Back to vendors
L

Lumi AI

Visit site
Entry priceFrom $50 per month ($45 billed annually), StarterFull pricing detail

Lumi AI is a chat based data analyst for operations teams that answers questions over ERP and warehouse data with read only access, grounded in a customer maintained knowledge base, with scheduled board alerts and an on premises data gateway.

Lumi AI lets supply chain, distribution, retail and other operations teams ask questions of their data in plain language. It connects with read only access to PostgreSQL, SQL Server, MySQL, Databricks, BigQuery, Snowflake, SAP HANA, Oracle, Athena and Redshift, breaks complex questions into parallel reasoning paths, adds Python analysis, and shows the logic, assumptions and transformations behind every answer. Lumi 3.0 adds editable artifacts, versioning and in thread collaboration.

Answers are grounded in a Knowledge Base the customer maintains: tables and fields, custom fields and filters, the data model, business context, KPIs and aliases, with memories that users propose from feedback and contributors commit. Boards can refresh on a schedule with alert rules that notify chosen people, and Human Verification lets contributors approve or reject a result without blocking it. Lumi is also available in Slack and Microsoft Teams.

Lumi offers role based access control, SAML SSO on Enterprise, query limiters and an on premises Data Gateway with a single tenant option so data stays in the customer's environment. Its features page claims SOC 2 compliance while its pricing page lists SOC 2 Type II as coming soon. Pricing starts at $50 a month for Starter, with Pro at $1,110 and Enterprise by contact with a pilot.

Vendor details

Canonical URL

https://lumi-ai.com

Category

Data analyst agent

Company status

independent

Use cases & customers

Integrations

Read only connectors: PostgreSQL, Microsoft SQL Server, MySQL, Databricks, BigQuery, Snowflake, SAP HANA, Oracle, AWS Athena, Redshift; on premises Data Gateway; Slack and Microsoft Teams bots.

In practice

A retail pricing team asks Lumi to find margin opportunities, and its agents analyze a full year of sales and elasticity inside the company network, returning ranked SKUs without any data leaving the environment.

A procurement lead connects Lumi to the enterprise resource planning system and asks which items were bought from multiple suppliers in one month, then uses the finding to negotiate better vendor terms.

An operations team configures Lumi to hunt for working capital opportunities, and its agents monitor operational data continuously, surfacing anomalies and sending decision ready recommendations to stakeholders without waiting to be asked.

Agentic Index coverage score

7.5 / 14 capabilities · 54%

Integrations & Tool Calling Partial

Lumi connects with read only access to PostgreSQL, SQL Server, MySQL, Databricks, BigQuery, Snowflake, SAP HANA, Oracle, Athena and Redshift and answers in Slack and Microsoft Teams, but it takes no action in those systems and no custom tool is documented.

Sourcedocs.lumi-ai.com/product-features/source-system-integrationsread 2026-09-28

Workflow Orchestration Partial

Lumi's agentic workflows break a complex question into several reasoning paths run in parallel and add Python analysis, which is the product's own decomposition; no flow, branching or conditions the buyer configures are documented.

Sourcelumi-ai.com/conversational-analyticsread 2026-09-28

Knowledge Grounding & RAG Full

A Knowledge Base the customer maintains holds tables, fields, custom fields and filters, the data model, business context, KPIs and aliases, with versioned saving, restoration and export, and the context each question needs is retrieved from it.

Sourcedocs.lumi-ai.com/product-features/knowledge-base/overviewread 2026-09-28

Human Oversight & Guardrails Partial

Lumi runs with read only access, query limiters and role based access, and Human Verification lets Knowledge Base contributors approve or reject a result, but the docs say verification never blocks an insight from being generated, so it is an advisory review rather than a gate before anything commits.

Sourcedocs.lumi-ai.com/product-features/human-verificationread 2026-09-28

Security, Identity & Governance Partial

The access half is documented: role based access control and custom SAML SSO on Enterprise. The attestation is contradicted on Lumi's own pages: the features page claims SOC 2 compliance while the pricing page lists SOC 2 Type II certification as coming soon, and trust.lumi-ai.com renders nothing readable.

Sourcelumi-ai.com/pricingread 2026-09-28

Observability & Auditability Full

Every answer shows its logic, assumptions and transformations, a Show Thinking control exposes the agent's reasoning, analyses are versioned and exportable, and the features page names audit trails, so the steps behind each result can be inspected.

Sourcelumi-ai.com/conversational-analyticsread 2026-09-28

Memory & State Persistence Partial

Memories are records users propose from feedback on answers, reviewed by Knowledge Base contributors and moved through proposed, committed, rejected and invalidated states within one Knowledge Base; they are written by people rather than kept by the agent.

Sourcedocs.lumi-ai.com/product-features/knowledge-base/memoriesread 2026-09-28

Deployment & Data Residency Full

Enterprise adds the Lumi AI Data Gateway deployed on premises so data stays in the customer's environment, with a single tenant option, and the docs cover deploying and configuring the gateway.

Sourcedocs.lumi-ai.com/product-features/data-gatewayread 2026-09-28

Prebuilt Agents, Templates & Packs Partial

The docs offer an example prompt repository and curated prompts across use cases (exploration, metrics, anomaly detection, trend and root cause analysis, data quality), which the customer adapts; no prebuilt agents or packaged templates are offered.

Sourcedocs.lumi-ai.com/using-lumi/lumi-use-casesread 2026-09-28

Triggers & Channel Coverage Full

Board cards refresh on a schedule and carry alert rules that notify the people the team chooses when a monitored metric trips, with Lumi then used to investigate; proactive insights and alerting sit on the Pro plan.

Sourcedocs.lumi-ai.com/using-lumi/lumi-use-cases/proactive-alertingread 2026-09-28

Model Flexibility & Routing Unable to verify

Lumi refers only to an LLM without naming a provider, and no model choice for the customer is documented in its features or docs.

Sourcelumi-ai.com/featuresread 2026-09-28

APIs, SDKs & MCP Extensibility Unable to verify

The hundred page docs index lists connectors, a data gateway, Slack and Teams bots and SSO, but no API, SDK or MCP server for calling Lumi.

SourceLumi AI, docs llms.txt index and Tool Integrations page; docs.lumi-ai.com/product-features/organization-settings/tool-integrationsread 2026-09-28

Testing, Debugging & Optimization Partial

The Query Builder is a guided environment for writing and refining SQL, Python and analytical logic, and contributors can verify or reject individual results, which is review and debugging; no test set, scored cases or evaluation of the agent before or after a change is documented.

Sourcedocs.lumi-ai.com/product-features/query-builderread 2026-09-28

Browser & Computer Use Unable to verify

Lumi works through read only database connections and a data gateway; no browser, desktop or computer control is described.

Sourcelumi-ai.com/featuresread 2026-09-28

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Recent platform changes

2026-08-26·Agent capabilityVerified

Lumi AI has released version 3.0 of its platform, introducing capabilities for handling complex, open-ended queries. The update enables the agent to perform multi-step analysis that users can edit directly within their workflows.

Bears on: Agent capability

View source
View all 1 change for Lumi AI →Tracked since Aug 2026 · Verified from public vendor sources

Pricing

From $50 per month ($45 billed annually), Starter

per plan per month by users and data models

What is public

Starter and Pro prices with users and data models; Enterprise is custom.

Variable cost rationale

Flat monthly plans sized by users and data models, with query limiters on the platform.

Sales call required

Mixed (some tiers require a call)

Free / trial

No free plan; Enterprise pilot by request

Lowest paid plan

Starter ($50 per month)

Agentic Index verified 2026-09-28

Alternatives to Lumi AI

The closest documented capability profiles to Lumi AI among data analyst agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Querio9.0 / 14Adds documented APIs, SDKs & MCP Extensibility
  • Pluvo6.5 / 14Adds documented APIs, SDKs & MCP Extensibility
  • Scoop Analytics8.5 / 14Adds documented Model Flexibility & Routing
  • Opensee10.0 / 14Adds documented Model Flexibility & Routing and APIs, SDKs & MCP Extensibility
  • Potato6.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
  • Powerdrill8.0 / 14Adds documented APIs, SDKs & MCP Extensibility

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.