AI-powered embedded analytics for SaaS

answers, not dashboards.

Let your customers ask about their data and get charts back, right inside your product. QueryPanel turns plain-English questions into tenant-safe SQL and live charts on the database you already run.

  1. 01Ask
  2. 02Get charts
  3. 03Ship answers

Tenant-safe by design · parameterized SQL · SDK, React embed, and MCP.

QueryPanel / showreel ’260:30

In production with

Seon logoBrandPresence logoTojásfertőtlenítés logo

01 · The problem

they don't want

dashboards.

they want answers.

Your customers have a question, like “which accounts churned last month?” They don't want another dashboard tour. Answering it in-house means a whole stack beneath the chart, for work that isn't your core product.

The DIY stack

  • 1Database
  • 2Custom API layer
  • 3Auth + permissions
  • 4Query engine
  • 5Chart library
  • 6Dashboard builder
  • 7Customer UI
  • 8Ongoing maintenance

Weeks to quarters of glue work, and little of it moves your differentiation forward.

With QueryPanel

  1. 1npm install @querypanel/node-sdk
  2. 2Connect your database
  3. Answers and charts inside your product

Ship analytics in days. Stay focused on what only you can build.

02 · Models × data

any model. any warehouse. one panel.

Bring the LLM you trust and the database you already run. QueryPanel grounds every question in your schema, scopes it to the right tenant, and hands back a chart. No data copied, no warehouse migration.

AI models

QueryPanel

OpenAI
Gemini
Soon
Anthropic
Soon
Mistral
PostgreSQL
ClickHouse
BigQuery
MySQL
Soon
Snowflake
Data sources

ask. → get charts.

03 · Live demo · no signup

charts your customers ask for.

This is the real embed running inside a mock ACME app. Ask a question and watch the answer land.

Ship this inside your product
app.acme.com/analytics
AnalyticsQueryPanel embedded

Live QuerypanelEmbedded inside a mock ACME app.

04 · Placement

your product shell. our panel.

Your navigation and main surface stay yours. QueryPanel renders as a dedicated panel: tenant-scoped, continuous with your UI, and free of a separate BI login.

  • 01Same session, same productNo context switch to another analytics tab.
  • 02Tenant-scoped by designIsolation travels with the request. It is not a filter you can forget.
  • 03Schema-aware over timeGeneration adapts as your model evolves, with less re-teaching.
app.yourproduct.comYour UI
Dashboard
Q2
Your UI
embeddedQueryPanel surface
tenant-scoped
Revenue by region · embedded panel

05 · Authoring

build it once. customers make it theirs.

Charts are blocks in a Notion-like editor, easy to review, rearrange, and ship. Publish a starting point, then let each tenant fork their own version without rebuilding UI surfaces.

/Customer analytics
Activation
A dashboard is a document. Charts are blocks. Your team ships updates without rebuilding a UI surface from scratch.
KPI row: Active accounts, expansion, churn
Chart blockembedded
Notes: tenant-scoped by default. Share internally before deploying to customers.

06 · How it works

question in. chart out.

Natural language, grounded schema context, executable SQL, visualization, and an embedded surface, choreographed into one path your team can ship.

01

User asks in plain language

Your customer phrases the question. No SQL literacy required.

02

AI reads your schema

Grounded in real tables and relationships, not generic guesses.

03

Parameterized SQL

Tenant-aware filters and explicit parameters before execution.

04

Chart that matches the question

Visualization chosen for the intent, not a random default.

05

Live embedded dashboard

Shipped inside your app, beside the workflow that matters.

07 · For developers

one install. first answer.

Call qp.ask() from your backend and get SQL, rows, and a chart spec back. Render it yourself, or drop in our React workspace.

$npm install @querypanel/node-sdk
const qp = new QueryPanelSdkAPI(...);
const result = await qp.ask("Revenue by month?");
// result.sql, result.rows, result.chart
  • Headless SDK

    Generate SQL and charts from your backend. Render with your UI or ours. Control stays in your stack.

  • Dashboard workspace

    Drop-in, white-label React components: dashboards, exploration, and saved views inside your app tree.

  • MCP for internal AI

    Connect governed MCP workflows so your own AI tools query data through the same tenant-safe path.

Read the Node SDK docs
QueryPanel / node-sdk onboarding0:45
QueryPanel / semantic layer0:50

08 · Semantic layer

define your words.

Your customers say “active customer”. Your schema says last_paid_at. The semantic layer teaches the model the difference, so answers match your business instead of a guess.

how many active customers by plan?

Glossary · term

Active customer

Paid at least one invoice in the last 90 days.

WHERE last_paid_at >= now() - interval '90 days'

  • Glossary. Define “active customer” or “revenue” once, in business words.
  • Column notes. Explain units, enums, and joins: “amount is in cents”, “revenue means paid only”.
  • Every tenant, same truth. Definitions ground every question, for every customer.
How the semantic layer works

09 · Trust

your data stays yours.

Built for production-minded teams: QueryPanel generates the query, your infrastructure runs it, and tenant boundaries hold at every step.

  • Data stays in your infrastructure

    We generate SQL. You execute it where you already run queries.

  • Multi-tenant isolation by default

    Tenant context is enforced during generation, not bolted on after.

  • JWT claims verified server-side

    Embed tokens are signed by your backend and checked on every call.

  • Parameterized execution path

    Generated queries bind values as parameters, not concatenated strings.

  • Schema metadata for grounding

    Table structure and your own notes ground every generated query.

  • One API for admin and tenants

    The same request shape everywhere, so there is no forked behavior to audit.

Works with your data stack

Connect to existing databases. No wholesale migration required.

  • PostgreSQL
  • ClickHouse
  • BigQuery
  • MySQL
  • SnowflakeSoon

Zero credential storage in code. Secrets live in a vault.

10 · Full walkthrough

the whole loop, end to end.

Natural language to grounded SQL, visualization, and an embedded surface your customers can actually use, in one continuous demo.

Open on YouTube

Alternatives

QueryPanel vs embedded analytics alternatives

Embedded analytics for SaaSAI-powered embedded analyticsEmbedded analytics tools2026 buyer guideTenant isolation
View full comparison

Pricing · AI analytics infrastructure for SaaS

pay as your customers grow.

Analytics infrastructure is complex. QueryPanel provides AI-powered dashboards out of the box. Our pricing scales simply with your tenant usage, so you only pay as your customer base grows. Starter and above include MCP support for governed internal analytics workflows.

Free

$0/mo

Experimentation

Core Usage
Tenants3
AI Charts50 / mo
AI Models
MCP
Bring your own key
Bring your own model
Platform Limits
Dashboards1
Data Sources1
Workspaces1
Editors1
Viewers0

Starter

$49/mo

Small teams shipping first analytics features.

Core Usage
Tenants10
AI Charts200 / mo
AI Models
MCP
Bring your own key
Bring your own model
Platform Limits
Dashboards5
Data Sources2
Workspaces2
Editors3
Viewers5

Growth

$249/mo

Early SaaS delivering analytics to real customers.

Core Usage
Tenants100
AI Charts1,000 / mo
AI Models
MCP
Bring your own key
Bring your own model
Platform Limits
Dashboards50
Data Sources5
Workspaces5
Editors10
Viewers25
Scale

Scale

$999/mo

SaaS platforms where analytics is a core product feature.

Core Usage
Tenants1,000
AI Charts5,000 / mo
AI Models
MCP
Bring your own key
Bring your own model
Platform Limits
DashboardsUnlimited
Data SourcesUnlimited
WorkspacesUnlimited
EditorsUnlimited
ViewersUnlimited

Enterprise

Custom

Unlimited scale and dedicated infrastructure.

Core Usage
TenantsUnlimited
AI ChartsCustom
AI Models
MCP
Bring your own key
Bring your own model
Platform Limits
DashboardsUnlimited
Data SourcesUnlimited
WorkspacesUnlimited
EditorsUnlimited
ViewersUnlimited

How Pricing Works

Platform Plans: Choose a base plan that fits your scale. Each plan includes a set number of tenants, AI chart credits, and platform features.

Included AI Credits: Every plan comes with a monthly allowance of AI chart generations.

Model Flexibility: Bring-your-own-key is included from Starter and above (Growth and Scale included). Custom plans also support bring-your-own-model deployments.

Optional Overage: If you exceed your AI chart limits, you can easily purchase additional usage credits without needing to upgrade your entire platform plan immediately.

MCP Workflows: Starter and above include MCP analytics workflows for admin-first AI tooling and governed internal automation.

Build vs. Buy

Building Internally

  • • Months of engineering
  • • Ongoing maintenance
  • • AI infrastructure complexity
  • • Multi-tenant challenges

Using QueryPanel

  • • Deploy analytics in hours
  • • Built-in tenant isolation
  • • AI chart generation
  • • MCP-ready admin workflows
  • • Scalable infrastructure

The Power of Tenant Dashboard Forking

QueryPanel allows you to create one dashboard template and automatically generate tenant-specific versions. Each tenant can customize their dashboards without affecting others.

Base Dashboard
Tenant A Version
Tenant B Version
Tenant C Version
No engineering work No dashboard duplication Automatic isolation

Compare Plans

FeaturesFreeStarterGrowthScaleEnterprise
AI Chart Generation
Embedded Dashboards
White-label Analytics
RBAC Permissions
Audit Logs
Dashboard Forks
MCP Analytics Workflows
Bring Your Own Key
Bring Your Own Model
SSO / SAML
Dedicated Infrastructure
SLA

FAQ

questions, answered.

Product, security, and pricing. Straight answers before you reshuffle the roadmap.

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

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

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

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.

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.

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.

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.

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.

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

answers, not dashboards.

Stop paying roadmap interest on DIY analytics. Let your customers ask about their data and get charts back inside your product.