Quickstart

Sign up, connect your data, and ask your first question in under 5 minutes.

Get from zero to your first data-backed answer in under 5 minutes.

1. Create your account

Go to app.klairr.com/register and sign up with your email address. You’ll need to:

  • Enter your name and email
  • Create a password
  • Name your organization (this is the workspace your team will share)

Verify your email address and you’re in.

2. Connect a data source

From the Data sources page, click Add data source and choose what to connect.

For Google BigQuery:

  1. Create a service account in your Google Cloud project
  2. Grant it the BigQuery Data Viewer and BigQuery Job User roles
  3. Download the JSON key file
  4. Paste the JSON key into Klairr and select your dataset

Klairr will automatically introspect your schema — tables, columns, types, and sample values. This takes a few seconds.

Need detailed steps? See the BigQuery Setup Guide.

3. Ask your first question

Go to the Home page and type a question in plain language:

  • “What were our top 10 deals last quarter?”
  • “How many users signed up this week?”
  • “What’s our revenue by month this year?”

Klairr will:

  1. Pick the right data source
  2. Generate and execute a SQL query
  3. Return a grounded answer with the data, query, and a confidence badge

Every answer shows its work — the SQL, raw data rows, source, and confidence level. Nothing is fabricated.

4. Invite your team

Go to the Users admin page and invite teammates by email. Assign each person a role:

RoleWhat they can do
AdminEverything — manage users, data sources, AI Memory, audit
Power UserAsk questions, save reports, configure AI Memory
AnalystAsk questions, save and share reports, SQL Live Edit
MemberAsk questions, view shared reports

5. Review what Klairr has learned (optional)

Klairr studies your schema on connect and starts building AI Memory automatically — the organizational knowledge layer that maps your terminology to your data. You don’t start from a blank page; you review and refine what’s already there:

  • Entity Aliases — Klairr suggests nicknames (“acme” = company_id=‘abc123’); you confirm or override.
  • Metric Definitions — Klairr proposes definitions for terms like “revenue”; you lock in the right one for your company.
  • Data Hints — Add rules like “always exclude test data” when you spot them.

AI Memory compounds over time. The more questions get asked, the smarter the suggestions — and every refinement applies to every user, every question, going forward.

What’s next

Need help? Contact support · Start free