How is this different from an automation tool like Klaviyo flows or Zapier?

A flow runs the branch you drew for it. If a buyer replies with something you did not anticipate, the flow has nothing to say. An AI employee reads the situation, decides whether to act, chooses the channel and offer within your policy, and escalates when the right answer is outside its authority.

What stops an AI employee from discounting away my margin?

Guardrails are set before anyone starts work — discount ceilings, tone, which products can be offered, when to escalate. Every decision is tested against those rules before it reaches a customer. Anything outside them stops and waits for your approval.

How long does setup take?

Connect Shopify and your channels, set your policy, and the first employee starts the same day. There is no middleware to configure and no separate login for your team.

Which channels do they work across?

WhatsApp and email today, both arriving in one inbox with full customer context attached. SMS and storefront chat are on the roadmap, not shipped.

Can I start with one employee instead of the whole team?

Yes — most merchants start with Emma on cart recovery, because it is the fastest outcome to measure. You add the others once you can see the numbers.

What happens to conversations already handled by my support team?

They continue as they are. WhatsApp coexistence means your existing support stack keeps running while the AI employees take the volume you hand them.

How do I know they are actually working?

Every action is logged against the employee that took it, with the outcome attached — recovered revenue, resolved tickets, accepted upsells. You review their work the way you would review anyone else’s.

What does the free 60-day beta include?

The full team of five, every channel, and the complete work log. No credit card, and nothing starts billing automatically at the end of it.

WhatsApp vs. Email for Cart Recovery: Why the Data Says Use Both, Not Pick One

The gap is larger than most merchants assume

WhatsApp's open-rate numbers are frequently cited around 95, 98%, though that figure blends personal and transactional messages with marketing sends. A more conservative, opt-in-marketing-specific benchmark puts broadcast campaign open rates closer to 68%, still roughly 3x a typical email open rate, and dramatically higher than the 20, 25% average email open rates common since Apple's Mail Privacy Protection made email open tracking itself less reliable.

Read speed tells a similar story: 88, 95% of WhatsApp messages are read within five minutes of delivery, compared to email, where a meaningful share of opens happen hours or days later, if they happen at all. Click-through rates follow the same pattern, WhatsApp campaigns commonly land in the 45, 60% range versus 2, 5% for email, roughly a 10, 30x gap.

Combine that with the deliverability problem email is separately fighting, global inbox placement rates falling to roughly 82% by late 2024, per Validity's benchmark data, meaning a growing share of cart-recovery emails don't even arrive, and the picture is clear: WhatsApp, where it's usable, reaches people faster and more reliably than email does today.

Why "just switch to WhatsApp" is still bad advice

None of that makes WhatsApp a direct replacement for email, and treating it as one creates a different set of problems.

WhatsApp business messaging is opt-in by design and by regulation. Meta's Business Messaging Policy requires either a customer-initiated conversation or a pre-approved message template with an opt-out before a business can message someone it doesn't have an existing conversation with, cold outreach at any volume risks the number getting flagged or banned. Several major markets go further: both the UK and India require explicit opt-in before WhatsApp business messaging is permitted at all. That means a merchant's WhatsApp-reachable customer list is, by definition, smaller than their email list, usually meaningfully smaller, since it excludes anyone who hasn't specifically consented to that channel.

Practically, this means WhatsApp isn't "better than email" as a channel in the abstract. It's a channel with a much higher performance ceiling for a narrower, opted-in audience, which is a different tradeoff than email's broader reach and weaker attention.

What the current cart-recovery tooling market gets wrong

Look at how the category is actually built today and the gap becomes obvious. Klaviyo, Recart, and most of the established cart-recovery tools are email-first, with SMS as the secondary channel, WhatsApp support, where it exists at all, tends to be an afterthought or a separate integration. TxtCart is built specifically around SMS. On the other side, WhatsApp-native tools like AiSensy or Interakt are built around WhatsApp specifically and don't reason across email at all.

Almost nothing in the category is built to treat email and WhatsApp as one coordinated recovery sequence for the same customer, choosing the channel per case based on what's actually available and appropriate, rather than running two disconnected systems that happen to both be active. That's a structural gap, not a marketing angle: most of the "AI cart recovery" content being published right now is channel-specific because most of the tools are channel-specific.

GoPrimy's Cart Recovery employee is built to work across both channels for the same customer record, email and WhatsApp aren't two separate products bolted together, they're two channels the same reasoning process can choose between, sequence, or use in combination depending on what the customer has opted into and where they're actually likely to respond.

The sequencing that actually makes sense

Given the data, the more defensible strategy isn't "email is dead, move to WhatsApp", it's channel-matched sequencing: email as the default broad-reach layer, since every customer has an email address and it requires no additional opt-in beyond what checkout already collects, and WhatsApp as the high-attention layer for the subset of customers who've opted in, used specifically where speed and read-through matter, the first touch on a high-value cart, or a follow-up once an email has gone unopened for a defined window.

That is a more accurate reading of the data than either channel's own advocates tend to give it. Email isn't obsolete, it's just fighting a real, measurable deliverability decline that has to be accounted for rather than ignored. WhatsApp isn't a universal upgrade, it's a smaller, higher-performing channel with real compliance boundaries around who a business can actually reach on it. The stores getting the most out of cart recovery right now are the ones treating that as two tools for two different moments, not a single either/or decision.

Sources

AiSensy, WhatsApp Statistics for Businesses (https://m.aisensy.com/blog/whatsapp-statistics-for-businesses/)

Validity, 2025 Email Deliverability Benchmark Report (https://www.validity.com/wp-content/uploads/2025/03/2025-Benchmark-Report-FINAL-1.pdf)

Klaviyo, Abandoned Cart Benchmark Report (https://www.klaviyo.com/blog/abandoned-cart-benchmarks)