AI email marketing automation
An AI email marketing engine that ships campaigns in hours, not weeks
An agency running email for a dozen consumer brands was limited by how fast its team could brief, write, build and QA campaigns. We built an AI engine that turns a product feed and a campaign brief into segmented, on-brand emails ready for review, and automates the lifecycle flows every brand needs.
- Client
- Marketing agency serving D2C brands
- Region
- United States
- Scale
- 30 to 60 employees
- Timeline
- 9 weeks, then rolled out brand by brand
What the client got
0x
More campaigns per brand per month
With the same team, production is no longer the limit.
0%
Less production time per campaign
From brief to review-ready in hours.
0%
Higher revenue per email
Driven by segments that were previously impractical to build.
The bottlenecks
Bottleneck 1
Campaign production was the bottleneck, not ideas
Each campaign went through brief, copy, design, build and QA across four people. Brands got two sends a week when they wanted five.
Bottleneck 2
Segmentation stopped at the basics
Deeper segments by product affinity, replenishment cycle or discount sensitivity were known to work but never built because of the effort.
Bottleneck 3
Lifecycle flows were set once and forgotten
Welcome, abandoned cart and win-back flows ran unchanged for a year while the product range moved on.
What we built
Step 1
Brand voice and product knowledge
Each brand has a profile: tone examples, banned phrases, product feed, pricing rules and compliance notes. Every generation is grounded in it.
Step 2
Campaign generation
From a short brief, the engine produces subject line variants, body copy, product blocks and segment-specific versions, assembled into the ESP template and queued for human review.
Step 3
Automated segmentation
Order data is scored nightly for replenishment timing, category affinity and discount sensitivity, creating segments the team never had time to build.
Step 4
Living lifecycle flows
Welcome, cart, browse and win-back flows refresh their product recommendations and copy automatically as the catalogue changes, with a monthly review summary.
The automation workflow
Brief to sent campaign
Segmented and on-brand, reviewed by a human
Questions clients ask about this engagement
Does the AI send without approval?
Campaigns always go through a human reviewer in the ESP. Lifecycle flows run automatically after their initial approval and are reviewed monthly.
Which email platforms are supported?
Klaviyo and Mailchimp in production. Any ESP with a template and campaign API can be connected.
More in E-Commerce & D2C
Industry overview
Customer support automation
Order status, returns and exchanges handled without a support agent
Three quarters of support tickets were about order status, returns or exchanges, and the queue doubled every sale. We automated those tickets end to end, connecting the help desk, Shopify and the carriers, and left agents with the conversations that need a person.
72%
Tickets resolved with no agent
Catalogue and content automation
Product listings for 40,000 SKUs written, translated and kept compliant by AI
A seller with 40,000 SKUs on Amazon, eBay, Otto and its own store could not keep listings complete, consistent or translated. New products took weeks to go live. We built a content pipeline that turns supplier data into optimised, marketplace-compliant listings in six languages, with humans reviewing exceptions rather than writing from scratch.
2 days
From supplier feed to live in six languages
Wholesale and retail lead generation
Taking a D2C beverage brand into 300 retail doors with outbound
A direct-to-consumer beverage brand had strong online reviews and rising ad costs. Growth needed wholesale: independent grocers, gyms, cafés and regional chains. We built an outbound engine to buyers and owners, with samples and sell-sheets handled by workflow, and the brand opened hundreds of retail doors without a field sales team.
312
Retail doors opened
Conversational commerce automation
A WhatsApp shopping agent that recovers carts and answers sizing at 2am
A fashion brand selling across India and the Gulf did most of its customer conversation on WhatsApp, with a team of eight answering sizing, delivery and exchange questions by hand. Abandoned carts were followed up with a generic blast. We built a WhatsApp agent that knows the catalogue, the customer and the order, recovers carts with a conversation, and hands off to a person when it should.
23%
Abandoned cart recovery rate
Have a similar bottleneck?
Tell us how the work happens today. We will show you the workflow we would build and prototype it on your own process.