QueryPanel is the embedded analytics platform for multi-tenant SaaS. Primary product: a headful React SDK (Notion-like dashboards and AI assistant). Secondary: a headless Node SDK for zero-trust custom UI. Searches that look like “fury query panel” almost always mean QueryPanel.

Is this another BI tool?

QueryPanel is infrastructure for embedding analytics and generating safe SQL, built for product surfaces, not standalone analyst workspaces.

How do you handle tenant isolation?

Tenant context is part of generation and execution, not something you toggle later in a dashboard filter.

What does implementation look like?

Attach your database with the SDK, wire auth claims, and embed UI where customers already work. Scope follows your surfaces, not building a query engine from scratch.

How do you keep AI SQL accurate as schemas evolve?

Ground generation in synced schema metadata and your knowledge base (annotations, glossaries, and examples) so retrieval and SQL stay aligned with how your data model actually works.

How are tenants counted?

A tenant represents a distinct customer or organization within your SaaS product. We count the number of unique tenants that access or generate analytics in a given billing month.

What counts as an AI chart?

An AI chart is generated whenever an end-user asks a natural language question that results in a new chart, or when an editor uses AI to create or modify a dashboard block.

What happens when limits are exceeded?

You can purchase overage credits for AI charts. For tenant limits, we'll notify you when you approach your plan's limit and help you upgrade to the next tier. We never cut off access for your end-users without warning.

How are AI models selected?

We support OpenAI, Gemini, Anthropic, and even OpenRouter. Bring-your-own-key is available from Starter and above (including Growth and Scale). Custom plans also support bring-your-own-model setups. If you want a specific provider or model path, ping us at csaba.ivancza@querypanel.io.

QueryPanel vs DataBrain

AI-powered embedded analytics with a governed semantic layer, multi-tenant RLS, and white-label dashboards.

DataBrain (usedatabrain.com) positions itself as an AI-powered embedded analytics platform for product and engineering teams. The product story centers on connecting a warehouse or database, defining governed metrics once, embedding white-label dashboards as web components such as `<dbn-dashboard>`, and answering natural-language questions with tenant-scoped, semantic-layer-grounded results. DataBrain says it stores metadata only and runs queries against your warehouse, and it publishes flat plans with unlimited seats and tenants. Teams shortlisting AI-powered embedded analytics for multi-tenant SaaS should also evaluate QueryPanel when they want a headful React workspace with an AI assistant and a headless Node path for zero-trust execution—not only a managed analytics suite.

Last reviewed October 19, 2026. Vendor facts are checked against public docs and pricing pages on that date.

Start building Read the docs

Comparison at a glance

This table summarizes typical positioning. Every vendor changes over time—validate details against current documentation and your security review.

Dimension	DataBrain	QueryPanel
Embed model	Web components such as `<dbn-dashboard>` mounted in your page with a guest token from your backend; framework guides cover React, Vue, Angular, and Next.js. Iframe embedding exists but is not the recommended path.	First-class `@querypanel/react-sdk` components—`QuerypanelEmbedded` for a full dashboard, or `QueryPanelProvider` with `QueryInput` / `QueryResult` for a bespoke flow. They render in your React tree like any other product screen (layout, router, modals, tokens)—not a separate iframe "mini app" on another origin. Mint short-lived JWTs on your server; never ship your workspace private key to the browser.
React SDK	No React-specific component library; you render DataBrain's custom elements in JSX and pass options as attributes.	`@querypanel/react-sdk` ships `QuerypanelEmbedded` for the full workspace, plus provider and query components for custom flows.
Primary product shape	Managed embedded analytics suite with warehouse connections, a governed semantic layer, low-code dashboard builder, and AI answers grounded in defined metrics.	Headful React workspace plus headless Node `ask()` calls for teams that want customer questions, SQL, and charts in one product loop.
Multi-tenancy mechanism	Guest token per embed session plus per-table SQL policies on a client identifier; DataBrain markets RLS by tenant, role, and attribute.	Tenant column declared at database attach; RS256 JWT minted by `@querypanel/node-sdk` carries the tenant ID; the tenant filter is applied at SQL generation and checked before execution.
AI / natural language	AI Chat Mode answers natural-language questions scoped to the requesting tenant and traced to semantic-layer metrics; DataBrain also markets MCP-ready agent access.	Natural language to SQL and chart generation are first-class API and embedded SDK workflows; the AI assistant can add charts to and reshape tenant dashboards.
End-user dashboard editing	Customers can explore, filter, drill down, and export; self-serve creation runs through DataBrain's builder and the metrics you expose.	Tenants fork shared dashboards and customize their own copy, with the AI assistant adding or changing charts on request.
Semantic layer / modeling	Core of the product: metrics defined once via Visual Builder, Custom SQL, or AI-assisted modeling, and versioned for dashboards and AI.	Gold SQL queries (curated examples the model prioritizes), database annotations (business context on tables/columns, re-embedded with schema), glossary (domain terms and definitions), and tenant-level definitions (isolation field, enforcement, and per-tenant sync context so every ask() is grounded in the right customer slice—not a one-size global prompt).
Data plane & credentials	DataBrain connects to your warehouse or database and says it stores metadata only, running queries against your source.	Headful path uses your attached database; the headless Node path runs SQL with your own drivers, so credentials and result rows stay on your servers.
Deployment	Cloud, with self-hosted / on-prem options marketed for stricter environments; verify which plan includes them.	Hosted service with React and Node SDKs; zero-trust headless mode keeps execution in your environment. Node SDK adapters cover Postgres, ClickHouse, and BigQuery, with a custom adapter option.
Pricing shape	Published flat plans: Growth $999/month, Pro $1,995/month, Enterprise custom; unlimited seats and tenants on every tier (checked October 19, 2026).	Counts unique tenants per billing month, not seats; AI chart generation metered separately; free tier available.
Time to first embed	Connect a warehouse, define metrics, design a dashboard, then drop in the web component; the 14-day trial covers a proof of concept.	Attach a database, mint a JWT on your server, render `QuerypanelEmbedded` on one route; customers can ask questions before any dashboard is designed.

Start with the system you need to operate

DataBrain is designed for teams that want a warehouse-centered semantic layer and a managed white-label analytics workflow: someone defines metrics in DataBrain's builder, designs dashboards there, and the product embeds them. QueryPanel is better aligned when your product backend should stay responsible for query execution and your team wants to add analytics in the same React and Node surfaces it already owns. Ask who will maintain metric definitions a year from now. If the answer is a data team inside a vendor tool, DataBrain fits. If it is product engineers in your repo, QueryPanel fits.

Semantic layer first, or questions first

DataBrain grounds AI answers in metrics you define up front, which gives consistent numbers but means the AI is only as broad as the model you have built. QueryPanel generates SQL against your schema directly and steers accuracy with gold SQL, annotations, a glossary, and tenant-level definitions. That lets customers ask new questions on day one, but you should test accuracy on your own schema and review generated SQL during rollout. Pick the trade-off that matches how often your customers ask questions nobody anticipated.

Web component versus React tree

Both products avoid an iframe for the main dashboard. DataBrain mounts web components such as `<dbn-dashboard>` and notes iframe embedding is not the recommended path. QueryPanel renders `QuerypanelEmbedded` as React components, so routing, modals, context providers, and design tokens behave like the rest of your app. If your app is React end to end, that difference shows up in theming, focus handling, and state sharing. If you run several front-end frameworks, a web component can be the simpler contract.

When DataBrain is the better fit

Honest tradeoffs help your team pick faster—and match how buyers actually decide.

You want a packaged embedded analytics engine—semantic layer, multi-tenant RLS, white-label dashboards, and governed AI—without assembling those pieces yourself.
Your data already lives in a warehouse (Snowflake, BigQuery, Redshift, Databricks, Postgres) and you want metrics defined once for dashboards and AI answers.
Product and data teams prefer a low-code builder plus SDK snippet over owning NL→SQL generation and validation in application code.
You want a published flat price with unlimited seats and tenants (Growth $999/month, Pro $1,995/month as checked October 19, 2026) so the bill does not move with every user your customers invite.
You need a framework-agnostic embed: DataBrain's web components work in React, Vue, Angular, or plain HTML, which helps when not every product surface is React.

When QueryPanel is the better fit

Choose QueryPanel when the initial product goal is a React-native AI analytics experience with reviewable SQL and tenant-level dashboard customization, rather than a managed semantic layer and dashboard builder. Choose DataBrain when governed metrics and a vendor builder should be the first milestone.

You want a trainable knowledge system—gold queries, DB annotations, glossary, and tenant-aware definitions—so NL→SQL and charts reflect your business, not generic schema-only guesses.
You want the primary customer experience to be a headful React workspace with a Notion-like dashboard shell and built-in AI assistant inside your product routes, not a custom element wrapping a vendor dashboard.
You want natural-language questions to become reviewable SQL and charts in your backend path, with execution on your drivers—not only answers inside a managed analytics control plane.
You need a headless zero-trust Node SDK path where credentials and query results stay on customer infrastructure when stricter data boundaries matter.
You prefer a smaller product-engineering surface: React SDK in the app tree, Node SDK in API routes, existing auth, and no second semantic-layer release train as the first milestone.
Your tenants should fork and reshape shared dashboards with an AI assistant, and you want pricing that counts tenants per month rather than plan tiers keyed to data sources.

Pricing notes

Checked October 19, 2026. Pricing changes; confirm on the vendor pages before you budget.

DataBrain

DataBrain publishes its prices. As checked October 19, 2026, Growth is $999 per month (one data source) and Pro is $1,995 per month (unlimited data sources), each with a 14-day free trial; Enterprise is custom. Every tier lists unlimited seats and unlimited tenants (clients), so cost does not rise with end users. Confirm data-source limits, self-hosting, and AI usage terms on the pricing page before you budget.

QueryPanel

QueryPanel pricing is tenant-based: plans count unique tenants per billing month, not end-user seats, so inviting more users inside a customer does not change the bill. AI chart generation is metered separately, and a free tier is available for evaluation. See the pricing section for current plans.

Sources: DataBrain pricing, QueryPanel pricing

Migrating from DataBrain to QueryPanel

1. Inventory DataBrain dashboards, metrics, and embeds
List every embedded `<dbn-dashboard>` placement, the dashboards behind them, and which semantic-layer metrics each one uses. Pull usage from your product analytics so you rebuild the dashboards customers open, not every draft. Note which metrics are also used by AI Chat Mode answers.
2. Map DataBrain's tenant policy to a QueryPanel tenant column
DataBrain scopes data with a guest token and per-table SQL policies on a client identifier. In QueryPanel, declare that same column (for example `tenant_id` or `client_id`) as the tenant field when you attach the database, and have your backend mint RS256 JWTs with `@querypanel/node-sdk` carrying the tenant ID from your auth session.
3. Translate metrics into trainable knowledge
Sync the schema, then turn each governed DataBrain metric into a gold SQL query, column annotations, and glossary terms (for example, what counts as an active account). Add tenant-level definitions where customers compute a metric differently. This is the step that decides NL-to-SQL accuracy, so give it real time.
4. Embed QuerypanelEmbedded behind a feature flag
Render `QuerypanelEmbedded` from `@querypanel/react-sdk` on one analytics route for internal users and a few friendly tenants. Recreate the top dashboards as shared templates that tenants can fork. Keep the DataBrain web component on the existing route.
5. Run both side by side and compare numbers per tenant
For each pilot tenant, compare headline metrics between the DataBrain dashboard and the QueryPanel dashboard over the same date range. Ask the same five questions in DataBrain's AI chat and in QueryPanel, inspect the generated SQL, and fix differences with gold SQL or annotations.
6. Cut over and remove the DataBrain embed
Move remaining tenants route by route, then remove the `<dbn-dashboard>` elements, the guest-token endpoint, and the DataBrain workspace credentials. Keep the old dashboards read-only for one billing cycle in case a customer asks for a historical comparison.

Comparison FAQ

How does QueryPanel differ from DataBrain for embedded analytics?

DataBrain centers on a managed semantic layer, a dashboard builder, and governed warehouse analytics delivered as web components. QueryPanel centers on a headful React workspace with an AI assistant that tenants use to customize dashboards, plus a headless Node SDK where your backend owns authentication and query execution.

How much does DataBrain cost compared with QueryPanel?

DataBrain's pricing page, as checked October 19, 2026, lists Growth at $999 per month and Pro at $1,995 per month, both with unlimited seats and tenants, and Enterprise as custom. QueryPanel plans count unique tenants per billing month, not end-user seats, meter AI chart generation separately, and include a free tier. Model both at your current and doubled tenant count.

Does DataBrain use iframes?

DataBrain's recommended embed is a web component, such as `<dbn-dashboard>`, that mounts in your page and is authorized with a guest token from your backend. An iframe option exists but is not the recommended path. QueryPanel's headful SDK renders React components directly in your tree, and its headless SDK lets you build your own UI.

How does multi-tenancy work in DataBrain versus QueryPanel?

DataBrain scopes tenants with a guest token and per-table SQL policies keyed on a client identifier, so each customer sees only its rows. QueryPanel declares a tenant column when you attach the database; your backend mints an RS256 JWT with the tenant ID, the tenant filter is part of SQL generation, and generated SQL is checked for it before execution.

Is QueryPanel a full replacement for DataBrain?

Not always. QueryPanel replaces the customer-facing dashboards and AI questions, but it is not a semantic-layer product. If many teams depend on DataBrain's governed metric definitions, you would move those definitions into gold SQL, annotations, and glossary entries, or keep a semantic layer elsewhere. For product-embedded analytics on Postgres or ClickHouse, QueryPanel usually covers the job.

How long does it take to migrate from DataBrain to QueryPanel?

Effort depends on how many dashboards and metrics you maintain in DataBrain. Most of the work is translating metric definitions into gold SQL and annotations, mapping DataBrain's tenant policy to a QueryPanel tenant column, and rebuilding the handful of dashboards customers actually open. Run both side by side per tenant before you remove the DataBrain embed.

Still evaluating DataBrain and QueryPanel?

Start on the free tier, embed one dashboard, and compare implementation time against your current shortlist.

Start free All comparisons