft 365, Google Workspace, Salesforce, ServiceNow, GitHub, Confluence, Jira, Box, and databases, and supports more than 100 LLMs, including on-prem models through Ollama and compatible frameworks. Enterprise exposes a REST API and MCP server for agents to access ranked, permissioned answers. Customers can deploy on-prem, in a private VPC, or in a cloud tenant using Docker Compose or Kubernetes. Enterprise supports SSO through OAuth2/OpenID Connect and can use Microsoft Presidio to detect and redact personal information. The optional Semantic Cache is separately licensed and is an exception to the no-vector-store approach. Departmental licensing is $24,000/year; a free plan and free trial are listed.
Spec sheet
- Product
- SWIRL provides federated AI search across enterprise systems, querying live as each signed-in user with permissions enforced at the source.Read 30 Sep 2026 · swirlaiconnect.com
- Audience
- The maker positions SWIRL for enterprises that cannot centralize their data and identifies lawyers, analysts, and clinicians as examples of users relying on grounded AI answers.Read 30 Sep 2026 · swirlaiconnect.com
- Deployment
- SWIRL can run inside a customer's environment on-prem, in a private VPC, or in a cloud tenant, using Docker Compose or Kubernetes.Read 30 Sep 2026 · swirlaiconnect.com
- Security
- SWIRL Enterprise supports SSO through OAuth2/OpenID Connect, and the maker says source ACLs are preserved by passing through the user's identity.Read 30 Sep 2026 · swirlaiconnect.com
- Compliance
- The maker says customers configure SWIRL and their surrounding controls to meet their regulatory obligations; it offers configuration guidance and, under NDA, audit-support artifacts.Read 30 Sep 2026 · swirlaiconnect.com
- Support
- Departmental includes community and email support, Business includes a standard SLA and priority support, and Enterprise includes a premium SLA and named technical account manager.Read 30 Sep 2026 · swirlaiconnect.com
- Headquarters
- Waltham, Massachusetts, United StatesRead 28 Sep 2026 · swirlaiconnect.com
- Founded
- 2024Read 28 Sep 2026 · swirlaiconnect.com
- Agent access
- The Enterprise product exposes a REST API and first-class MCP server for agents to access the same ranked, permissioned, cited answers.Read 30 Sep 2026 · swirlaiconnect.com
- Answers
- SWIRL generates cited answers from retrieved sources and can flag claims that are not supported by the retrieved material.Read 30 Sep 2026 · swirlaiconnect.com
- Connectors
- The maker lists more than 150 connectors, including Microsoft 365, Google Workspace, Salesforce, ServiceNow, GitHub, Confluence, Jira, Box, and databases.Read 30 Sep 2026 · swirlaiconnect.com
- Limits
- The optional Semantic Cache is separately licensed and is the exception to the no-vector-store approach; its caching is based on documents users have already retrieved with their credentials.Read 30 Sep 2026 · swirlaiconnect.com
- LLMs
- SWIRL supports more than 100 LLMs, including OpenAI, Azure OpenAI, Anthropic Claude, Google Gemini, Mistral, and on-prem models through Ollama and compatible frameworks.Read 30 Sep 2026 · swirlaiconnect.com
- PII controls
- Enterprise can use Microsoft Presidio to detect and redact personal information, with redaction enabled per SearchProvider.Read 30 Sep 2026 · swirlaiconnect.com
- Ranking
- Its three-pass ranking uses keyword/BM25, E5-Large-V2 embedding re-ranking with hybrid fusion, and an MS-MARCO cross-encoder.Read 30 Sep 2026 · swirlaiconnect.com
- Zero-copy retrieval
- The maker says searches run against source systems without copying, indexing, or moving source content; retrieved text is held for the request duration.Read 30 Sep 2026 · swirlaiconnect.com
Plans and prices
Strong points and limits
Strong points
- Searches preserve source permissions through user identity
- Cited answers can flag unsupported claims
- More than 150 connectors are listed
- More than 100 LLMs are supported
- On-prem, private VPC, and cloud-tenant deployment
Limits
- Departmental costs $24,000/year
- Semantic Cache is separately licensed
- Compliance depends on customer-configured controls
- Personal-information redaction is enabled per SearchProvider
Who it suits
SWIRL is positioned for enterprises that cannot centralize their data. The maker names lawyers, analysts, and clinicians as examples of users who rely on grounded AI answers.
Verdict
SWIRL is designed for enterprise search where data stays in source systems and access follows user permissions. Consider deployment, compliance configuration, and the separately licensed Semantic Cache when evaluating it.
Where Specifiction places it
- AI Enterprise Search Software#13 of 267.8