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 ThoughtSpot Embedded

Search-driven analytics at scale.

Buyers shortlisting AI-powered embedded analytics often compare ThoughtSpot for search-driven governed exploration. ThoughtSpot popularized AI-assisted search over governed models; embedded scenarios often emphasize consistent answers on top of curated metrics and a strong operations story for analytics teams. QueryPanel fits when the goal is customer-facing analytics inside a multi-tenant SaaS product with a headful React workspace and optional headless zero-trust Node path.

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	ThoughtSpot Embedded	QueryPanel
In-app experience for end users	Visual Embed SDK embeds Liveboards, search, and Spotter; its React components wrap iframe embeds served by the ThoughtSpot cluster.	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.
Experience shape	Search-first exploration on curated models; users with the right privileges create Answers and pin them to Liveboards.	Customer questions on your routes, rendered by your React tree, routed to tenant-safe SQL against your operational schema.
Trainable knowledge & steering	Search quality is driven by governed business objects and metric definitions; layering ad-hoc SQL libraries next to product code is less central to the platform story.	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).
Integration owner	Analytics and data platform teams typically lead modeling and rollout.	Product engineering owns the embedded surface; data stays in your existing Postgres / warehouse.
Flexibility vs guardrails	Strong guardrails when metrics are modeled carefully upstream.	Faster iteration for product teams that accept owning validation, review, and rollout of generated SQL.
Stack fit	Best when the ThoughtSpot stack aligns with your enterprise data architecture choices.	Postgres, ClickHouse, and BigQuery adapters today, plus a custom adapter hook; fits teams that want to stay close to operational stores.
Multi-tenancy mechanism	Orgs (isolated tenant containers; Enterprise or Embedded license) or row-level security rules on a shared model, with trusted authentication tokens scoped per Org.	Tenant id in a short-lived RS256 JWT minted by `@querypanel/node-sdk`; generation applies it to every query.
AI / natural language	Spotter AI analyst, embeddable through `SpotterEmbed`, answering over curated ThoughtSpot models.	AI assistant inside the tenant's dashboard workspace, plus headless `ask()` from your API routes.
Data plane & deployment	ThoughtSpot Cloud runs the UI and query engine and connects to your warehouse through connections configured in ThoughtSpot.	SQL executes in your environment; database credentials and query results stay on your servers.
Pricing shape	Free Developer tier for a proof of concept; production embedded plans quoted by sales; LLM tokens not metered separately.	Tenant-based: unique tenants per billing month, not seats; AI chart generation metered separately; free tier.
Buyer motion	Often a top-down analytics platform decision with POCs across data leadership.	Bottom-up trial: add `@querypanel/react-sdk` to a route, wire `@querypanel/node-sdk` in an API handler, connect a database, ship.

React components that still wrap an iframe

ThoughtSpot's Visual Embed SDK ships React components, but its own React embed docs show they wrap iframe embeds of ThoughtSpot pages. That gives you a solid search and Liveboard experience, but layout, theming, and routing still cross an iframe boundary, and the ThoughtSpot cluster serves the UI. QueryPanel's `QuerypanelEmbedded` renders in your React tree, so the dashboard workspace shares your layout, modals, and design tokens. If customers should not be able to tell where your product ends and the analytics begin, test this difference in a proof of concept.

Orgs, RLS, and where the tenant boundary lives

ThoughtSpot documents two ways to separate customers: Orgs, which are isolated tenant containers with their own users, groups, and objects (they need an Enterprise or Embedded license), and a single Org where row-level security rules on the model separate each customer's rows. Trusted authentication tokens can be scoped to an Org. QueryPanel skips the per-tenant admin objects: your backend signs a JWT with the tenant id using `@querypanel/node-sdk`, and generation applies it to every query.

Spotter versus an assistant inside a tenant's dashboard

Spotter, ThoughtSpot's AI analyst, can be embedded with the `SpotterEmbed` component and answers questions over models your data team curates. That works well when the model is large and well governed. QueryPanel's assistant lives inside the tenant's own dashboard workspace: a customer asks a question, gets SQL and a chart, and adds it to their copy of the dashboard. Accuracy depends on the gold SQL, annotations, and glossary you train, so evaluate both on your own schema.

When ThoughtSpot Embedded is the better fit

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

Search and drill across a wide enterprise metric layer is the primary experience you are selling.
You already invest in governed semantic layers and want AI on top of that foundation.
You need a brand-name analytics platform with a long enterprise track record.

When QueryPanel is the better fit

Choose QueryPanel over ThoughtSpot Embedded when analytics should render as part of your React product, scoped by a tenant claim your backend signs, rather than as an iframe onto a governed ThoughtSpot cluster. Keep ThoughtSpot when search and Spotter over a large, curated model are the product you are selling.

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 embedded analytics as native React—`QuerypanelEmbedded` or composable provider pieces—so customers never deal with a boxed iframe app inside your SaaS.
You are embedding analytics into a multi-tenant SaaS product, not rolling out another enterprise BI portal.
You want developers to own the stack: React components in your app, Node SDK on your API for auth and `ask()`, not a separate BI release train.
You want lightweight onboarding: connect the database, describe tenants, ship dashboards on a normal product route.

Pricing notes

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

ThoughtSpot Embedded

ThoughtSpot's pricing page lists a free Developer tier aimed at building an embedded proof of concept, limited in users and duration, and quote-based plans for production embedding. The page states that LLM tokens are included and not metered separately. Embedded production pricing is not published as a list price, so request a quote that covers your expected tenants, users, and data volume.

QueryPanel

QueryPanel pricing is tenant-based: plans count unique tenants per billing month, not end-user seats. AI chart generation is metered separately, and a free tier lets you ship a first embedded route before choosing a plan.

Sources: ThoughtSpot pricing, QueryPanel pricing

Migrating from ThoughtSpot Embedded to QueryPanel

1. Inventory Liveboards, Answers, and embed components
List the Liveboards and saved Answers customers see, which models they read, and which Visual Embed SDK components you use (Liveboard, search, Spotter). Mark the ones tied to revenue conversations; start there.
2. Map Orgs and RLS rules to a tenant claim
Record how each customer is isolated today: a dedicated Org, or RLS rules on a shared model keyed to a user attribute. Map that attribute to the tenant column in your database and mint a QueryPanel JWT with `@querypanel/node-sdk` that carries the tenant id, replacing the trusted authentication token request.
3. Sync the schema and port model knowledge
Run schema sync on the Postgres, ClickHouse, or BigQuery source. Turn model formulas and column synonyms into gold SQL queries, annotations, and glossary terms so the questions customers ask Spotter today map to the right tables and metrics.
4. Embed QuerypanelEmbedded on one route behind a flag
Install `@querypanel/react-sdk` and render `QuerypanelEmbedded` on one analytics route for internal accounts or a few pilot tenants, behind a feature flag. Keep the ThoughtSpot iframe embed live on the existing route.
5. Run both and compare answers per tenant
Ask the same question set in Spotter and in QueryPanel for each pilot tenant, and compare numbers, filters, and date handling. Fix gaps with gold SQL or annotations, and confirm that one tenant can never see another's rows.
6. Cut over and retire the ThoughtSpot embed service
Move tenants in batches, then remove the Visual Embed SDK code, the trusted authentication token endpoint, and any per-tenant Org provisioning scripts. Keep ThoughtSpot for internal analytics if your analysts still rely on it.

Comparison FAQ

Is QueryPanel a good ThoughtSpot Embedded alternative for SaaS?

Yes, when you are embedding analytics into a multi-tenant SaaS product built in React and want the UI to render natively. QueryPanel's primary product is its headful React SDK with a Notion-like dashboard management system and AI assistant for tenant customization. ThoughtSpot remains the stronger option for search-first analytics over large, governed enterprise models.

Does ThoughtSpot embed with an iframe?

Yes. As checked October 19, 2026, ThoughtSpot's Visual Embed SDK embeds Liveboards, search, and Spotter, and its React components wrap iframe embeds according to ThoughtSpot's developer docs. QueryPanel's `QuerypanelEmbedded` component renders directly in your React tree, with no separate iframe origin to size, theme, or authenticate.

How much does ThoughtSpot Embedded cost compared with QueryPanel?

ThoughtSpot's pricing page offers a free Developer tier for building an embedded proof of concept, while production embedded plans are quoted by sales; the page also says LLM tokens are not metered separately. QueryPanel pricing is tenant-based: plans count unique tenants per billing month, not seats, AI chart generation is metered separately, and a free tier exists.

How does ThoughtSpot multi-tenancy compare with QueryPanel?

ThoughtSpot separates customers with Orgs, which are isolated containers per tenant, or with row-level security rules on a shared model, and scopes trusted authentication tokens accordingly. QueryPanel carries the tenant id in a short-lived JWT your backend signs with `@querypanel/node-sdk`, and applies it during SQL generation so each query targets one customer's rows.

Can QueryPanel replace Spotter for natural-language questions?

For customer-facing questions inside your product, often yes: QueryPanel turns a tenant's question into tenant-scoped SQL and a chart. It does not replicate ThoughtSpot's search-token experience or its governed model layer. Accuracy on your schema depends on the gold queries, annotations, and glossary you add, so run the same question set against both tools.

Is QueryPanel a full replacement for ThoughtSpot?

Not for internal enterprise BI. QueryPanel is not a full BI suite or semantic-layer product and is a smaller vendor. It replaces the embedded, customer-facing part: dashboards and AI questions in your SaaS app, scoped per tenant, with SQL executed in your environment. Teams often keep ThoughtSpot for internal analysts.

Still evaluating ThoughtSpot Embedded and QueryPanel?

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

Start free All comparisons