Why Claude + Brevo is a powerful email stack
Brevo (the platform formerly known as Sendinblue) earned its place by being affordable, EU-based, and genuinely GDPR-friendly, the rare all-in-one that small teams can actually afford to grow into. Email, SMS, automations, and a light CRM in one account. The catch is the same one every marketer knows: the tool is ready, but the work is slow. Segments, subject lines, the campaign body, the automation logic: it all still has to be written by someone, and that someone is usually too busy.
Claude changes the economics of that work. Connected to your Brevo account, it can read who your contacts are, reason about who to talk to and why, and draft the whole thing (segments, campaigns, and automations) in the time it used to take to write one email. The one thing it shouldn't do is press send on its own. That's the line this workflow is built around: Claude does the drafting; you approve; Brevo sends.
The missing piece is somewhere for all of that to live. Drafts inside a chat window scroll away, and an agent firing campaigns straight into Brevo with no review is how you end up emailing the wrong list at the wrong time. Plainpaper is the canvas in the middle: every segment, campaign, and automation the agent produces lands as a typed card you can see, question, and approve, with the audience and the offer that shaped it attached.
What each tool does
Each of the three tools has a clear lane, and the workflow is strongest when you let them stay in it.
The workflow, end to end
Six stages, each producing a persistent artifact that feeds the next. The whole thing runs from the chat window you already use. Claude does the work and writes cards onto the board in real time.
Claude · Re-engagement
brevo · get_contacts
brevo · create_campaign
Drafted a 2-email sequence and put it on the board for review.
What you'd see: Claude calls Brevo over MCP to pull lapsed contacts, then drops the drafted sequence onto the board. Nothing is live yet.
Step by step: a campaign from brief to send
Connect Claude to Brevo and a board
Everything here runs over MCP, the open protocol that lets Claude call other tools. In your Claude client, connect two servers: your Brevo account (read contacts, draft campaigns) and a Plainpaper board. Now the same conversation can look up a segment, draft an email, and put it somewhere you can approve it.
Permissions matter. Give Claude read access to contacts and lists, and keep Brevo's send and publish actions behind your approval on the board. The agent can draft a campaign freely; it can't ship one without you.
Brief Claude like you'd brief a marketer
Skip the prompt engineering. Tell Claude what you're trying to do in plain language: the goal, the offer, the audience, the deadline. The more you'd tell a new hire, the better the first draft. Claude turns that brief into a plan on the board before it writes a single email, so you can correct the direction while it's cheap.
Goal: bring back contacts who've gone quiet. Offer: 15% off, expires in 7 days. Audience: subscribers with no open in 90 days. Put a campaign plan on the board first, then we'll draft the emails.
Segment your Brevo contacts and lists
Ask Claude to translate the brief into segments and build them from your Brevo lists and contact attributes. A good starting set: engaged subscribers, recent signups, lapsed contacts (no open in 90+ days), and customers vs. non-customers. Each one becomes an Audience card on the board, so you can see the logic and the size before anything is built on top of it.
From my Brevo contacts, define these segments and add an Audience card for each: engaged (opened in 30d), lapsed (no open 90d), recent signups, and customers. For each, note the hook, the offer, and what we should never say to them.
Draft the campaign and automation as Email cards
Now the writing. Have Claude draft the campaign and any automation that goes with it. Each email arrives as a card with subject-line variants, preview text, body, and CTA, linked back to the segment it targets and the trigger or send date. Because the lineage is visible, you can tell at a glance whether the offer fits the audience.
Draft the re-engagement sequence (2 emails: day 0, day 4). Email 1 is a warm "we miss you," email 2 carries the 15% offer with the expiry. Give me two subject lines per email, keep it friendly, and put each as an Email card linked to the campaign.
Approve on the board: the safety layer
This is the step that makes an autonomous agent safe to run on a real list. Every email sits on the canvas as a finished, sendable asset with its full lineage: the audience, the offer, the timing. Read it, tweak the copy in plain language, then approve. Only approved cards get scheduled.
The agent can draft a dozen emails in a minute. The board is where one human decides which of them are good enough to send.
Pull Brevo results back so the next campaign compounds
After a send, ask Claude to pull Brevo opens, clicks, and conversions back onto the board as Result cards. Now the next campaign doesn't start from a blank chat. It starts from "the win-back at 15% off beat the plain newsletter, do that again." Your learnings stop evaporating, and each campaign builds on the last.
The campaigns and automations to build first
If you do nothing else, build these. They have the clearest triggers, the best contact data to draw on, and the fastest payback, which makes them the perfect first job for the agent.
- Welcome automation. Fires when a contact is added to a Brevo list. Claude leads with your story and your best first offer instead of a generic "thanks for signing up," spread across two or three timed steps.
- Newsletter / broadcast. Your regular send to engaged subscribers. Claude drafts the whole issue and segments it so the offer matches the reader, rather than blasting one email to the entire list.
- Promotional / seasonal campaign. A sale, a launch, a holiday push. Claude plans the calendar, writes the build-up and reminder emails, and reuses Brevo's templates so the look stays on brand.
- Re-engagement (win-back). Fires for lapsed contacts. Claude reasons about the right incentive and a clean exit for people who never come back, which keeps your Brevo deliverability healthy.
- Transactional + birthday. Order confirmations, receipts, and a birthday email driven by Brevo contact attributes. Low effort, high open rates, and the perfect place for a quiet cross-sell.
How this compares to Brevo's AI and a plain chatbot
Brevo's own AI is good at what it does. So is asking a chatbot for a subject line. Neither replaces a stack that segments your contacts, reasons across the whole campaign, and keeps a human in the approval loop.
| Approach | What it's good at | Where it falls short |
|---|---|---|
| Plain chatbot copy/paste into Brevo | Fast first drafts of copy and ideas. | No list context, no memory between chats, every campaign starts from zero. |
| Brevo built-in AI | Subject-line suggestions and send-time help inside Brevo. | Optimises within Brevo; doesn't plan the sequence or write the whole campaign and automation. |
| Claude + Brevo + Plainpaper | Segments contacts, plans and writes the whole campaign, keeps lineage, approve before send. | You still set the strategy and approve. By design, not by limitation. |
Pitfalls to avoid
- Letting the agent send unreviewed. Keep publish actions behind board approval. An agent that drafts is an asset; an agent that ships unreviewed is a liability.
- Skipping the segment step. If Claude writes before it segments, you get one generic email for everyone. The segment is what makes the copy land.
- Ignoring consent on a re-engage. Brevo is built for GDPR. Honour it. Win-back contacts who opted out, and offer a clean unsubscribe, or you risk both compliance and deliverability.
- One giant prompt. Work stage by stage (brief, then segment, then copy) so each artifact is reviewable instead of a wall of text.
Key takeaways
- Connect Claude to Brevo (read contacts, draft campaigns) and a Plainpaper board over MCP.
- Brief Claude in plain language (goal, offer, audience) and let it plan on the board before it writes.
- Segment first; the segment is what turns a generic blast into a campaign that converts.
- Approve every campaign and automation on the board. The agent drafts; you decide what ships.
- Pull Brevo results back so each campaign compounds on the last instead of starting from a blank chat.
Frequently asked questions
Can Claude build Brevo email campaigns?
Yes. Connected over MCP, Claude can read your Brevo contacts and lists, then draft segments, email campaigns, and automations: subject lines, preview text, body, and CTAs. It produces finished, approvable drafts; a human approves them on the board before anything is scheduled or sent in Brevo.
Does this work with Brevo automations?
Yes. Automations are one of Brevo's strengths, and Claude drafts them the same way it drafts a one-off campaign (a welcome series, a re-engagement flow, a birthday email), laid out step by step as cards. You review the trigger, the timing, and the copy on the board, then approve before the automation goes live in Brevo.
Is Brevo the same as Sendinblue?
Yes. Brevo is the platform formerly known as Sendinblue; it rebranded in 2023. It is the same all-in-one tool for email, SMS, automations, and a light CRM, so this workflow applies whether you still call it Sendinblue or Brevo.
Will Claude send emails without my approval?
No. The workflow is built so the agent only ever drafts. Every campaign and automation lands on the Plainpaper board as a finished asset with its lineage (segment, offer, timing), and you approve it there. Only then does Claude schedule or push it through Brevo.
Is this better than Brevo's built-in AI?
They solve different problems. Brevo's AI helps inside Brevo with subject-line suggestions and send-time optimisation. Claude reasons across the whole campaign: it segments your contacts, plans the sequence, and writes the copy and the automation. Plainpaper keeps that reasoning visible and approvable instead of trapped in a chat window. Use both.
Do I need to know how to write prompts?
Not really. You brief Claude the way you'd brief a marketer (the goal, the offer, the audience) and steer from there. The board shows you exactly what it produced, so you correct in plain language instead of re-engineering a prompt.
Next step: give the workflow a home
You have the workflow. The piece that makes it safe and repeatable is the board in the middle, where the agent's work becomes visible, linked, and approvable. Plainpaper is free to try and connects to your Claude client over MCP in a couple of minutes. Your next Brevo campaign can start from last campaign's results instead of a blank chat.