AI analytics for SaaS — MRR, churn and retention in plain English
Updated 2026-08-22
SaaS metrics live across a product database, a billing system and a CRM. An AI data analyst connects them and answers the growth and retention questions founders and operators ask every week — MRR, churn, activation, cohort retention — in plain English, with a chart and the numbers behind it.
You don't have to start with the production database. A Google Sheet connects with no read-only user and no open port, and it never counts against the free tier's one source; CSV and Excel uploads work on the 14-day Pro trial. A billing export is usually enough to get the first MRR question answered before anyone opens a firewall rule. The one thing no plan waives is your own AI provider key, and a Google Gemini key is free to create.
Sources it connects for SaaS
- Your product/application database (PostgreSQL, MySQL).
- A warehouse if you pipe events in (BigQuery, Snowflake, Redshift, Databricks).
- Exports from billing or CRM as Google Sheets, CSV or Excel.
- Cross-source questions join product usage with billing in one query.
Questions SaaS teams ask
- MRR trend and net new MRR this year
- Logo and revenue churn by plan over the last 6 months
- Activation rate: signup → first key action
- Retention by signup cohort
- Expansion revenue by segment
Metrics worth keeping on a dashboard
- MRR / ARR and net new MRR
- Gross and net revenue retention
- Activation and time-to-value
- Churn by plan and by cohort
Why it fits SaaS
Definitions matter in SaaS — "active", "churned", "activated" mean different things to different teams. An AI data analyst lets you pin those definitions once and reuses them, so your MRR and churn numbers stay consistent across everyone who asks — through later sessions and a schema refresh. One exception: on a Google Sheet, re-running the tab picker clears the definitions saved for that source. It's especially strong for analysts and dbt users who already model events.
Frequently asked questions
Yes. Point it at your dbt target schema and it recognises your fact/dimension/staging tables and uses your definitions.
Yes — clarify what activation means once and it holds that definition against the source, so the metric stays consistent through later sessions and a schema refresh. The one action that clears it is re-running a Google Sheet source's tab picker.
Related
Get your end-to-end AI business intelligence now.
Ask in plain English, pin the answer to a dashboard, export it as CSV, Excel, PDF or PowerPoint — on the free tier that whole loop runs on one database source plus Google Sheets, and the field definitions you save carry into every later session, including after a schema refresh. One exception you should hear from us rather than discover: on a Google Sheet, re-running the tab picker — even only to add a tab — clears the definitions saved for that source and reads its schema fresh. Connecting a database is the technical part: a read-only user and network access, once. If your numbers live in a spreadsheet, none of that applies: put the file in a Google Sheet and it connects on the free tier, with no read-only user and no open port. Uploading a CSV or Excel file directly is a Pro feature, and every new account gets 14 days of Pro with no card. The one thing no plan waives is your own AI provider key, and a Google Gemini key is free to create.
Every new account starts on a 14-day Pro trial with no card. After it lapses, the free tier stays free.