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:
- Create a service account in your Google Cloud project
- Grant it the BigQuery Data Viewer and BigQuery Job User roles
- Download the JSON key file
- 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 English:
- “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:
- Pick the right data source
- Generate and execute a query against it
- Return a grounded answer with the data, the analysis trace, and a confidence badge
Every answer shows its work — the analysis steps, the raw data rows, the source, and the 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:
| Role | What they can do |
|---|---|
| Admin | Everything — manage users, data sources, AI Memory, audit |
| Power User | Ask questions, save reports, configure AI Memory |
| Analyst | Ask questions, save and share reports, Query Live Edit |
| Member | Ask 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
- Ask Your First Question — detailed guide to understanding answers
- BigQuery Setup — full setup walkthrough
- AI Memory Overview — configure organizational knowledge
- Roles & Permissions — understand access control