AI Data Analyst

An AI data analyst you ask in plain words.

Ask a question about your numbers and it pulls the data from your apps and spreadsheets, runs the analysis and sends back a chart and a short answer. Ask a follow-up in the same thread and it builds on what it already found.

Start free

300 free credits to start. Live in two minutes.

Marta · WhatsApp
Marta · 4:02 PM
why did repeat orders drop in september
Cicada · 4:04 PM
Repeat orders fell from 412 in August to 338 in September. Most of the drop is in the West region, where average delivery time went from 3 days to 6 after the carrier change on August 22. Other regions are flat.
IMG
Repeat orders by region · June to September
Chart · from Shopify and ShipStation
Open
Marta · 4:06 PM
is it the same for wholesale
Cicada · 4:07 PM
No. Wholesale repeat orders are steady at about 61 a month. Those go out on your own trucks, so the carrier change didn't touch them.
WhatsApp · one-to-one · the answer, the chart, then the follow-up
The short answer

What is an AI data analyst?

An AI data analyst is an agent that answers questions about a business's data the way an analyst would: finds the right source, cleans and joins the data, runs the numbers and explains what they mean. Cicada's pulls from the apps you connect and from the spreadsheets or CSVs you send it, runs the analysis in its own code sandbox, and replies with a chart and a few plain sentences in Slack, iMessage, WhatsApp or email. It keeps a dashboard sheet current on a schedule, says where each number came from, and takes follow-up questions in the same thread.

What it does

What your AI data analyst does.

01

Answers the question you asked

Ask in a sentence. It finds the data in your connected apps or the sheet you point it at and replies with the number and the reason behind it.

02

Runs the analysis properly

Joins, cleans and calculates in its own code sandbox, so a figure is computed, not estimated. It says which source each number came from.

03

Sends a chart that reads

One chart for one question, labeled, with a two-line caption. As an image in the chat, or in a sheet with the chart built in.

04

Keeps a dashboard current

A Google Sheet with your weekly metrics, refreshed on the schedule you set, and a short message when something moves outside the range you gave it.

05

Works with your files

Send a CSV, an export or a spreadsheet with thousands of rows in the chat and it works from the whole file, not the first page.

06

Takes the follow-up

"And for wholesale?" in the same thread picks up where it left off, with the same definitions, so the second answer matches the first.

Who it's for

Who hires an AI data analyst.

Founders

Answers without a data team

The questions you'd ask an analyst, answered from your own apps when you ask them.

Operations leads

The weekly metrics, on time

Orders, delivery times and returns in one sheet every Monday, with the outliers called out.

Ecommerce managers

Why the numbers moved

Sales, repeat rates and returns broken down by product, region and channel from Shopify.

Sales leaders

A pipeline you can read

Win rates, cycle length and stage conversion from HubSpot or Salesforce, by rep and by segment.

Marketing leads

Where customers came from

Signups and revenue by source from your CRM and Stripe, month on month.

Analysts

The repeat pulls, off your desk

The weekly exports and the same five charts done on a schedule, so you can work on the hard questions.

Setup

Set up in three steps.

  1. Say what the job is

    Describe the role in a sentence when you sign up, or tell the agent in the chat. It writes its own brief, which you can read and change any time.

  2. Connect the apps it needs

    One click for most apps. Each one can be Full, Ask first or Read-only, for every agent in the workspace.

  3. Link your phone, or don't

    Scan a code and it's in your iMessage or WhatsApp. Or keep it in the app, Slack and email. Hand it the first job in the same message.

Works withGoogle SheetsAirtableHubSpotSalesforceShopifyShipStationStripeQuickBooksSlackWhatsAppand 1,000+ more
Control

Nothing goes out without your yes.

Nothing goes out without your yes

Anything that can't be undone, and any message to another person, waits for your OK. Approve with a 👍 in the chat, or set a role to full autonomy once you trust it.

Read-only is a real lock

Make any app read-only and the agent can look but never change a thing. It applies to every agent in the workspace, from their next run.

Every step on the record

Each run shows what it read, what it did and what it sent, step by step, in the Activity tab. Corrections you make stick.

What it won't do.

Won't pretend

If it couldn't confirm something, it leaves it out and says so. A number without a source doesn't go in a message.

Won't go around you

It never messages anyone on your behalf unless you asked, never spends money, and never makes a judgement call about money on its own.

Won't read what isn't shared

Teammates' agents work only through the apps the workspace shares. Your inbox and your personal apps stay under your own login.

Compared

Three ways to answer a question with data

TaskExporting to a spreadsheetA BI dashboard toolAn AI data analyst
Getting the dataExport, download, pasteConnected once by someone technicalPulled from your connected apps or the file you send
Asking a new questionRebuild the pivot tableBuild a new chart, or ask whoever built the dashboardAsk in a sentence
Doing the mathFormulas you hope are rightDefined in the toolComputed in its code sandbox, with the source named
Explaining whyUp to youThe chart; the why is up to youA short answer with the reason behind the number
Follow-up questionsStart againFilter and drill inAsk in the same thread
Recurring reportsRedone every weekA dashboard you log in toA sheet refreshed on schedule, and a message when something moves
Try it

Things to ask your AI data analyst.

  1. 01

    "what were our top 10 products by margin last quarter"

    You get: A ranked list with revenue, cost and margin from Shopify and your cost sheet, and a chart.

  2. 02

    "Here's the export from our booking system. Which weekday has the most no-shows?"

    You get: The whole file read, the no-show rate by weekday, and a note on anything that skews it.

  3. 03

    "Compare win rate by rep for the last two quarters."

    You get: A table and a chart from HubSpot, the change for each rep, and the deals behind the biggest swings.

  4. 04

    "Every Monday at 9, refresh the ops dashboard and tell me if anything moved more than 10%."

    You get: The sheet updated on the minute and a short message naming what moved and by how much.

  5. 05

    "and what if we leave out the two biggest customers"

    You get: The same analysis rerun without them, with both answers side by side.

Questions

Frequently asked questions.

Where do I talk to it?

Slack, iMessage, WhatsApp, email or the web app. It answers in the thread you asked in, and in a channel or group chat it stays quiet until someone names it.

Where does it get the data?

From the apps you connect (CRM, store, billing, accounting, support desk, project tools), from spreadsheets and Airtable bases, and from any CSV or export you send it. It says where each number came from.

Can it connect to our database?

If your database has an MCP server, it can work through that. Otherwise send it an export or a CSV, or point it at the sheet your data already lands in.

How do I know the numbers are right?

It computes them in its code sandbox rather than estimating, says which source and filters it used, and leaves out any figure it couldn't confirm. Every step it took is in the Activity tab.

What won't it do?

It won't change the data in your apps unless you ask and approve it, won't send a report to anyone but you without your yes, and won't present a guess as a number. Set any app to Read-only and it can only look.

Does it build dashboards?

It keeps a Google Sheet dashboard current on the schedule you set, with the charts built in, and messages you when something moves. It doesn't replace a BI tool your team already lives in.

Can my team use it?

Yes. Everyone in your workspace gets their own agent, and shared apps like your CRM or store are connected once for the team. Add your agent to a Slack channel and anyone can name it with a question.

What does it cost?

Every workspace starts with 300 free credits. You add a card at sign-up and nothing is charged until you run low; then it's $25 for 200 credits, with no subscription. A quick reply is about 5 credits and a typical run under 20; plans start at $99 a month.

Often hired together

One teammate. The output of a team.

Works nights, remembers every decision, answers in the thread. Start free with 300 credits.

Start free