What Supabase is and how Kite uses it
Supabase is a hosted Postgres database that many software companies run their product on. It holds your app's users and sign-in records, plus whatever tables your team has built around them, such as workspaces, plans, orders, and usage events. For a marketer, that makes Supabase the record of what happens after the signup. Your analytics shows the visit. Supabase shows whether that visitor became a user who stuck around.
An AI marketing agent uses Supabase to answer marketing questions with product data instead of estimates. Kite reads how your tables are organized, writes the queries itself, and turns the results into funnel numbers, audiences, and research on who your customers are. Then it acts on what it finds. It sends the campaign, updates its picture of your best customers, or saves a finished list into a table your team already uses. You connect your own Supabase account through OAuth.
Marketing jobs Kite can do with Supabase
Kite treats Supabase as the place where your product data lives and works from there. The jobs below start with understanding that data, move through measuring and acting on it, and end with Kite writing its own work back into your database.
Learn how your product data is organized
Kite reads the structure of your database first, so you don't have to explain your schema to it. It lists the tables and views in your project, then reads the columns, data types, and relationships in the ones that matter. From that it works out where your signups live, which column holds each account's plan, and which table records the actions that show someone is getting value from your product.
Say your app has a profiles table, a workspaces table, and an events table. Kite notices that a user's first workspace gets created a few minutes after signup and that people who create one tend to stay. It proposes that moment as your activation step and asks you to confirm it. Once you agree, Kite saves the definition to your team's knowledge base, so every later question starts from the same meaning of "activated."
Measure signups, activation, and paid conversion
Kite measures your funnel by querying your tables directly. It counts new signups by day or week, the share who reached your activation step, and how many moved to a paid plan. It can split any of those by a column you already store, such as plan, country, or the signup source your app records.
That's how a vague question gets a specific answer. You ask how last week's launch went. Kite finds 380 signups against a usual 140, but only 22 percent created a workspace, compared with 35 percent most weeks. The launch brought in plenty of people, and the onboarding lost more of them than usual. Kite points to that step and proposes a change to the welcome email or the first screen's copy.
Kite can also run the same queries on a schedule. Every Monday it can send last week's signups, activation rate, and paid conversions, to a Slack channel or by email, with the change from the week before and a short explanation of what moved.
Build campaign audiences from what people did in your product
Kite builds email audiences from product behavior rather than from a static list. It queries for the people who match a situation worth acting on, such as users who signed up in the last 60 days but never created a workspace, or accounts that were active last quarter and haven't signed in for a month. For each person it returns the name, email, plan, signup date, and the last thing they did.
Then Kite writes the campaign around where each group stopped. Trial users who never invited a teammate get a message about what the product does for a team. Users who set up a project and left get a note about the next step in that project. Kite sends the emails from your Kite team address or a connected email product once you approve them. A week later it runs the same query again to see how many people came back.
Learn which companies your best customers work at
Kite turns your customer table into research on who actually buys. It pulls the work email domains of your paying or most active users, then looks up those companies with its built-in research sources. That gives it each company's industry, headcount, location, funding, and the technology it uses.
The pattern is usually clearer than anyone expected. Kite might find that 40 percent of your paid accounts are agencies with 20 to 100 people, even though your site speaks mostly to in-house teams. It records that finding in your ideal customer profile and uses it the next time it builds a lead list or writes landing page copy.
Save lead lists and research into your own tables
Kite can write its finished work into Supabase when that's where your team keeps it. It can create a new table through a tracked migration and insert rows into it, or update rows that already exist, using SQL it writes against your schema.
For example, Kite builds a prospect list of 200 people at companies that look like your best customers. Each row carries the person's name, role, company, professional email, LinkedIn profile, a fit score from one to five, and the reason for that score. Kite saves the list to a prospects table that your internal sales dashboard already reads. It can also add a fit score to each row in your accounts table, so your team sees Kite's research next to the data they already use.
What Kite reads and changes in Supabase
Kite uses Supabase mainly as a source of product data and occasionally as a destination for its finished work. The two lists below separate what it reads from what it writes.
Information Kite can read
- ProjectsThe Supabase projects your account can reach, so Kite works in the one that holds your product data.
- Tables, views, and columnsThe structure of your database, including each column's type and the relationships between tables. Kite uses this to write accurate queries.
- RowsThe records in any table you point it at, with filters, sorting, and limits. Kite uses these for audiences and customer lists.
- Query resultsCounts, groupings, and joins across tables from SQL that Kite writes and runs as Supabase's read-only database user. These become your funnel numbers and weekly report.
Information Kite can create or change
- New tablesTables for Kite's work, such as a prospects table, created through a migration that appears in your project's migration history.
- RowsNew records Kite inserts, such as a scored lead list, and new values it writes into existing rows, such as a fit score on each account.
How Kite connects to Supabase
Connect your Supabase account through OAuth. Kite then works with the organizations and projects that account can reach. If you have more than one project, Kite lists them and asks which one holds your product data. You don't need to hand over a database password or an API key.
You can start with a plain question, like "How many of September's signups are still using the product?" Kite already knows your product and pricing from its research on your business. It reads your tables, proposes what it'll count as "still using," and brings back the number with the query behind it.
Where Supabase fits in Kite's marketing work
Supabase tells Kite what happens after a visitor converts. Your analytics shows which page produced a signup. Supabase shows whether that person set up an account and kept using it. When your app saves the signup source or landing page on the user's record, Kite can see which pages bring in people who stay, and it fixes those pages first.
Supabase supplies the product half of the weekly report. Kite reads signups, activation, and paid conversions from your tables and puts them next to traffic and campaign results from your other connected tools. That way the report covers the whole path from visit to customer rather than stopping at the form.
Supabase owns the stages between the signup and the paying customer. Kite counts signups, activation, and paid plans from your tables, using the definitions your team agreed on, and places them next to the numbers from the tools that own the earlier stages. Your team then reads the whole funnel in one place, with the product stages drawn from the record of what people actually did.
Supabase is where Kite finds the people who signed up and went quiet. It reads each user's last activity and the step where they stopped, then writes a win-back email that speaks to that step instead of a generic check-in.
Supabase is where Kite finds the action that turns a new signup into an active customer, and where it checks whether the emails work. Kite reads your tables to see which step comes before people stay, such as creating a first workspace, and plans the sequence around getting new signups to it. Once the emails are running, Kite queries the same tables to count how many of the people who received each email went on to activate and pay.
Supabase holds the product usage that shows a free or trial user is ready for a sales conversation. Kite queries your tables for the actions that came before your users moved to a paid plan, then looks for free and trial users who reach the same point. It researches the company behind each one's work email and drafts the personal email your founder sends.
Supabase shows what your paying customers did in your product before they paid. Kite queries your tables for the actions that came before each move to a paid plan, and that moment becomes the point your paywall, upgrade prompts, and trial emails are designed around.
Supabase holds the signup dates and product activity that a cohort analysis is built from. Kite queries your tables to group users by when they signed up, then compares how many in each group are still active and how many moved to a paid plan, so you can see whether recent signups stick around better or worse than earlier ones.
Supabase records what your customers did in your product before they cancelled. Kite queries your tables for the warning signs that came before past cancellations, then runs the same check against every paying customer each week to find the ones showing those signs now.
Limits and product-specific details
- Hosted Supabase projects. This page covers projects on Supabase's hosted platform that you reach by signing in to Supabase. A self-hosted Supabase install isn't part of this connection.
- Kite only knows what your tables record. Kite can split signups by source, plan, or company only when your app stores those details. When it doesn't, Kite tells you which field to start saving and what question it would answer.
Common questions
Will Kite change data in my Supabase database?
Only when the job is to save something there. Analysis and audience queries use read-only actions, including SQL that runs as Supabase's read-only database user, so they can't modify rows. Writing a lead list or a score is a separate step.
Does Kite work with a product built on Lovable or Bolt that uses Supabase?
Yes, when the app uses a Supabase project in your own Supabase account. Both tools let you connect your own Supabase project, and Kite connects to that project the same way. Lovable's built-in Cloud backend and Bolt's built-in database are run by those tools rather than in your Supabase account, so they aren't part of this connection. Kite reads whatever tables the app created, so it doesn't matter which tool generated them.