è����Ƶ

Made With è����Ƶ is an on-site decision engine for eCommerce businesses. It reads people's buying intent in real time and allocates experiences to the visitors most likely to respond to them

is a digital experience platform. It does web and feature experimentation, rule-based personalisation, content recommendations. It's designed for teams running structured test-and-learn programmes at scale.

This blog post explains where the two platforms complement each other and when you would use both versus just one on its own. But if you're too impatient to read to the end, we've got you:‍

Made With è����Ƶ and Optimizely serve different functions. Optimizely handles experimentation and rule-based personalisation.

Made With è����Ƶ reads visitor intent in real time and decides who sees an experience and when. The two work really well together:

Optimizely executes what, Made with è����Ƶ decides who and when. We serve your Optimizely experiences when it matters (the right time within their session) and to whom, all based on what really matters; their intent.

How Made With è����Ƶ is different to Optimizely

‍

1. Respond to users in real-time with experiences tailored to what their digital body language tells you

Optimizely's strongest targeting comes from rule-based audiences in Web Experimentation and Personalization, boolean logic on geo, device, behavioural events, URL targeting, and page Tags, plus optional machine learning (ML) layers:

• Adaptive Audiences (interest categories inferred from content engagement)
• Content Recommendations (NLP-driven topic affinity per visitor)
• Optimizely Data Platform (ODP) real-time audiences��

‍

The Stats Engine inside experiments is genuinely best-in-class — sequential testing with always-valid p-values — but the targeting decision still asks the marketer to define which audience rule a visitor fits into.

Made With è����Ƶ flips the model. It reads buying intent in real-time from the first pageview. Stage, signals, trends, purchase confidence, abandon risk, shopper mindset, and re-scores every three-five seconds.

Targeting is driven by what's happening now, in real-time, by a human, not by which rule-defined audience or topic interest a visitor has been mapped into. Nor by behaviour that's already happened. This means you can respond to the signals that sit between events and pageviews; what we call moments that matter.

You can read more about How Made With è����Ƶ Works, and the moments that matter, by clicking the link.

‍

2. Segment the right experience to your customers automatically, without fiddling with rule trees manually

Your team currently builds and maintains audiences in Optimizely's Audience Builder, Dynamic Customer Profiles, Adaptive Audiences, and ODP. All with decision rule trees, content-tagging taxonomies, attribute conditions, event conditions.

Even with contextual bandits reallocating traffic within a defined audience, the audience definition itself stays manual: design the rules, QA the segments, redesign as the catalogue and content evolve. These segments are website-attributes, too. Not human attributes, not intent based (the most human of all attributes). That's where personalisation really succeeds.

Made With è����Ƶ replaces all of the above with continuous intent prediction and delivery.

Our agent decides who sees what, in real time, across hundreds of intent combinations. You'll focus on strategy, creative and proof, instead of tweaking and analysing rules or segments all the time.

The agent retrains daily, which means the experience compounds toward intent combinations where impact is seen and felt. In an always on state, always learning, always getting better.

Where Optimizely's multi-armed bandits (if used) allocate traffic across the variants of a single experiment to maximise one fixed metric within one defined audience, Made With è����Ƶ allocates across hundreds of audiences (intent combinations) — adding the layer of to whom and when an experience should be served, and measuring it against a holdback rather than just exploiting the winner.

Made With è����Ƶ and Optimizely: In depth

Here is how the two platforms compare on the things that matter most for eCommerce teams:

Where does Made With è����Ƶ integrate with Optimizely?

We've broken this section down into three parts. We want to be honest about where you'll gain functionality by utilising Made With è����Ƶ with Optimizely, where we augment it, and things we simply don't do, or Optimizely does better.

How Made With è����Ƶ adds new functionality to Optimizely

Understand and act on every visitor (including anonymous) from the first pageview. Optimizely's Personalization is rule-driven. It works once a visitor matches an audience rule. Content Recommendations builds a per-visitor interest profile from content engagement, which strengthens as the session progresses.

Made With è����Ƶ's model, which collates 50bn+ monthly events across 150+ retailers, reads continuous intent from pageview one, every few seconds. Anonymous, identified, first-time, returning. The opening moments of a session get the same intent read as the tenth pageview.

Automatically identify and serve the best experiences to people without guessing. Optimizely's contextual multi-armed bandit (CMAB, powered by Opal) is the closest thing in their stack, and it's genuinely good, so it's worth being precise about what it does.

A CMAB picks the best-performing variation for each visitor based on context (device, geo, behavioural history) to maximise one primary metric, within a single experiment.

Three design choices define it: the context attributes are declared up front and can't be added or removed once it starts (even paused); it optimises exclusively to a single primary metric fixed at launch; and it begins with a 100% exploration phase, randomly serving variations until it has gathered enough data before it shifts to exploiting the winner.

It's a smarter way to split traffic across the variations you built for the audience you defined.

But we'd like to go into detail on what that context is.

Device, geo and behavioural history are proxies for a person. They describe who a visitor appears to be, not what they want or how close they are to buying. They're arbitrary website attributes that correlate with conversion only loosely, and a bandit optimising over them is tuning against a weak signal.

è����Ƶ — buying stage, momentum, hesitation, purchase confidence — is the proximate driver of what a visitor actually does next. The proxies describe identity; intent describes decision, and decision is what moves the metric. Optimising the allocation over the wrong variable caps how much a CMAB can ever find.

Made With è����Ƶ's agentic campaigns work a level up.

Rather than splitting traffic across the variations of one experiment to maximise one metric, it allocates across hundreds of intent combinations.

Diamonds Factory, a Made With è����Ƶ customer, , where the 'context' is live, multi-dimensional intent (stage, signal, trend, purchase confidence, abandon risk, mindset) that updates every 3–5 seconds and is discovered by the agent, not enumerated by the team upfront. Learn more about basket abandonment here.

There's no per-experiment exploration tax, because the model is trained across 50bn+ events, 150+ retailers and live from page view one.

And because a bandit is built to shift traffic toward winners, it has no standing no-treatment baseline — Made With è����Ƶ keeps a holdback on every experience, so it can answer "did this cause incremental orders," the question a metric-maximising bandit structurally can't.

Causal incrementality on every experience. Optimizely's Stats Engine reports variant lift with always-valid p-values; genuinely strong for variant comparison.

Made With è����Ƶ runs a holdback group on every experience by default and reports incremental orders against a no-intervention baseline.

The difference is between "variant A beat variant B" and "this experience caused X orders that wouldn't have happened otherwise."

Where Made With è����Ƶ improves Optimizely

These are things Optimizely does that get better with Made With è����Ƶ on top:

• Audience Builder and ODP audiences become intent-aware
  Instead of boolean rules on attributes and events, or content-engagement interest categories, Optimizely audiences can take Made With è����Ƶ's live intent attributes and target on signals that actually predict conversion. ODP's segment builder picks these up as attribute conditions; Web Experimentation picks them up as Tags.
• Personalization variants get the right routing
  Made With è����Ƶ decides which Optimizely-created variant a visitor should see based on their current intent state, replacing rule-based audience routing. The marketer keeps the variant production; our agent handles the allocation.
• Web Experimentation tests get causal lift on top of variant performance. Run Optimizely tests with Stats Engine as you do today. Add Made With è����Ƶ's holdback measurement on the experience itself to answer "would users have purchased regardless of any variant?"
• Content Recommendations recommend to live intent, not just topic affinity. Made With è����Ƶ lets Content Recommendations reflect what's happening in this session, not just historical topic engagement. Particularly useful for anonymous visitors where you’re not sure what their behaviour is telling you.

‍

What Made With è����Ƶ doesn't do

• Feature flagging and server-side experimentation. Optimizely Feature Experimentation (SDKs in 19+ languages, Edge Workers, Agent microservice) is a category leader. We don’t offer anything here.
• Sequential testing methodology for variant comparison. The Stats Engine's mSPRT-based always-valid p-values are best-in-class for inferring variant winners under continuous monitoring. Made With è����Ƶ uses Bayesian A/B with holdback.
• CMS-native content personalisation across the wider DXP. Optimizely Content Cloud, Content Marketing Platform and the broader DXP integration are all things that are not within Made With è����Ƶ's scope.
• Made With è����Ƶ isn’t going to change your recommendations process Optimizely's NLP-driven content recommendations and ecommerce product recommendations are well-established. Made With è����Ƶ adds an intent layer; we don’t replace what’s powering your recommendations process.
• Mobile app personalisation. Optimizely Feature Experimentation has native SDKs for iOS, Android, React Native. Made With è����Ƶ is web-first.
• Edge experimentation. Optimizely's Edge Worker integrations (Cloudflare, Akamai, Fastly) sit outside Made With è����Ƶ's use case

‍

How to get started with Optimizely and Made With è����Ƶ

1. Use Made With è����Ƶ to create intent-ready audiences in Optimizely: Pass Made With è����Ƶ's live intent attributes — purchase confidence, abandon risk, buying stage, intent trend — into ODP as attribute conditions, or into Web Experimentation as Tags.
   
   Build audiences like "high purchase confidence + declining intent trend" (needs reassurance), "medium confidence + high abandon risk" (needs timely intervention), "low confidence + active comparison signals" (needs guidance, not a discount).
   
   
2. Execute experiences in Optimizely using those audiences. Use Web Experimentation and Personalization for what they do well, so things like variant production, Stats Engine analysis, content variations across the DXP.
   
   
3. Serve the experience (or a variant) through Made With è����Ƶ's decision agent, where the experience is served based on visitor intent rather than rule-defined audiences.
   
   
4. Use Made With è����Ƶ to prove the incrementality of "Optimizely + intent". Holdback groups on top of the Optimizely experience answer the CFO question: did this cause incremental orders, or did we just personalise for visitors who would have bought anyway? Particularly valuable for discounting — Made With è����Ƶ surfaces which high-intent visitors needed no incentive.

Neve Jewels Group, the luxury jewellery brands Austen Blake and Sacet, moved from universal promotions to intent-level targeting across their basket abandonment strategy.

Rather than applying the same discount to every abandoning visitor, Made With è����Ƶ segmented interventions across four intent levels, targeting what Director of Customer Experience Jo Homer described as "the nudge moment."

The result: 13% conversion uplift on basket abandonment, and £2.4m in annual revenue uplift overall, 4.8x the original business case, paid back within a single experience. You can learn more here.

What sort of businesses work best with Made With è����Ƶ?

This all depends on the size and structure of your eCommerce operation.

Mid-market retailers (£20m–£100m online revenue)

Made With è����Ƶ often leads here. Optimizely's Intelligence Cloud commonly lands at £50–80k+/year for this band, based on and procurement data. Made With è����Ƶ's session-based pricing, 30 to 60 minute install, and agentic layer fit eCommerce teams of two to ten people who need to ship and prove things quickly.

If you are running Optimizely for the Stats Engine and feature experimentation and those are load-bearing, keep them. Add Made With è����Ƶ for intent targeting and causal measurement of your on-site experiences.

Enterprise retailers with dedicated personalisation teams

Both, with clear role separation. Optimizely for the experimentation surface, Stats Engine credibility, server-side feature flagging, and DXP integration. Made With è����Ƶ for on-site intent-driven decisioning and causal measurement.

Try Made With è����Ƶ today

There you have it. Made With è����Ƶ and Optimizely are designed to complement one-another, not compete with one another. Many of our clients use Optimizely to continue A/B testing, while using Made With è����Ƶ to serve experience to customers on a 1:1 basis.

If you're interested in learning more about how Made With è����Ƶ works, and how you can use it in your tool stack, book a demo here.

Disclaimer: This comparison is based on publicly available information from Optimizely's documentation, marketing site, and customer reviews as of July 2026. Both products evolve continuously. If anything looks out of date, get in touch.

Editor's note: this article is adapted from a recent è����Ƶ Live session with Jack Simkins, Digital Product Manager at Golfbreaks.com.

A test that lifted time on site by 14% still spent its first week looking like a failure. Conversion rate was down. Under a traditional A/B testing programme, Golfbreaks.com would have pulled the experiment.

They didn't. And the reason why says a lot about what happens when a genuinely high-consideration purchase journey meets a testing programme built for one-session eCommerce.

is a golf tour operator based in Windsor, with offices in Copenhagen and Charleston, though the Made with è����Ƶ account focuses on the US and UK. It sends golfers on trips ranging from a single night in the UK to a week in Spain or Portugal, across a lot of different golfer segments. It's a lead generation business first. Visitors don't check out online in one sitting, they enquire, then a sales agent works out flights, transfers, accommodation, and course access, and gets them to a booking over the phone, sometimes weeks later.

That's not unusual for travel, where research and comparison typically happen across several separate visits and sites before a decision gets made. Optimising a single-session conversion rate for a purchase that actually plays out over weeks measures the wrong moment entirely.

A booking journey that can't be forced into one session

Jack has spent seven years at Golfbreaks.com, the last couple focused on conversion rate optimisation. "We've got quite a unique scenario whereby we're trying to encourage that inquiry," he said. "Particularly in travel, in the industry in general, it's quite an unusual thing to not be able to book entirely online."

A small portionof trips get booked online. But most go through a sales agent, because a golf trip has too many moving parts (courses, transfers, flights, accommodation, and group logistics) for most visitors to configure and commit to in one sitting.

Colin Spooner, Principal Value Consultant at Made with è����Ƶ, put his finger on why that matters: "It's not our traditional eCommerce brand where it's a pure purchase journey. But that almost plays into the hands of intent, where you need to think about that considered purchase and how to get people through the funnel before even thinking about the booking, weeks and months down the line."

Measuring what happens before conversion

"You are what you measure" is a phrase the Golfbreaks.com team has adopted internally. If a new visitor is unlikely to enquire on their first visit, optimising purely for enquiry rate on that visit measures the wrong thing.

So alongside enquiry rate, the team tracks bounce rate and time on site together (a new visitor who bounces immediately clearly hasn't been given a reason to stay), pages viewed per session as a depth-of-exploration signal, and, specifically, movement from low to building intent, the kind of signals behind Made with è����Ƶ's content prioritisation and messaging use cases. None of these are vanity metrics here. They're proxies for whether a visitor is progressing through a decision process that runs across several sessions, not on a single visit.

Before building any experience, the team asks these questions to get in their customers shoes:

• What is a brand-new visitor actually trying to work out?
• Who are Golfbreaks.com?
• Can we be trusted?
• Do you have to pay full price up front?
• Can you book online at all?

That last one is really important. Because Golfbreaks.com can't be booked entirely online, setting that expectation early avoids disappointment later in the funnel, right when a visitor is closest to converting. As Colin put it, getting that messaging right up front was "a huge realisation" for how the whole experience needed to be built.

What agentic campaigns change about testing

Golfbreaks.com's testing programme runs on Made with è����Ƶ's agentic campaigns. In standard A/B testing, you decide up front which segment sees which variant, based on a hypothesis about who will respond to what. Agentic campaigns invert that: you define the strategy (the moment you're trying to influence, and the goal, whether that's enquiries, conversions, or a secondary metric) and hand the agent your set of tactics. It tests them against real segments and works out which one performs best, for whom, and when, using the same intent signals that power the rest of the platform.

For Jack, a self-described non-developer, the practical benefit was speed. "The tool allows me to get these experiences up much faster," he said. "My concept-to-live process is significantly shorter... it means the agents have got time to learn."

But the deeper change is what gets removed. "No longer am I having to set up those individual segments, or serve experiences to segments that I think will benefit from them," he said. "It's in the hands of the agent to then work out what segments it would benefit from... It's a much wider net." A message built for low-intent visitors might also help a segment already building toward a decision. A manual test is only as good as the human guess behind who it's shown to. An agent testing against a hundred segments simultaneously doesn't have that blind spot.

The "do nothing" variant is a genuine conversion tool

One of the more counter-intuitive parts of Golfbreaks.com's setup is what Jack calls the "do nothing" variant. In standard A/B testing, every visitor sees a control or one of several variants. Agentic campaigns add an option where the visitor sees nothing added or changed at all.

"The do nothing essentially sits within those variants as a copy of the control," Jack explained. "It's a safety net because it prevents us from showing negative experiences to customers that don't need to see it."

"In most experience it's always about adding things onto your site," Colin observed. "Having a version where actually sometimes the best thing is leaving the customer alone to progress, or even suppressing things on site, is a nice alternative to what we've experienced over the last 10, 20 years in experimentation." As the data below shows, it's frequently the top performer, because some visitors don't need an intervention. They're already progressing on their own, or they arrived with enough context that added messaging just gets in the way.

When the agent's early data looks wrong

Here's where the seven-day lesson from the top of this article comes back in. Jack's team built two welcome-visit experiences using the same messaging, one for the homepage, one for a location page such as a product discovery landing point for someone who searched "golf breaks in England."

The homepage experience delivered a 14% uplift in time on site. But conversion rate showed a negative trend for the first seven days. "With traditional AB testing, I would have perhaps turned it off," Jack said. "I would have panicked when I saw negative 14%, and I would have said, this isn't working."

He didn't, because the agent was still learning. That's consistent with what independent testing research shows more broadly: . Once the agent had enough data, performance turned around.

Same messaging, two different visitors

The location-page test surfaced something else: identical messaging performed in opposite ways depending on where a visitor arrived. On the homepage, a "how to book guide" message performed best, evidence of a genuinely low-intent visitor who needs some hand-holding.

On the location page, the top performer was a trust-building "number one tour operator" message and the do-nothing variant. Jack's take is that a visitor who searched "golf breaks in England" already has affinity toward the destination, closer to a returning visit mindset than a cold product visit. They don't need the basics explained.

A message about Golfbreaks.com's customisable packages underperformed with brand-new homepage visitors. It's true and important, but it's the wrong message at the wrong moment, the same lesson behind Made with è����Ƶ's discounting use case: showing a message before a visitor is ready for it does more harm than good.

The surprise that only showed up in the data

Asked what surprised him most, Jack pointed to something that had been sitting in plain sight. An early "ready to plan?" message aimed at brand-new visitors looked like a reasonable nudge. But in the data, it actually came across as overbearing.

"If you think about a new user landing on the site and asking, are you ready to plan? It's probably a bit overbearing," Jack said. "At the time, when you're setting up those tests, it's like, right, I'm going to use the same messages for the homepage, same message for the location page. They're surely going to work." They didn't, for every segment.

Colin's read: "The amount of times we see customers who have a predefined view of what will work, and it's completely different. That point around being subjective comes to life when you start to see the way the agent starts to make decisions." That tracks with the broader shift in shopper expectations, , a generic message is no longer neutral, it actively reads as a miss.

When a message doesn't resonate with any segment, the fix is simple. Delete it, let the agent relearn, and add a new tactic later if needed. You don't need to manually re-segment.

Measure the journey, not just the moment

None of this is unique to golf holidays. Any purchase with a real consideration cycle shares the same shape, including B2B software, where . A first-time visitor is rarely the same as a returning, further-along one, and treating them identically wastes the message on the visitor least ready to act on it.

Three things carry over regardless of your industry. You don't need to be a developer to find early wins, a visual editor is enough to start. If your purchase journey has any real consideration cycle in it, top-of-funnel testing should measure more than conversion. And build a tactic sheet of messages at a global level, then let the data show which ones resonate with which visitors, rather than deciding that yourself up front.

If your own funnel has visitors who aren't ready to buy on visit one, the same logic applies. See the intent framework behind it. Or book a demo to see it against your own traffic.

If you've enjoyed this write up of our latest è����Ƶ Live session, why don't you join our

Why standard advice on eCommerce bounce rate might not be enough

In 2023, Google Analytics 4 replaced Universal Analytics (UA) as the default, shifting the definition of bounce rate entirely. Under UA, any single-page session counted as a bounce, regardless of how long the visitor stayed or what they did. Under GA4, a "bounce" is a session with no meaningful engagement in the first ten seconds (, 2023).

Most published advice on reducing eCommerce bounce rate, including almost everything ranking on the first page of Google right now, predates that change. The benchmarks cited, the comparisons drawn, the thresholds used to define a "good" or "bad" rate: much of it is calibrated to a metric that no longer exists in its original form. It's worth bearing in mind before treating a published figure as a reliable signal that something is broken.

There's a connection here to the intent signals argument. GA4 defines a bounce as a session with no meaningful engagement, which is itself the absence of any intent signal. However, the metric has quietly moved closer to what we're suggesting: that what matters is whether a visitor showed signs of engagement and intent, not simply whether they viewed more than one page.

The standard fixes aren't useless. A page that takes four seconds to load on mobile will lose shoppers. Navigation that buries products three levels deep creates friction. These are real problems. But they're also largely table stakes. Most mid-market eCommerce teams have addressed them, or at least know they need to.

What the generic checklist rarely asks is: why did this particular visitor leave this particular page? Speed explains some of it. Confusing navigation explains more. But there's a third explanation that gets far less attention: the visitor arrived with a specific intent, and the experience they landed on didn't reflect it.

What on-site intent signals actually are

è����Ƶ signals aren't abstract. They're specific, observable events already firing on your site every day, most of them visible in your analytics if you know where to look.

Consider what happens in the first thirty seconds of a session. A visitor lands on a product detail page. Do they scroll past the first image, or stop there? Do they interact with the size selector, or skip straight past it? Do they hover over the "Add to Basket" button without clicking? Do they navigate to a second product, return to the category page, or leave entirely?

Each of those micro-behaviours carries a signal. Taken individually, they don't mean anything. Taken together, they start to suggest something about intent: whether the visitor is browsing loosely, comparing seriously, or hitting a wall they can't get past.

Some of the most informative on-site signals include:

- Scroll depth: how far down the page a visitor gets before stopping or leaving

- Hover behaviour: where the cursor lingers without a click (interest that didn't convert to action)

- On-site search queries: what visitors type into the search bar, and crucially, what they do next

- Dwell time relative to site average: a visitor spending significantly longer on a PDP than average may be closer to buying than the raw bounce metric suggests

- Variant and size selection: engaging with product options is a meaningful buying signal, regardless of whether a purchase follows

- Back-navigation patterns: returning from a PDP to the same category page repeatedly often indicates comparison behaviour, not disinterest

None of these signals individually tells you what a visitor intends to do. But patterns across them might tell you something useful about why they're not finding what they came for, and whether the bounce that follows is a genuine commercial loss or an inevitable one.

For a deeper look at why behavioural signals tend to outperform the proxy metrics most teams rely on, Predictions Not Proxies, our blog post, is worth a read.

The signals worth watching by page type

One limitation of tracking bounce rate as a single site-wide number is that it flattens very different problems into one metric. A visitor who bounces from the homepage is probably experiencing something quite different from one who bounces from a product detail page after two minutes of engagement. The signals worth reading, and the interventions that might help, differ depending on where the bounce is happening.

Homepage

Homepage bounces are often about relevance at first impression. Was the visitor expecting something the page doesn't immediately surface? Traffic source matters here. A visitor arriving from a paid social ad promoting a specific sale and landing on a generic homepage is likely to read that as a mismatch before they've even scrolled.

You should, instead, consider time to first scroll, engagement with any navigation element, and click-through to any product page. A visitor who lands and never scrolls is usually gone for reasons that faster load times can't fully address.

Category pages

Bounce from a category page often points to a discovery problem. Either the product range isn't what the visitor expected, or the tools for narrowing it down (filters, sorting, on-site search) aren't doing their job.

You could monitor for filter use, scroll depth through the product grid, and whether visitors click through to multiple PDPs or just one (or none). A visitor who opens the filter panel but doesn't apply anything may be signalling that the available options don't map to what they had in mind.

Product detail pages

PDP bounce is the most commercially sensitive, because this is where visitors are closest to a decision and where intent signals tend to be richest. Image engagement, variant selection, and dwell time relative to site average can all suggest whether a visitor is actively evaluating or has already decided the product isn't right.

A visitor who spends three minutes on a PDP, selects a size, and then leaves is a very different prospect from one who bounced in under ten seconds. Treating both as equivalent in a site-wide bounce metric misses that distinction entirely, and probably points the subsequent analysis in the wrong direction.

Paid landing pages

For pages receiving meaningful paid traffic, the most important signal is often the simplest: does the message on the page match the ad that brought the visitor here? Post-click relevance is frequently the first place to look when bounce rate on paid traffic is elevated, before speed or UX enter the conversation.

Consider a fashion retailer seeing high PDP bounce from paid social. You may think audience mismatch or slow load times. But scroll depth data tells a different story. Visitors are reaching the size selector and stopping, not scrolling away. The real problem is out-of-stock variants being featured in the ad creative. Shoppers arrive, find their size unavailable, and leave. This is nothing to do with a UX fix, simply a case of reading the right signal, the right context.

Acting on intent signals before the bounce happens

Reading these signals is useful. Responding to them is where it gets more interesting.

The standard eCommerce pop-up is a useful counterexample. A blanket overlay triggered by exit intent, offering a discount to everyone regardless of what they've been doing, ignores every signal the visitor has sent. A visitor who spent four minutes on a PDP, selected a variant, and then paused receives the same intervention as one who arrived and left in eight seconds. So, really, you're not delivering a proper personalised experience that's appropriate to your customers' different needs.

A more considered approach starts with the signal, instead of the user navigating away. A visitor showing strong PDP engagement (extended dwell time, variant selection, multiple image views) is telling you something. The right response is probably social proof surfaced at that moment: stock scarcity, recent purchase activity, a well-timed review. Not a discount. A visitor who used the search bar, found no useful results, and is now leaving needs a different intervention entirely: a related product suggestion, or a prompt to browse a relevant category.

The interventions don't have to be complex to be more relevant. Start with your highest-bounce page type, identify which signals are already firing there, and ask whether your current exit triggers reflect any of them. That's a reasonable first step, and it costs nothing to consider.

If you're looking at how this kind of approach works for browse abandonment specifically, our browse abandonment use case walks through one way to think about it.

What a bounce means for your CRM, and why it matters

Bounce rate is typically discussed as a traffic or UX problem. It's less often discussed as a CRM problem. But there's an argument that it should be.

Every visitor who leaves without converting, subscribing, or taking any traceable action represents not just a lost session, but a lost contact. For a brand spending meaningfully on paid acquisition, that loss isn't only the missed immediate sale. It's the absence of any first-party data to re-engage with later. The CAC clock is ticking whether or not the visit converts.

The intent signals that might help reduce bounce in the moment are the same signals that could inform a more relevant recovery sequence when the bounce does happen. A visitor who engaged with a specific category, hovered on a product, and then left is a different re-engagement prospect from one who arrived on the homepage and bounced immediately. Where that behavioural data is captured, it can feed a browse abandonment email or SMS that speaks to what the visitor was actually looking at, not a generic "you left something behind" message.

Most browse abandonment recovery today operates on a relatively simple trigger. The visitor viewed a product and left. è����Ƶ signals could make that logic more nuanced, and the message that follows more relevant to where the visitor actually was in their decision.

How to read bounce rate differently

Bounce rate, as a metric, doesn't tell you very much on its own. It tells you someone left. It doesn't tell you why, which page type to prioritise, or whether the bounce represents a genuine commercial loss or a session that was never going to convert.

On-site intent signals can't answer all of those questions. But they might answer more of them than page speed tests and navigation audits typically do. For eCommerce teams who've already done the basics and are still looking for what to try next, it's worth examining what visitors are doing before they leave, not just that they left.

That shift in framing, from "how do we stop bounces?" to "what are bounces telling us?", might be where the more useful work sits.

If you want to see how Made With è����Ƶ reads on-site intent signals across eCommerce traffic, book a demo and we'll walk through it with your site.

ran a discount and watched conversions climb 11%. On paper, it looked like a win, right?

It wasn't. Average order value fell 6.7% in the same period, and once the discount depth was accounted for, the "win" was worth barely £8k a month.

So, the luxury jewellery brand tried something different. It handed the decision to our told it to optimise for revenue per customer instead of conversion rate, and gave it the option to do nothing at all.��

Our model decided that for 52% of customers, nothing was exactly the right call. That decision alone was worth £1.6m in incremental annual revenue.

‍Editor's note: This post is a write-up of an featuring Jo Homer, Director of CX at the parent company of Diamonds Factory. Jo walked through a real, live test of Made With è����Ƶ's agentic campaigns, hosted by Charley Bader, VP Strategy & Ops, and Colin Spooner, Principal Value Consultant, both at Made With è����Ƶ.

Diamonds Factory is a made-to-order luxury jewellery brand, one of the brands under Neve Jewels Group. Jo was upfront that this wasn't automation for automation's sake. It was a genuine test of what happens when a business gives an AI the ability to make real commercial decisions, and watches closely what it actually decides.

Agentic campaigns, most recent product launch, replace the old manual approach (build a segment, write a rule, set it live, hope the hypothesis was right). You stay in control of the strategy, the moment being targeted, and the goal being optimised for. But the moment-to-moment decision, based on who sees what and when, goes to an AI agent that keeps learning and reallocating traffic as it goes.

The discounting trap that feels like a win

The original brief was simple: catch basket abandonment before a customer leaves, offer 25% off, and recover the sale. It's the default move for most eCommerce brands, and doubly so in a vertical as competitive as jewellery, where discounting is normal.

The first-pass numbers looked good. Conversions were up 11%. However, the problem is what sat underneath it. Average order value dropped 6.7% over the same period. Diamonds Factory wasn't gaining new revenue so much as buying back sales it would likely have made anyway, at a lower margin.

As Jo Homer, Director of CX at Neve Jewels Group, put it:

"We were basically training the customer to wait for a deal, which in return was affecting margin."

Diamonds Factory fell into a similar trap many retailers fall into. A single rule applied to everyone optimises for the metric that's easiest to see (conversions) while diminishing the one that matters (margin).

For a luxury brand, the cost isn't only the discount itself. It's what the discount teaches the customer to expect next time. Train customers to wait for 25% off, and full price starts to look like a mistake they'd be silly to make.

It's a familiar story for anyone who has run basket abandonment campaigns before. A rule fires the same offer at every visitor who matches a condition, regardless of why they left.

Some were genuinely price-sensitive and needed the nudge. Others were already going to buy and simply hadn't checked out yet. Blanket rules can't tell the difference, so it pays the same discount for both.

Changing the question the model was answering

The shift that mattered wasn't really about AI. It was about changing what "success" meant.

Diamonds Factory moved from a single rule (25% off, applied to everyone) to an agentic campaign with four possible responses: a 25% discount, a 15% discount, a trust-building message, or no intervention at all. Crucially, the goal changed too, from conversion rate to revenue per customer.

That distinction is easy to state and hard to act on, because it means giving up control over exactly which lever gets pulled and letting the model decide, case by case, based on what it observes. As Jo describes it:

"The tool didn't change. The objective did. And that's the real unlock in some cases."

The model started with no historical or behavioural data. It had to learn the pattern from scratch, in real time. The result: revenue per customer rose from £127 in the control group to £145 in the agentic group. A 13.8% uplift.

"It didn't come from offering more," Jo said. "It was offering much smarter."

Jo frames the difference as hiring someone and handing them a script to read, versus hiring someone and trusting them to think on their feet. A script covers the cases you anticipated. Under the agentic model, the system sets its own rules based on what it actually observes in customer behaviour, and updates them continuously rather than waiting for the next quarterly review.

What our agentic model found without being told

Neither Jo nor anyone on her team instructed our AI model to look for a basket-value threshold.��

It found one anyway, identifying a specific value point below which doing nothing consistently maximised revenue, and above which a discount or message made more sense.��

It also separated customers by where they sat in the buying journey, not just by what was in their basket. Shoppers who looked like they were still comparing options, still in a research mindset rather than a checkout mindset, were shown trust messaging instead. So, things like craftsmanship, heritage, and guarantees.

A discount at that stage would have read as pushy. The model inferred that without being told what a "research mindset" should look like.

"The model basically developed a theory of buyer psychology without being given one," Jo said. "No human would take months, sometimes years, to get to that kind of analysis."

Device behaviour told a similarly specific story. On desktop, 79% of customers were offered some form of discount. On mobile, 96% were shown nothing. The model had, in effect, worked out that mobile sessions were browsing sessions rather than buying sessions, and treated them accordingly, without anyone telling it.

The value of restraint

Marketers are trained to intervene. Numbers dip, and the instinct in the room is always "what should we do about this," never "should we do anything at all." Jo made the point that in a hundred trading meetings, that second question rarely gets asked, let alone answered with "nothing."

In this case, the model decided that 52% of customers were best served by being left alone entirely.��

"The highest value of action really was the restraint," Jo said. "The agent knew when to get out of the way."

That restraint was worth £1.6m in annual incremental revenue. Not because doing nothing is inherently valuable, but because for those customers, any intervention would have either converted someone who was already going to buy (at a needlessly reduced margin) or interrupted someone who wasn't ready to be nudged.

This figure is the outcome of testing across three separate markets, over more than a hundred individual tests.��

Turning Made With è����Ƶ into a trading lever

Beyond the topline number, the agentic model isn't a fixed campaign. It's something Diamonds Factory can turn on and off in step with its trading calendar.

Around Black Friday, for example, the team pauses the agent so customers already in a high-intent buying mode aren't shown a discount they didn't need. When trading returns to business as usual in January, the campaign flips back on, and the model picks up its learning from where it left off.

"It's a lever we can control," Jo said, describing how the model compounds its learning across each on/off cycle rather than resetting.

That reframes the agent from a one-off experiment into infrastructure. ����’s something that learns continuously and can be dialled up or down around known peaks and troughs. Jo's team started seeing patterns emerge after three to four weeks, and reached genuine confidence in the results within six weeks to two months, consistent across all three markets tested.

What setting up agentic campaigns looks like

, Principal Value Consultant at Made With è����Ƶ, walked through the mechanics live during the session, because "agentic" can sound more abstract than it actually is.

Setting up a campaign starts with choosing the moment it targets (new customer arrival, , browse or basket abandonment), then the goal it optimises for, revenue per customer, conversions, or something custom like a credit application.

From there, you build the toolkit of possible responses: a discount at whatever depth makes sense, a trust message, a finance nudge for customers who might be mid-month on cash flow, and, deliberately, a do-nothing option.

The agent then goes into a learning phase, typically two to four weeks, working out which response suits which individual, before it starts compounding that performance over time.

What this doesn't mean

The point that came out from the session is that a single discount applied to everyone, regardless of where they are in the journey, is a blunt instrument in a world that calls for something more precise.

It also doesn't mean every brand will find that 52% of its customers are best left alone. That figure is specific to Diamonds Factory's price points and customer base, and a mass-market retailer with a lower average order value would likely see a different split.

What should generalise is the method, not the exact number: test more than one response, optimise for a metric that reflects margin as well as conversion, and make "do nothing" a genuine option rather than an assumption nobody checks.

In conclusion: From what rule should we apply, to what does this customer need

The shift Jo describes isn't really technical, even though the mechanism is AI. It's a change in the question being asked. Diamonds Factory moved from "what rule should we apply" and "what do we think will work" to "what does this specific customer need right now."

Sometimes, as this blog post shows, the right answer to that question is nothing at all. That's a harder thing for a marketing team to sit with than a 25% discount, but it's the one that protected both the brand's margin and its positioning as a luxury retailer, while still growing revenue per customer by double digits.

If you're running basket abandonment campaigns on a single blanket rule, the question worth asking isn't whether your discount converts. It's whether it's the right decision for the customer in front of you, or just the easiest one to set and forget.

Not every abandoned basket is a fire to put out. Some are customers who are always going to come back, and every discount you throw at them is a margin you don't need to give away.

Curious what an agentic approach could do in your own basket abandonment process? with Made With è����Ƶ to see it in action.

If you liked this article and want to join our next webinar, follow the link to join our next session.

Visual Editor has just shipped. It's a brand new feature for Made With è����Ƶ.

Yes, we know this isn't something groundbreaking, and you've used something like Visual Editor before, with your favourite tools, but this is one of the most requested features from our customers.

It lets you create and preview on-site changes against your own live website. You'll have more flexibility and control over the kinds of experiences you'd like our tool to test and deliver to your customers.

It'll reduce the need for developers to get involved, and give you a familiar, visual way of editing experiences, directly within Made With è����Ƶ, that you can ship on your own.

So, that's the short version. Here's a bit more background on what it does, why we built it and a sneak preview of what's coming next.

What Visual Editor does

Visual Editor lets you create and preview on-site changes against your own live website, without developer support and without guessing how something will look once it's live.

It solves a familiar problem. The person responsible for the site experience is rarely the person who can build it. As Ryan Jordan, our CPO, puts it:

"The people that are using our product are generally those who are responsible for the site experience but not necessarily technically able to always build for the site experience."

Here's a list of of some of things you'll be able to do with this new feature:

• Change a banner
• Update, restyle, hide or show a specific element on a page
• Fully customisable overlays, built to cater for every moment��
• Build and preview components on your live site before they go anywhere near a visitor.

You'll have, no doubt, used lots and lots of WYSIWYG tools before in your favourite A/B testing, experience and ecommerce tools. We've deliberately designed Visual Editor to be familiar, and work similar to the products you know and love, so you'll find it intuitive to use.

We built Visual Editor because it is the feature that was most requested by our customers. We feel it's a natural evolution of our well-loved . With the ability to essentially edit your site by clicking and typing, we think it'll be flexible enough for non-technical people to pick it up and build something quick and dirty.

But this new feature will also let you see the context of what you've built in-situ, perfect for your site and your context, instead of leaving it to imagination.

But Ryan reckons you'll go further: "Previously, campaigns delivered with Made With è����Ƶ were generally thought about from a \"template\" first approach, but the Visual Editor now allows you to think about how real-time moments of intent can change the page and its content"

Moving towards a goal-orientated mindset

We reckon our Visual Editor will help you change your mindset. Most experience delivery tools tell you to pick a format first. You decide you want a pop-up, then you go and fill it with content. You decide you want a sticky banner, then you fill that with content. The format leads, and the goal follows.

But that's backwards for a lot of what teams are trying to do.

Let's take basket abandonment. One brand might come in knowing they want a pop-up. Fine, build the pop-up, fill it with content. But another brand comes in knowing only that they want to offer a 20% discount when someone's about to leave. They've got the goal. Why should we dictate how you deliver that discount?

So we've built Visual Editor to work from either end. Start with a format and add your content. Or start with your content: the discount, the message, the countdown timer. Then see how it looks as a sticky banner, a pop-up, a slide-in, or an in-page element.

"Most of the market always just goes format-into-content," Ryan explained. "What we're doing by flipping it and being able to go content-into-format is giving people the ability to play around."

On paper this might seem like a small thing. But we think this will give you different options to explore different solutions to the same problems you've been optimising and experimenting with for years. You'll be inspired to create different solutions to the same problems you've been having for years.

A quick note on CSP

Some sites run Content Security Policy (CSP) rules that can stop a visual editor from working on the page. To help with that, we're rolling out a Chrome extension called è����Ƶ Studio that unblocks it.

If your site's CSP rules mean you can't use the editor on the page yet, nothing else changes, everything you could do yesterday, you can still do today. For sites that don't have CSP rules, you should be fine without è����Ƶ Studio.

So, what's coming next?

We'll be adding more templates. We've built Visual Editor to be flexible deliberately, so people get used to it and start asking "can it do this, can it do that," we'll keep adding to what's there.

Longer term, this is where things get a bit interesting. We're finding with tools like Claude Design, many, many people are designing experiences using prompts, instead of fiddling around manually.

Ryan says: "It's now no longer click on an element and change the background colour to blue. It's tell an AI, make this background blue, and it kind of just does it for you."

The widgets behind Visual Editor have been built so that AI can understand them and make changes to them. This is the groundwork for letting you describe the change you want and have it built for you.

There's no hard date on when this is coming, but Ryan said it's a matter of weeks, not quarters.

Made With è����Ƶ has always been about one thing: enabling you to respond to real-time intent on your ecommerce site. Everything we do is in service of making that easier and more effective.

For a long time, acting on intent meant working within the formats we gave you or dev resource. Visual Editor changes that. It lowers the barrier between knowing what you want a visitor to experience and actually building it — without waiting on someone else to do it for you.

The gap between who owns the site experience and who can build it just got a lot smaller.

And the next step, simply describing the change instead of building it manually, is next.

Login to Made With è����Ƶ to see Visual Editor in action. If you're not a customer yet, and are curious, why don't you book a demo?

, a British online fashion retailer, captured 88% more email signups from their popups. They didn't rewrite the copy. They didn't redesign their site. They just changed when their message appeared.

How did they manage this? Simply, they made the switch from rule-based experience delivery, to an intent-based approach.

And the results across email capture and product recommendations tell a consistent story: rule-based experience delivery forces a single answer on a question that has many right answers.

Rigid, predefined rules can't answer those questions. è����Ƶ signals can. Improving the impact of your onsite experiences is all about sending the right message, at the right time to your customers. We'll show you how Ollie Wilson, Insights Activation Manager at MandM does this with Made With è����Ƶ.

Editor's note: This blog post is a write up based on our first è����Ƶ Live: The session was hosted by Ollie Wilson, Insights Activation Manager at MandM. He showed how Made With è����Ƶ helped deliver better, more appropriate experiences to his customers, getting 88% more email signups.

The problem with rules-based personalisation

Most eCommerce personalisation sits on top of a set of rules. A customer views a Product Landing Page (PLP), then two Product Display Pages (PDPs), then gets hit with an email capture popup.

Or they get served "last viewed" recommendations based on browsing history. Or a basket abandonment email fires after 10 minutes of leaving the site.

These rules work to a point. Delivering the same experiences to every visitor using predefined rules, based on what they've done before gives you a critical foundation, but it puts a ceiling on growth.

They treat the journey as a sequence rather than a state. And a customer's state when they trigger your rules can be completely different depending on who they are, why they're there, and what they're about to do.

MandM saw this clearly in their email capture data. Their rule-based popup was capturing emails, but they were seeing broken journeys. The pop-up was technically firing at the right moment in the sequence. It wasn't firing at the right moment for the person and their intent.

As Ollie Wilson, Insights Activation Manager at MandM, puts it:

"It's not necessarily specific things a customer does in the journey. It's more so the timing and intent really helped us leverage this in a more efficient way."

The argument we're making here is that it's key to make this distinction. Rules track what a customer has done. The moment for you to intervene has gone. è����Ƶ-based experience delivery is issued in real time, predicts what they're about to do, and allows you to take appropriate action.

Pop ups delivered at the right time

The email capture popup is one of the highest-value tools in eCommerce, but also one of the most frequently misused. Use it too early and you interrupt a customer who hasn't found a reason to stay yet. Fire it according to a fixed rule and you'll hit some customers at the peak of their interest, but most others at exactly the wrong moment.

Ollie and his team tested a different approach. Instead of triggering the popup after a visitor hit a fixed sequence of pages, they introduced to identify when a customer was building meaningful engagement.

When those signals crossed a threshold, the popup fired. Exactly at the moment the customer was most receptive.

When talking about this, Ollie said: "We were hitting them at the right time because we knew they were building intent. They were right at the peak of their journey. Whereas before we were very much relying on this rule-based system which potentially wasn't the right time."

The results across three metrics tell the story. And these figures are lifted directly from the numbers Ollie shared during è����Ƶ Live:

- 55% increase in email sign-up rate, the rate at which people served the popup chose to subscribe

- 88% uplift in total emails captured, the volume consequence of that improved rate

- 15% resubscription rate among previously unsubscribed customers

That last number is particularly significant. Lapsed customers don't re-subscribe because of a well-timed popup by accident. They re-subscribe because they were caught at a moment of genuine brand or product affinity, at the right time. This simply isn't possible with rules-based personalisation.

What MandM actually changed

What's actually surprising is how little MandM had to do to arrive at these results.

They were already using for their on-site experiences, including the consent popup. The popup itself, design, copy, offer, stayed exactly the same.

On changes, Ollie says: "To be honest, it was so easy. We already had our consent popup in Bloomreach as a web layer. It was just a trigger we had to change. With being so easy, we could just feed all of the data into Bloomreach and then use that as the trigger for the popup rather than those stringent rule bases."

Agentic campaigns: testing 157 segment combinations at once

The email capture result came from MandM's first phase of work with intent signals. Their second phase went further, introducing a different kind of challenge.

MandM runs an active personalisation testing programme. At any given point, they're running recommendation strategy tests: last viewed versus category affinity versus the Bloomreach Loomi engine versus most popular, and so on.

Each test runs for roughly two weeks, produces results for a specific segment or device type, and then the cycle starts again.

The problem isn't that the testing doesn't work. It's that it's slow. Each test answers one question, for one segment, in one context. And by the time you've worked through a few cycles, the results of the first test may not apply to the next season, the next acquisition cohort, or mobile versus desktop. And not to mention how resource intensive this all is.

Agentic campaigns changed this by running multiple recommendation strategies in parallel, doing the segmentation work automatically.

MandM tested five homepage recommendation strategies simultaneously. Rather than splitting traffic across two variants and waiting two weeks per test, Made With è����Ƶ's optimisation agent tested all five, across 157 unique segment combinations, and allocated each visitor to the strategy most likely to drive Ollie's defined commercial goal; revenue per user.

The result was a 2% increase in revenue per user. But the more valuable output was just how granular MandM could get. Not just "strategy X wins." For MandM it was strategy X wins for loyal mobile customers, strategy Y wins for new desktop visitors, and for your most engaged customers, showing recommendations at all might be the wrong call.

Let that sink in: showing recommendations at all might be the wrong call.

On the PDP, where new customers arriving from paid search land and recommendations have some of the most direct commercial impact, MandM ran a similar test with five strategies including a "hidden" variant (no recommendations shown at all). The result: 4% increase in revenue per user, from 130 unique segment combinations tested.

On the webinar, Colin Spooner, Principal Value Consultant, at Made With è����Ƶ, describes what this looks like inside the platform:

"There's kind of no winners or losers anymore. It just is the best experience to give that visitor at the right time."

Sometimes, doing nothing is the best strategy

In MandM's PDP test, 14% of visitors were allocated to seeing no recommendations at all, and for that segment, it was the highest-performing option.

That segment, as Ollie describes it, is your most loyal customers. The ones who know the site, know what they want, and don't need or want a carousel of "You might also like" items interrupting their path to purchase.

Ollie says: "For a certain subset of customers, your very loyal customers, the ones that know the site, they know what they want, removing recommendations is actually beneficial. Sometimes it can be a bit of a loop for a customer."

The PDP recommendation loop is a real issue. A customer lands on a PDP, clicks a recommendation to another PDP, clicks another, and ends up in a browse abandonment spiral that started as a purchase intent session. It's almost like you're giving them too much to navigate through.

Removing the recommendations breaks the loop and lets the customer do what they came to do.

This can be uncomfortable for personalisation teams to hear whose KPI is coverage, ensuring every visitor gets served something. But it reflects a more mature way of thinking about personalisation: not "show more" but "show what's right, when it's right."

For some customers in some moments, the right thing is nothing.

What MandM's results point to

MandM's results across two distinct experiments expose the same fundamental flaw in how most onsite experiences are built. They're designed to give every customer an answer at predefined moments, when real impact is about giving each customer the right answer for their specific moment.

Rule-based email capture fires at step three of the journey regardless of whether the customer is engaged or about to leave. Sequential recommendation testing finds one winning strategy for one segment, then starts over.

Ollie used intent signals and agentic campaigns both push against that. One changes when you fire an experience based on real-time behavioural signals. The other changes what you show based on continuous, parallel testing across hundreds of segment combinations. The outcome, in both cases, is the same — fewer experiences wasted on the wrong customer in the wrong moment.

For MandM, the next step is applying agentic testing to placement-level messaging. So, buy now pay later, delivery propositions, app downloads, and letting our agent match messages to customer segments in real time across the same placements.

If you enjoyed this blog post, why don't you watch our è����Ƶ Live series over on Failing that, we're going to be running these sessions frequently, so you can sign up here for our next session.

While we're doing CTAs, here's another one: If this has piqued your interest, why don't you book a demo with our team?