mirror of
https://github.com/supabase/supabase.git
synced 2026-10-05 09:25:06 +03:00
Fixed a few typos in the text (#43434)
## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Just clarified that the prize is an iPhone 17 Pro Max and the dinner is on a Wednesday, not a Tuesday.
This commit is contained in:
Prashant Sridharan authored and GitHub committed
1 parent
a052dd7409
commit
ef6e44bc24
7 files changed
+101
-54
No files matched your search
@@ -28,7 +28,10 @@ region: 'Europe'
|
||||
supabase_products: ['database']
|
||||
---
|
||||
|
||||
<Quote img="alexandre-le-goupil-brevo.jpeg" caption="Alexandre Le Goupil, Revenue Systems and AI, Brevo">
|
||||
<Quote
|
||||
img="alexandre-le-goupil-brevo.jpeg"
|
||||
caption="Alexandre Le Goupil, Revenue Systems and AI, Brevo"
|
||||
>
|
||||
Our AI agents are only as good as the data they can reach. Supabase gave them access to our entire
|
||||
CRM, stored what they produced, and never got in the way. It is the quiet part of our stack that
|
||||
makes everything else work.
|
||||
@@ -44,10 +47,13 @@ All of that intelligence sits in the CRM. Contacts, Deals, Companies. Years of a
|
||||
|
||||
Alexandre Le Goupil runs Revenue Systems and AI for Brevo's sales team. His group had adopted **[Dust](https://dust.tt), an AI agent platform**, and the agents were already good at research, reasoning, and writing. But the CRM was completely out of reach, and that data was what would make the agents' output truly actionable.
|
||||
|
||||
<Quote img="alexandre-le-goupil-brevo.jpeg" caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo">
|
||||
Salespeople would come to me and ask for a list of our best e-commerce customers before a call. Or they
|
||||
would need to know if we had history with a prospect's company. That context was all in the CRM,
|
||||
but our AI agents were completely blind to it. I needed to connect those two worlds.
|
||||
<Quote
|
||||
img="alexandre-le-goupil-brevo.jpeg"
|
||||
caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo"
|
||||
>
|
||||
Salespeople would come to me and ask for a list of our best e-commerce customers before a call. Or
|
||||
they would need to know if we had history with a prospect's company. That context was all in the
|
||||
CRM, but our AI agents were completely blind to it. I needed to connect those two worlds.
|
||||
</Quote>
|
||||
|
||||
Other teams at Brevo ran their analytics on BigQuery, Snowflake, and Databricks. None of those were built for what Alexandre needed: a database that AI agents could read from and write to in real time, through a standard protocol, without a custom integration for every workflow.
|
||||
@@ -56,7 +62,10 @@ Other teams at Brevo ran their analytics on BigQuery, Snowflake, and Databricks.
|
||||
|
||||
Alexandre found his answer in the [Supabase MCP server](/docs/guides/getting-started/mcp). MCP (Model Context Protocol) gives AI agents a structured way to interact with databases. Supabase ships one out of the box. That meant a direct connection between Dust's AI agents and a Postgres database, with read and write permissions controlled at the tool level.
|
||||
|
||||
<Quote img="https://github.com/LeandreLeBizec.png" caption="Léandre Le Bizec, Dust engineering team">
|
||||
<Quote
|
||||
img="https://github.com/LeandreLeBizec.png"
|
||||
caption="Léandre Le Bizec, Dust engineering team"
|
||||
>
|
||||
Supabase shipping a remote MCP server means any Dust agent can connect to it instantly, with read
|
||||
and write access, no custom integration needed. That is exactly the model we want to see from data
|
||||
platforms: natively agent-ready, so teams can focus on building workflows instead of plumbing.
|
||||
@@ -64,20 +73,26 @@ Alexandre found his answer in the [Supabase MCP server](/docs/guides/getting-sta
|
||||
|
||||
According to Dust's engineering team, Supabase was the first data platform where they enabled both read and write capabilities through natural language. Snowflake has since followed with its own MCP, and Databricks is next. But Supabase got there first, and for teams like Alexandre's that need to iterate fast with AI, that head start mattered.
|
||||
|
||||
<Quote img="alexandre-le-goupil-brevo.jpeg" caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo">
|
||||
BigQuery and Snowflake are great for analytics. But I needed something an AI agent could query live,
|
||||
in the middle of a conversation. Supabase gave me Postgres with an MCP server ready to go. That was
|
||||
what decided it.
|
||||
<Quote
|
||||
img="alexandre-le-goupil-brevo.jpeg"
|
||||
caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo"
|
||||
>
|
||||
BigQuery and Snowflake are great for analytics. But I needed something an AI agent could query
|
||||
live, in the middle of a conversation. Supabase gave me Postgres with an MCP server ready to go.
|
||||
That was what decided it.
|
||||
</Quote>
|
||||
|
||||
Brevo actually started with a custom MCP connection before Dust launched its official Supabase integration in June 2025. When the official version shipped, they migrated. The fact that they went from a scrappy custom setup to the supported integration says something about commitment: this was not an experiment.
|
||||
|
||||
The team is Revenue Operations, not database engineering. Speed mattered. Alexandre connected Supabase to Dust in days. He defined his tables, wrote descriptions of every field so the LLM would know what each one meant, and started testing.
|
||||
|
||||
<Quote img="alexandre-le-goupil-brevo.jpeg" caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo">
|
||||
<Quote
|
||||
img="alexandre-le-goupil-brevo.jpeg"
|
||||
caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo"
|
||||
>
|
||||
Connecting Supabase was the easy part. The real work was writing good documentation for the AI,
|
||||
telling it what each field means, which tables to query for which questions. Once we got that right,
|
||||
everything clicked.
|
||||
telling it what each field means, which tables to query for which questions. Once we got that
|
||||
right, everything clicked.
|
||||
</Quote>
|
||||
|
||||
The Supabase MCP was well-documented and stable, and the integration was live on the platform level within minutes. Alexandre's investment in that documentation is what separates a good Dust agent from a great one.
|
||||
@@ -90,7 +105,10 @@ Brevo's sales reps now ask a Dust agent: "Find me the top three e-commerce custo
|
||||
|
||||
Before, that request went to RevOps. Someone would pull a report, filter it, and send it back. Fifteen minutes per request, minimum.
|
||||
|
||||
<Quote img="alexandre-le-goupil-brevo.jpeg" caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo">
|
||||
<Quote
|
||||
img="alexandre-le-goupil-brevo.jpeg"
|
||||
caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo"
|
||||
>
|
||||
That workflow alone changed how reps prepare for calls. They get reference customers, account
|
||||
context, and a suggested angle in seconds. It freed up hours of my team's time every week.
|
||||
</Quote>
|
||||
@@ -103,7 +121,10 @@ The agent also grabs context from the web. LinkedIn profiles, firmographic data,
|
||||
|
||||
The emails come back as structured JSON and HTML. Dust writes them directly to Supabase. Brevo's CRM then pulls those emails into multi-channel sales sequences: email, phone, LinkedIn.
|
||||
|
||||
<Quote img="alexandre-le-goupil-brevo.jpeg" caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo">
|
||||
<Quote
|
||||
img="alexandre-le-goupil-brevo.jpeg"
|
||||
caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo"
|
||||
>
|
||||
We used to send the same generic email to every e-commerce prospect. Now every email reflects who
|
||||
this person is and what we know about them. Supabase holds the context going in and stores the
|
||||
output coming out. It is the connective tissue between our CRM and our AI.
|
||||
@@ -117,7 +138,10 @@ The team also built anti-hallucination guardrails into their prompts. A sales em
|
||||
|
||||
Brevo's marketing team uses the same architecture for lead generation. A visitor enters their email and company name on a [landing page](https://www.brevo.com/tools/relationship-plan?utm_medium=web-external&utm_source=CTA_dust_blog&utm_campaign=en_supabase_blog_202602). The data goes into Supabase and triggers a Dust agent that generates a complete marketing plan for that company: channel recommendations, campaign ideas, timelines. The output lands back in Supabase and renders as a unique page for that visitor.
|
||||
|
||||
<Quote img="alexandre-le-goupil-brevo.jpeg" caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo">
|
||||
<Quote
|
||||
img="alexandre-le-goupil-brevo.jpeg"
|
||||
caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo"
|
||||
>
|
||||
Someone fills out a form and gets a [custom marketing
|
||||
plan](https://www.brevo.com/tools/relationship-plan?utm_medium=web-external&utm_source=CTA_dust_blog&utm_campaign=en_supabase_blog_202602)
|
||||
in seconds. Data goes into Supabase, the AI builds the plan, the result comes back through
|
||||
@@ -130,16 +154,22 @@ The part of this story that stands out most is what happened after launch. Nothi
|
||||
|
||||
Alexandre's team connected Supabase, documented their schema, tested the workflows, and moved on. They have not had to troubleshoot, reconfigure, or debug the connection since.
|
||||
|
||||
<Quote img="alexandre-le-goupil-brevo.jpeg" caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo">
|
||||
We set it up, it worked, and we have not gone back. It just runs. That is exactly what you want from
|
||||
infrastructure when you are a small ops team trying to ship fast.
|
||||
<Quote
|
||||
img="alexandre-le-goupil-brevo.jpeg"
|
||||
caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo"
|
||||
>
|
||||
We set it up, it worked, and we have not gone back. It just runs. That is exactly what you want
|
||||
from infrastructure when you are a small ops team trying to ship fast.
|
||||
</Quote>
|
||||
|
||||
Dust's data backs this up. Since the official integration launched in June 2025, Brevo has executed over 2,500 actions through the Supabase MCP. That includes parallel batch runs where dozens of AI conversations query and write to the database at the same time.
|
||||
|
||||
<Quote img="https://github.com/LeandreLeBizec.png" caption="Léandre Le Bizec, Dust engineering team">
|
||||
Brevo runs parallel batch conversations making Supabase queries, and it works smoothly. The MCP has
|
||||
been rock-solid since deployment with no incidents.
|
||||
<Quote
|
||||
img="https://github.com/LeandreLeBizec.png"
|
||||
caption="Léandre Le Bizec, Dust engineering team"
|
||||
>
|
||||
Brevo runs parallel batch conversations making Supabase queries, and it works smoothly. The MCP
|
||||
has been rock-solid since deployment with no incidents.
|
||||
</Quote>
|
||||
|
||||
Because Supabase is Postgres under the hood, extending it is simple. A new use case means a new table and an updated agent prompt. No re-architecture, no new integrations.
|
||||
@@ -150,7 +180,10 @@ Brevo's Revenue Operations team is not an engineering team. They do not write ba
|
||||
|
||||
This is the pattern Supabase sees across enterprise innovation teams: when you give non-engineering builders a production-grade backend with AI-native tooling, they stop waiting and start shipping.
|
||||
|
||||
<Quote img="https://github.com/LeandreLeBizec.png" caption="Léandre Le Bizec, Dust engineering team">
|
||||
<Quote
|
||||
img="https://github.com/LeandreLeBizec.png"
|
||||
caption="Léandre Le Bizec, Dust engineering team"
|
||||
>
|
||||
What makes Supabase particularly exciting is its agility. It is lighter and faster to iterate with
|
||||
than traditional data platforms. For AI use cases, this speed matters: storing agent outputs,
|
||||
syncing workflows, generating content that feeds directly into production systems. It is perfectly
|
||||
@@ -161,7 +194,10 @@ This is the pattern Supabase sees across enterprise innovation teams: when you g
|
||||
|
||||
Dust's engineering team points to three things that make Supabase work for agents. The remote MCP server is production-grade and easy to onboard. Read and write access closes the agentic loop, so agents produce durable outputs, not just answers. And non-technical teams own the entire data layer themselves, no engineering bottleneck. For agentic use cases where iteration speed is the advantage, that is a structural edge.
|
||||
|
||||
<Quote img="https://github.com/LeandreLeBizec.png" caption="Léandre Le Bizec, Dust engineering team">
|
||||
<Quote
|
||||
img="https://github.com/LeandreLeBizec.png"
|
||||
caption="Léandre Le Bizec, Dust engineering team"
|
||||
>
|
||||
What teams like Brevo's gain is not just speed, it is focus. When agents handle the data pulling,
|
||||
the personalization, the logging, the people can spend their time where it actually matters:
|
||||
strategy, relationships, decisions. That is the version of AI we are building toward.
|
||||
@@ -173,7 +209,10 @@ Alexandre estimates that 30% or more of the internal support requests his team f
|
||||
|
||||
They are also scaling the email generation workflow to handle thousands of prospects in a single batch run.
|
||||
|
||||
<Quote img="alexandre-le-goupil-brevo.jpeg" caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo">
|
||||
<Quote
|
||||
img="alexandre-le-goupil-brevo.jpeg"
|
||||
caption="Alexandre Le Goupil, Head of Revenue Systems and AI, Brevo"
|
||||
>
|
||||
We started with one use case. Now we have three in production and more on the way. Every time we
|
||||
have a new idea, the first question is: what table do we need in Supabase? That is how fast we can
|
||||
move now.
|
||||
|
||||
@@ -47,11 +47,11 @@ Marketing is fragmented. Every platform — Meta, Google, Shopify, ESPs — has
|
||||
Without a unified action system and data layer, problems go unnoticed. A broken campaign. A budget overspend. A drop in conversions that nobody catches for weeks.
|
||||
|
||||
<Quote img="elliot-fleck-hyper.jpeg" caption="Elliot Fleck, Co-founder, Hyper">
|
||||
Whether you're a first-time founder or an agency managing hundreds of accounts, your data is spread
|
||||
across every platform — and no one knows if something is broken until weeks later. Agents on Hyper
|
||||
consolidate all of it and catch problems immediately, like an expert watching everything 24/7. AI is
|
||||
changing how work gets done — people want to say 'launch this' and 'run analysis and email me the
|
||||
report,' not do it themselves.
|
||||
Whether you're a first-time founder or an agency managing hundreds of accounts, your data is
|
||||
spread across every platform — and no one knows if something is broken until weeks later. Agents
|
||||
on Hyper consolidate all of it and catch problems immediately, like an expert watching everything
|
||||
24/7. AI is changing how work gets done — people want to say 'launch this' and 'run analysis and
|
||||
email me the report,' not do it themselves.
|
||||
</Quote>
|
||||
|
||||
## Why they chose Supabase
|
||||
@@ -70,9 +70,9 @@ Beyond the database, Supabase gives Hyper a full platform to grow into. Auth, Re
|
||||
|
||||
<Quote img="elliot-fleck-hyper.jpeg" caption="Elliot Fleck, Co-founder, Hyper">
|
||||
It's clear what Supabase is building for. They're building databases and features in the age of
|
||||
super intelligence. Fantastic community, amazing developer documentation. If you're a startup looking
|
||||
to build the next unicorn or just a lifestyle business, it's the easiest way to get started and
|
||||
scale.
|
||||
super intelligence. Fantastic community, amazing developer documentation. If you're a startup
|
||||
looking to build the next unicorn or just a lifestyle business, it's the easiest way to get
|
||||
started and scale.
|
||||
</Quote>
|
||||
|
||||
## The solution
|
||||
@@ -127,9 +127,10 @@ Supabase for Platforms handles the backend infrastructure: per-customer database
|
||||
The vision goes further. If marketing agencies can spin up websites for their end clients through Hyper, all powered by Supabase for Platforms, that opens an entirely new competitive front.
|
||||
|
||||
<Quote img="elliot-fleck-hyper.jpeg" caption="Elliot Fleck, Co-founder, Hyper">
|
||||
With Supabase for Platforms, anyone can come into Hyper and launch a marketing agency from scratch.
|
||||
Build a website, set up authentication and contact forms, create a funnel. In under 15 minutes you
|
||||
have a live agency with AI agents that intake clients and run their marketing end to end.
|
||||
With Supabase for Platforms, anyone can come into Hyper and launch a marketing agency from
|
||||
scratch. Build a website, set up authentication and contact forms, create a funnel. In under 15
|
||||
minutes you have a live agency with AI agents that intake clients and run their marketing end to
|
||||
end.
|
||||
</Quote>
|
||||
|
||||
That is what happens when you give a product team a platform that handles databases, auth, storage, and real-time out of the box. They stop building infrastructure and start building the thing they set out to build.
|
||||
|
||||
@@ -6,18 +6,19 @@ const page: GoPageInput = {
|
||||
template: 'lead-gen',
|
||||
slug: 'accenture-reinvention-2026/contest',
|
||||
metadata: {
|
||||
title: 'Win an iPhone Pro Max | Supabase at Accenture AI & Data Conference (ReinventionX) 2026',
|
||||
title:
|
||||
'Win an iPhone 17 Pro Max | Supabase at Accenture AI & Data Conference (ReinventionX) 2026',
|
||||
description:
|
||||
'Create a Supabase account and load data for a chance to win an iPhone Pro Max. Accenture AI & Data Conference (ReinventionX) 2026.',
|
||||
'Create a Supabase account and load data for a chance to win an iPhone 17 Pro Max. Accenture AI & Data Conference (ReinventionX) 2026.',
|
||||
},
|
||||
hero: {
|
||||
title: 'Win an iPhone Pro Max',
|
||||
title: 'Win an iPhone 17 Pro Max',
|
||||
subtitle: 'Supabase at Accenture AI & Data Conference 2026',
|
||||
description:
|
||||
'Your team is already building with AI tools. Supabase is the production backend that turns those prototypes into secure, scalable applications. Try it out -- create an account, load some data, and you could win an iPhone Pro Max.',
|
||||
'Your team is already building with AI tools. Supabase is the production backend that turns those prototypes into secure, scalable applications. Try it out -- create an account, load some data, and you could win an iPhone 17 Pro Max.',
|
||||
image: {
|
||||
src: '/images/landing-pages/stripe-sessions/iphone17-pro-max.png',
|
||||
alt: 'iPhone Pro Max',
|
||||
alt: 'Orange iPhone 17 Pro Max',
|
||||
width: 400,
|
||||
height: 500,
|
||||
},
|
||||
|
||||
@@ -6,18 +6,18 @@ const page: GoPageInput = {
|
||||
template: 'lead-gen',
|
||||
slug: 'postgresconf-sjc-2026/contest',
|
||||
metadata: {
|
||||
title: 'Win an iPhone Pro Max | Supabase at PostgresConf San Jose 2026',
|
||||
title: 'Win an iPhone 17 Pro Max | Supabase at PostgresConf San Jose 2026',
|
||||
description:
|
||||
'Sign up for Supabase and enter the contest for a chance to win an iPhone Pro Max. PostgresConf San Jose 2026.',
|
||||
'Sign up for Supabase and enter the contest for a chance to win an iPhone 17 Pro Max. PostgresConf San Jose 2026.',
|
||||
},
|
||||
hero: {
|
||||
title: 'Win an iPhone Pro Max',
|
||||
title: 'Win an iPhone 17 Pro Max',
|
||||
subtitle: 'Supabase at PostgresConf San Jose 2026',
|
||||
description:
|
||||
'Supabase is Postgres with batteries included -- auth, storage, edge functions, vectors, and real-time, all built on top of the database you already know. Sign up, load some data, and enter below for a chance to win an iPhone Pro Max.',
|
||||
'Supabase is Postgres with batteries included -- auth, storage, edge functions, vectors, and real-time, all built on top of the database you already know. Sign up, load some data, and enter below for a chance to win an iPhone 17 Pro Max.',
|
||||
image: {
|
||||
src: '/images/landing-pages/stripe-sessions/iphone17-pro-max.png',
|
||||
alt: 'iPhone Pro Max',
|
||||
alt: 'Orange iPhone 17 Pro Max',
|
||||
width: 400,
|
||||
height: 500,
|
||||
},
|
||||
|
||||
@@ -6,18 +6,18 @@ const page: GoPageInput = {
|
||||
template: 'lead-gen',
|
||||
slug: 'startup-grind-2026/contest',
|
||||
metadata: {
|
||||
title: 'Win an iPhone Pro Max | Supabase at Startup Grind 2026',
|
||||
title: 'Win an iPhone 17 Pro Max | Supabase at Startup Grind 2026',
|
||||
description:
|
||||
'Create a Supabase account and load data for a chance to win an iPhone Pro Max. Startup Grind 2026.',
|
||||
'Create a Supabase account and load data for a chance to win an iPhone 17 Pro Max. Startup Grind 2026.',
|
||||
},
|
||||
hero: {
|
||||
title: 'Win an iPhone Pro Max',
|
||||
title: 'Win an iPhone 17 Pro Max',
|
||||
subtitle: 'Supabase at Startup Grind 2026',
|
||||
description:
|
||||
'Great meeting you at Startup Grind. Supabase gives you Postgres with auth, storage, edge functions, and real-time -- everything you need to ship your product faster. Try it out and you could win an iPhone Pro Max.',
|
||||
'Great meeting you at Startup Grind. Supabase gives you Postgres with auth, storage, edge functions, and real-time -- everything you need to ship your product faster. Try it out and you could win an iPhone 17 Pro Max.',
|
||||
image: {
|
||||
src: '/images/landing-pages/stripe-sessions/iphone17-pro-max.png',
|
||||
alt: 'iPhone Pro Max',
|
||||
alt: 'Orange iPhone 17 Pro Max',
|
||||
width: 400,
|
||||
height: 500,
|
||||
},
|
||||
@@ -37,7 +37,10 @@ const page: GoPageInput = {
|
||||
children: (
|
||||
<div className="flex flex-col items-center gap-6">
|
||||
<ol className="flex flex-col gap-4 text-foreground-light text-lg list-decimal list-inside">
|
||||
<li>Create a Supabase account with the same email where you got our post-event note</li>
|
||||
<li>
|
||||
Create a Supabase account with the same email address where you got our post-event
|
||||
note
|
||||
</li>
|
||||
<li>Load data into a Supabase database</li>
|
||||
<li>Complete these steps by Monday, May 11, 2026 at 12:00 PM PST</li>
|
||||
</ol>
|
||||
|
||||
@@ -37,7 +37,10 @@ const page: GoPageInput = {
|
||||
children: (
|
||||
<div className="flex flex-col items-center gap-6">
|
||||
<ol className="flex flex-col gap-4 text-foreground-light text-lg list-decimal list-inside">
|
||||
<li>Create a Supabase account with the same email where you got our post-event note</li>
|
||||
<li>
|
||||
Create a Supabase account with the same email address where you got our post-event
|
||||
note
|
||||
</li>
|
||||
<li>Load data into a Supabase database</li>
|
||||
<li>Complete these steps by Monday, May 11, 2026 at 12:00 PM PST</li>
|
||||
</ol>
|
||||
|
||||
@@ -29,7 +29,7 @@ const page: GoPageInput = {
|
||||
<div className="flex flex-col items-center gap-2 text-foreground-light">
|
||||
<p className="text-lg font-medium text-foreground">Spruce Restaurant</p>
|
||||
<p>3640 Sacramento St, San Francisco, CA</p>
|
||||
<p className="mt-4 text-lg font-medium text-foreground">Tuesday, April 29, 2026</p>
|
||||
<p className="mt-4 text-lg font-medium text-foreground">Wednesday, April 29, 2026</p>
|
||||
<p>6:30 PM -- Cocktails and introductions</p>
|
||||
<p>7:00 PM -- Dinner and discussion</p>
|
||||
</div>
|
||||
|
||||
Reference in new issue
Block a user