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 Sisense

Enterprise embedded analytics and OEM-style programs.

Sisense is a long-standing analytics platform with strong enterprise traction. Teams often evaluate it when they need a full embedded BI stack, semantic modeling, and services-led rollout for complex customer bases.

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	Sisense	QueryPanel
In-app experience for end users	Two embed paths: iframe embedding of Sisense dashboards, or Compose SDK components. Iframes bring Sisense's own surface; Compose SDK components render in your app but still query a Sisense instance.	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	Compose SDK (`@sisense/sdk-ui`) provides React components for charts, dashboards, and generative AI features; it authenticates against and reads from a Sisense deployment.	`@querypanel/react-sdk` with `QuerypanelEmbedded`; it calls your API, which mints tenant JWTs with `@querypanel/node-sdk`.
Semantic layer & modeling	ElastiCube and live data models hold joins, formulas, and data security rules; analysts maintain them inside Sisense.	No separate semantic-layer product: schema sync plus gold SQL, annotations, and glossary steer generation against your own tables.
End-user dashboard editing	Depends on the multitenancy model and license; in Sisense's shared-model pattern, tenants can create dashboards but cannot change the data model.	Tenants fork and customize dashboards in the Notion-like workspace and add charts by asking the built-in AI assistant.
Primary interface	Dashboards and modeling workflows aimed at analysts and BI teams.	Product teams lead with `@querypanel/react-sdk` for customer UI; `@querypanel/node-sdk` on your backend for signing, schema sync, and `ask()` from API routes.
Trainable knowledge & steering	Correctness is anchored in governed metrics and BI modeling; ad-hoc SQL exemplars and column-level glossaries are usually separate analytics workflows from product code.	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).
AI / natural language	Built-in AI features, plus Compose SDK generative AI components (chatbot, natural-language query hooks) that work over Sisense data models governed by the model's row and column security.	Natural language to SQL is a first-class path, designed for customer questions inside your app.
Multi-tenant SaaS fit	Self-contained tenants with separate user management (a premium feature), or row-level data security rules on shared data models, configured in Sisense.	Tenant context and tenant-scoped SQL generation are core to the embedded workflow.
Credentials & data plane	Data connections, ElastiCubes, and models live in your Sisense deployment, either Sisense managed cloud or self-hosted.	You execute SQL in your environment; QueryPanel focuses on generation and UX, not holding database credentials.
Pricing shape	Quote-based enterprise and OEM pricing; self-service Launch and Grow tiers reported in February 2026, with credits metering AI services.	Tenant-based: unique tenants per billing month, not seats; AI chart generation metered separately; free tier available.
Time-to-first embed	Depends on modeling work: data models, security rules, and the embed method have to be in place before the first customer sees a dashboard.	Designed for days-to-weeks when your schema and tenant model are already defined in Postgres or similar.

Compose SDK narrows the UI gap, not the platform gap

Sisense's Compose SDK (`@sisense/sdk-ui`) gives React developers chart, dashboard, and generative AI components, so the old "Sisense means iframes" objection is weaker than it was. Those components still query a Sisense instance: you license it, host or subscribe to it, build data models in it, and authenticate users against it. QueryPanel's React SDK talks to your API, which mints a tenant JWT with `@querypanel/node-sdk`, and SQL runs against the database you already operate. The real question is whether you want a BI platform running behind your product.

Sisense tenants versus a tenant claim in your JWT

Sisense documents two broad multitenancy patterns: self-contained tenants with their own user management (a premium feature) and shared data models secured with row-level data security rules, which is common in OEM deployments. Both keep tenant logic inside Sisense administration. QueryPanel keeps the tenant boundary in your code: the tenant id travels in a server-signed JWT and in the generation request, so the SQL is scoped to one customer before it runs on your database. Test cross-tenant access on both before you sign.

Who answers the next new customer question

In a Sisense program, a new customer question usually means an analyst updates a data model or dashboard and publishes it. In QueryPanel, a tenant user asks the AI assistant inside the embedded workspace, gets SQL and a chart, and saves it to their own copy of the dashboard. That moves work from a BI team into the product. It suits SaaS teams without dedicated analysts and does not suit teams that need every metric approved centrally.

When Sisense is the better fit

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

You need a broad enterprise BI footprint with established procurement paths.
You are standardizing on a vendor that already serves centralized analytics and embedded programs together.
You have dedicated data engineering and BI resources to own modeling, rollout, and customer-specific tailoring.

When QueryPanel is the better fit

Choose QueryPanel over Sisense when a product team wants customer analytics inside its React app without running a Sisense instance, data models, and OEM program behind it. Keep Sisense when governed data models, OEM licensing, and enterprise BI breadth are the point.

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 customer analytics to feel like the rest of your product: React components in your shell and design system—not an iframe-hosted analytics app with its own chrome and awkward sizing.
You want `@querypanel/react-sdk` for the embedded UI and `@querypanel/node-sdk` on your API for JWT signing, schema sync, and tenant-scoped `ask()`—a small, composable stack.
You need to ship customer-facing analytics quickly without standing up a classic BI program or months of custom chart UI.
You want AI-native generation (question → SQL → chart) as the default workflow, not a bolt-on.

Pricing notes

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

Sisense

Enterprise and OEM embedded pricing is quote-based on Sisense's pricing page. As reported by S&P Global 451 Research in February 2026 (republished by Sisense), Sisense added credit-card self-service tiers: Launch at $399/month (view-only) and Grow at $1,299/month (adds persistence, basic SSO, and white-labeling), with credits metering AI and consumption services. Confirm current tiers with Sisense, and budget for the license, hosting (Sisense managed cloud or self-hosted), and implementation together.

QueryPanel

QueryPanel pricing is tenant-based: plans count unique tenants per billing month, not end-user seats, so adding users inside an existing customer does not raise the bill. AI chart generation is metered separately, and a free tier lets you embed on one route before committing.

Sources: Sisense pricing, S&P Global 451 report on Sisense tiers (Feb 2026), QueryPanel pricing

Migrating from Sisense to QueryPanel

1. Inventory Sisense dashboards, data models, and embeds
List every customer-facing dashboard, the ElastiCube or live model it reads, and how it is embedded (iframe or Compose SDK). Check which dashboards customers actually open; dashboards nobody uses do not need to move.
2. Map Sisense tenants and data security rules to a tenant claim
For each customer, record how Sisense isolates them today: a self-contained tenant, a user group, or data security rules on a shared model. Pick the column that identifies the customer in your database, such as `organization_id`, and have your backend mint a QueryPanel JWT with `@querypanel/node-sdk` that carries that tenant id.
3. Sync the schema and turn model logic into knowledge
Run schema sync against the Postgres, ClickHouse, or BigQuery database behind your Sisense models. Rewrite important model formulas and filters as gold SQL queries, add database annotations for columns whose names do not explain themselves, and add glossary entries for the metric names customers see.
4. Embed QuerypanelEmbedded on one route behind a flag
Install `@querypanel/react-sdk` and render `QuerypanelEmbedded` on one analytics route, behind a feature flag for internal accounts or a few pilot tenants. Leave the Sisense iframe or Compose SDK view on the existing route.
5. Compare numbers per tenant side by side
For each pilot tenant, compare totals, date ranges, and filters between the Sisense dashboard and the QueryPanel version. Differences usually come from joins or calculated fields defined in the Sisense model; fix them with gold SQL or annotations rather than one-off patches.
6. Cut over and retire the Sisense embed path
Move tenants in batches, then remove the Sisense embed code and the SSO or token service that signed Sisense sessions. Keep Sisense for internal BI only if it still earns its license.

Comparison FAQ

Is QueryPanel a good Sisense alternative for a React SaaS product?

Yes, when the goal is customer-facing analytics inside your React app on a database you already run. QueryPanel's primary product is its headful React SDK with a Notion-like dashboard management system and AI assistant for tenant customization. Sisense remains the better choice when you need a full enterprise BI suite, governed data models, and an OEM program staffed by a BI team.

Does Sisense embed with iframes or React components?

Both. As checked October 19, 2026, Sisense supports iframe embedding and the Compose SDK, whose `@sisense/sdk-ui` package exposes React components for charts, dashboards, and generative AI features. Compose SDK components still connect to a Sisense instance for data and authentication. QueryPanel's `QuerypanelEmbedded` component renders in your React tree and talks to your own API.

How much does Sisense cost compared with QueryPanel?

As checked October 19, 2026, Sisense quotes enterprise and OEM embedded pricing through sales; S&P Global reported self-service Launch ($399/month) and Grow ($1,299/month) tiers in February 2026, so confirm current tiers with Sisense. QueryPanel pricing is tenant-based: plans count unique tenants per billing month rather than end-user seats, AI chart generation is metered separately, and there is a free tier. See the pricing section on the QueryPanel homepage for current plans.

How does multi-tenancy differ between Sisense and QueryPanel?

Sisense handles tenants inside the platform, either as self-contained tenants with separate user management or with row-level data security rules on shared data models. QueryPanel puts the tenant id in a short-lived JWT signed by your backend with `@querypanel/node-sdk` and applies it during SQL generation, so each query is scoped to one customer before it executes in your environment.

How much work is a migration from Sisense to QueryPanel?

It depends on how many dashboards and data models you carry. Most of the effort is rewriting the logic that lives in Sisense data models as gold SQL queries, annotations, and glossary entries, then checking numbers per tenant. A team with a handful of customer-facing dashboards on Postgres can run both side by side within weeks; large OEM programs take longer.

Is QueryPanel a full replacement for Sisense?

Not for every Sisense use case. QueryPanel is not a full enterprise BI suite or semantic-layer product, and it does not focus on pixel-perfect reports or scheduled PDF delivery. It replaces the customer-facing embedded part: dashboards and AI questions inside your SaaS product, scoped per tenant. Internal BI on Sisense can stay where it is.

Still evaluating Sisense and QueryPanel?

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

Start free All comparisons