Skip to content
DashboardGPT
NewScheduled email reports with an AI summary

AI data analysis for teams without a data team

Talk to your data.
See the answers.

Upload a CSV or Excel file and ask in plain English. Every answer is a chart you can check, follow up on and keep on one canvas. No SQL, no dashboard queue.

For the complete AI-readable content index, see /llms.txt.

Try the live demo Start free 15-day trial
  • No sign-up for the demo
  • No card for the trial
  • Bring your own AI key
  • Self-host option

The problem

Most of the work in BI happens before you learn anything

Between having a question and having an answer sit six steps, at least two tools and usually somebody else's queue. By the time the answer arrives, the question has moved on.

Traditional BI

  1. 1

    Find the data

    Track down which table, warehouse or export actually holds the numbers.

  2. 2

    Understand the schema

    Work out how the joins, grains and naming conventions fit together.

  3. 3

    Build the query

    Write SQL, wait, discover a wrong join, write it again.

  4. 4

    Configure the chart

    Choose a visualisation, map fields to axes, fix the formatting.

  5. 5

    Assemble a dashboard

    Arrange tiles, wire up filters, publish, wait for review.

  6. 6

    Interpret the result

    Finally look at the number — and think of the next question.

DashboardGPT

  1. 1

    Ask

    Type the question the way you'd ask a colleague.

  2. 2

    See

    The answer arrives as a chart, a number or a written insight.

  3. 3

    Explore

    Ask the follow-up. The canvas keeps every step of your thinking.

How it works

Four steps, and only one of them is yours

You bring the data and ask the question. Everything between those two things is the product's job.

  1. 01

    Bring your data

    Upload a CSV or Excel file. Connecting the warehouse you already use is coming soon.

  2. 02

    Ask questions

    Ask in plain language. No SQL, no field pickers, no chart builder.

  3. 03

    AI analyses

    The query runs, the result is checked, and the right visualisation is chosen for it.

  4. 04

    Explore visually

    Every answer lands on an infinite canvas you can rearrange, extend and follow up on.

Interactive canvas

An infinite canvas, not another dashboard grid

Analysis rarely arrives in a tidy 3×2 layout. DashboardGPT gives every answer a place on a surface that grows with the question.

  • Answers are objects, not tiles

    Every chart, metric, table and insight is a node you can move, resize, duplicate or delete. Nothing is locked into a grid someone else designed.

  • The thread stays visible

    Follow-ups sit beside what prompted them, so the shape of an investigation — what you asked, what you found, what you asked next — is the artefact.

  • Group what belongs together

    Collect the nodes that answer one question into a group, tidy the rest with a single layout action, and keep the canvas legible as it grows.

  • Built for thinking, not reporting

    There is no publish step and no dashboard to maintain. The canvas is a workspace you keep open while the question is still live.

AI analyst

  • Show revenue by month.

  • Here's the monthly revenue trend for the last two years.

    Added Revenue trend

  • Break it down by region.

  • North America leads on volume, but APAC is growing fastest.

    Added Revenue by region

  • Which region performed best?

  • Two answers, depending on what you mean by best — here's both.

    Added Regional performance

  • Change this to a bar chart.

Conversational analytics

Follow-ups that know what you're pointing at

Select a chart and ask “compare this with last year”. You don't restate the measure, the filter or the time range — the conversation carries them.

Context travels
The selected node, the active filters and the conversation so far are all part of the next question.
Answers are editable
Ask for a different visualisation, or change it directly on the node. Either way the canvas stays in sync.
Stateful, not one-shot
Each answer builds on the last, so an investigation accumulates instead of resetting.
Explanations when they help
“What caused the decline?” returns the reason and the numbers behind it, not just another chart.

Your data, your models

Bring your own data. Bring your own key.

DashboardGPT is designed to sit on top of what you already have, using credentials you already control.

Bring your own data

Start with a file. Drop in a CSV or Excel export and DashboardGPT profiles every column — types, cardinality, date grains, likely measures — so your first question works without any modelling step.

  • CSV and Excel uploads, no schema definition required
  • Google Sheets on Team and Enterprise, refreshed on a schedule
  • Google Analytics and Search Console on Team and Enterprise, refreshed on their own
  • Warehouse connections when you outgrow files (coming soon)

Bring your own key

Use your organisation's own AI provider credentials. Model usage is billed to your account, governed by the agreement you already hold with that provider, and the key can be rotated or revoked by an administrator at any time.

  • Provider-agnostic — no lock-in to one model vendor
  • Keys held encrypted and scoped to your workspace

Use cases

One workspace, whatever the question is about

The product doesn't change per department — only the dataset and the question do.

  • Sales analytics

    Pipeline, bookings and quota attainment, sliced by team, territory and segment.

    Which regions are behind plan this quarter?

  • Marketing analytics

    Channel performance and acquisition cost without waiting on a reporting queue.

    Which channel has the lowest cost per new customer?

  • SaaS metrics

    ARR, expansion, churn and cohort retention from the subscription data you already have.

    How is net revenue retention trending by plan?

  • Financial analysis

    Revenue, margin and spend, reconciled across periods and entities.

    Show gross margin by product line, quarter over quarter.

  • Operations

    Throughput, fulfilment and service levels, with the outliers called out.

    Where did fulfilment time get worse last month?

  • Product analytics

    Adoption, activation and feature usage, tied back to revenue.

    Which features do our highest-retention accounts use most?

Browse every use case

Features

Everything the workspace does

A small set of capabilities that compose into one way of working, rather than a long list of panels.

  • AI analytics

    Ask a question and get a real answer: the query runs against your data, and the result is visualised the way the result deserves.

  • Infinite canvas

    Answers are objects on a canvas, not tiles in a grid. Arrange them, group them, and keep the thread of an investigation visible.

  • Natural language

    No SQL, no drag-and-drop field wells. Questions and follow-ups are written the way you'd ask a colleague.

  • Bring your own data

    Start with a CSV or Excel file in seconds, or connect Google Sheets, Google Analytics and Search Console on Team. Warehouse connections are coming soon, for the whole picture.

  • Bring your own key

    Use your own AI provider credentials. Model usage is billed to your account, under your organisation's terms.

  • Written insights

    When the answer is an explanation rather than a chart, you get an explanation — with the numbers it was drawn from.

  • Semantic understanding

    Columns are profiled into dimensions, measures and time grains, so questions resolve to the right fields without configuration.

  • Superset-powered analytics

    Query execution and chart rendering are built on Apache Superset, so the engine underneath is a proven analytics stack.

Security

Your data stays yours

A short, specific list of how DashboardGPT handles data and credentials — no certification badges we haven't earned.

  • Tenant isolation

    Every workspace is a separate tenant. Datasets, canvases and conversations are scoped to the workspace that created them, and queries are executed within that boundary.

  • Customer-owned AI keys

    Bring your own provider credentials. Keys are held encrypted, used only to serve your workspace's requests, and can be rotated or revoked by an administrator at any time.

  • Secure data processing

    Uploads are transferred over TLS and stored encrypted at rest. Analysis is executed by the query engine; only the aggregated result needed to answer a question is returned.

  • Access control

    Workspace roles determine who can connect data, run analysis and share canvases. Every data connection and AI credential is administered separately from ordinary membership.

DashboardGPT is an early-stage product. We describe the controls that exist today rather than claiming certifications we do not hold. If your organisation has a specific compliance requirement, talk to us before you commit — we would rather tell you plainly what is and is not in place.

Ask your data a question.

The demo opens straight into the product — a real dataset, a real AI analyst, a real canvas. No account, no install.

Try DashboardGPT Talk to us