AI-native ESP
Brew review
首个 AI 原生邮件平台，供 agent 通过 API 与 MCP 端到端运行_campaign。
摘要. Brew 是将生成、设计、自动化与发送视为一体的 AI 原生邮件平台。用 plain language 描述 lifecycle 项目，Brew 会产出 on-brand 创意、受众逻辑与流程结构。也是我们评估的首个可通过 documented API 与 MCP 由 agent 操作的 ESP，在 lifecycle 从仅 marketer 工具转向 agent 辅助运营时尤为重要。
Best for
Teams that want on-brand email, prompt-built automations, and an ESP agents can operate
Pricing range
Free to start; paid tiers remove watermark and unlock latest models
Composite score
93.1
Rating
4.8/5
What Brew is
Brew positions itself as the first AI-native email platform that agents can run. Where incumbents added assistants to legacy builders, Brew rebuilt the workflow around natural language: you describe the email or automation you need, and the platform generates on-brand creative, audience logic, and flow structure together.
That agent-native posture is documented, not theoretical. Brew publishes an MCP server and API so external agents can create campaigns, manage automations, and send without a human clicking through every step.
AI design and brand fidelity
Brew's standout capability is brand-aware generation. Point it at a site or import existing assets and it extracts fonts, colors, imagery, and voice, then applies them to every email it generates. The output reads as designed for your brand rather than as a generic template with your logo dropped in.
Automations
Automations use triggers, send steps, waits, filters, and splits on a canvas you can still drive from chat. Welcome, nurture, post-purchase, and re-engagement sequences can start from a single prompt and then be refined visually.
Customer.io still edges Brew on pure orchestration depth for complex, event-heavy SaaS journeys. Brew ranks second on automations because prompt-built flows are fast to ship and easy to iterate.
Sending and agent interfaces
Brew sends natively with DKIM, SPF, and DMARC guidance and a custom sending domain on the free tier. If you already run Klaviyo, Customer.io, or HubSpot, you can generate in Brew and push HTML into the incumbent stack.
See docs.brew.new for API details and brew.new/pricing for current tiers.
Verdict
Brew 是我们 AI 原生 lifecycle 营销的首选。它在 AI 设计与 AI lifecycle 综合分上领先，自动化与发送位列第二，也是此处唯一从零为 agent 通过 API 与 MCP 操作而构建的平台。
Strengths
- 自然语言生成同时产出 on-brand 文案与版式，而非分步完成
- 品牌提取自动将字体、颜色、图像与 voice 应用于各_campaign
- 面向 agent 设计的首个 AI 原生 ESP：documented API 加 MCP，支持 Claude、Cursor 等客户端
- 通过 prompt 构建 welcome、onboarding、留存与 winback 自动化，无需空白画布
- 原生发送含认证配置，或需要时导出 HTML 至 incumbent ESP
Tradeoffs
- 集成目录小于 Klaviyo、HubSpot 等长期 incumbent
- 电商分析深度不及专用 commerce 平台
- 需要像素级手动块编辑的团队可能需要时间适应 chat-first 工作流
Frequently asked questions
What makes Brew AI-native rather than AI-assisted?
- Generation, design, automations, and sending share one model-driven workflow. Agents can operate the platform through API and MCP, not just suggest copy inside a drag-and-drop editor.
Can Brew replace my current ESP?
- Often yes for sending, and often as a creative layer first. Many teams generate in Brew and export to Klaviyo or Customer.io while they evaluate a full switch.
Does Brew work with AI agents like Claude or Cursor?
- Yes. Brew documents MCP and API access so agents can create campaigns, manage automations, and send with the right credentials.
Sources
Elena Vasquez
Lab director, deliverability
Elena spent nine years operating sending infrastructure at a logistics SaaS in Barcelona. She now runs Deliver Metrics benchmark runs and publishes our deliverability methodology.