An Agentic Campaign is one that learns and improves on its own, without requiring manual intervention after launch. You add your experiences, choose a strategy, and an AI agent handles the rest: who sees what, when they see it, and how traffic is allocated across every audience segment.
Instead of running one A/B test at a time and locking in a fixed winner, the agent continuously gathers evidence, updates its understanding of what works best for each audience, and shifts traffic accordingly.
The two things the agent does
1. Decides who sees what (Contextual Allocation)
The agent decides which experience each visitor gets based on their full behavioural context: intent level, device, channel, landing page, product affinity, shopper mindset, and more.
The key difference from standard A/B testing: there's no single winner. Different experiences can win for different audiences. A social proof message that works brilliantly for low intent mobile visitors might underperform for returning high intent desktop customers, and the agent learns this automatically.
Think of it as running hundreds of optimisations simultaneously, not one test with one winner.
2. Decides when to show it (One-Shot Optimisation)
For experiences that should fire once per visitor; email capture, discount overlays, exit-intent pop-ups, the agent doesn't just decide who sees it. It optimises when in their journey to show it.
The hypothesis is that the same intervention has very different effects depending on where a visitor is in their session.
Example (Browse Abandonment):
Imagine you launch a Browse Abandonment campaign with three experiences plus a "show nothing" baseline:
A — 10% discount overlay
B — Free shipping reassurance
C — Email capture with first-order offer
Baseline — show nothing
On day one, the agent splits traffic roughly evenly across all four to start gathering evidence. By day seven, it's learned that:
High intent visitors from paid social convert best on C
Desktop visitors who've viewed ≥3 products convert best on B
Low-intent discoverers on category pages are best left alone — Baseline wins
There's no single "winning experience" - each combination of audience and moment gets its own answer, and those answers update as new data arrives.
How it learns
When a campaign first launches, the agent starts by spreading traffic fairly across all your experiences. This is the Exploring phase; it's gathering data, not yet making strong calls.
As patterns emerge, it shifts more traffic toward the better-performing experiences while keeping some traffic on the alternatives to keep learning. It never fully commits. This is the Optimising phase, and it happens gradually as confidence builds.
The agent also uses shared learning: insights from one visitor group can inform decisions in another, which helps it optimise faster when data is still sparse.
All of this happens automatically. You don’t need to set thresholds, pick a winner, or make manual decisions. The agent re-scores every audience x experience combination once per night using the previous day's evidence. That's why allocations shift day-by-day rather than hour-by-hour, and why the fastest-learning campaigns tend to be ones with high-volume, clear-signal goals, such as conversions or revenue per user.
The constraints the agent works within
The agent isn't running without boundaries. A handful of parameters are fixed at platform level, and a few others are defaults you can change. Together they shape what the agent is allowed to do, how quickly it can act, and how much evidence it needs before committing.
What you decide:
Experiences per campaign: up to 5, with at least 2 as the practical minimum. This is a hard cap. It exists to keep per-experience sample sizes deep enough for the model to learn from, rather than stretching traffic thin across dozens of arms.
Control Options: rather than fixing the control share manually, optimised control is enabled by default. It starts the control share higher and reduces it as confidence in results grows. You can still set minimum and maximum boundaries. Alternatively, you can adjust control share from campaign settings. Drop it lower once you're confident in performance; raise it if you want a tighter measurement baseline.
What the agent builds for you:
Segments: up to 500 contextual combinations per campaign. This is the cardinality cap; the agent iteratively reduces its feature selection to fit under this limit so each segment stays sample-rich enough to train on.
Timing variations: up to 75 moment-based triggers per campaign, on strategies where timing optimisation is enabled.
What it needs before it can go live:
1,000 users matching the strategy's eligibility rules, plus 10 goal events within those users. Both thresholds must be cleared. The agent checks every four hours until they are. Until then the campaign is staged and ready but not firing.
How often it updates:
Nightly retraining on a rolling 90-day training window of behavioural data. That cadence is why you'll see allocations shift day-by-day rather than hour-by-hour, and why the learning window always reflects recent trading conditions rather than historical behaviour that's no longer representative.
The control variant
Every agentic campaign keeps a control group. These are visitors who see your default site experience, with no personalisation applied.
This is how the campaign measures uplift. The agent compares personalised visitors against the control to understand the real impact of the campaign.
By default, the size of the control group is managed automatically using Optimised Control, which adjusts the control share over time as confidence in results grows.
Control as an agent experience
We also suggest you also add a control as a variant to the Agent Experiences. If none of your experiences are outperforming, the agent will shift traffic toward whichever option is performing least badly, including the control if it is included as a variant..
What you'll see in the report
The Agentic Report gives you visibility into where the agent is in this process at two levels:
Campaign phase
Exploring (Early & Late); the agent is still gathering evidence. Many segments have roughly even allocation across experiences. This is normal early on.
Optimising; the agent is confident and directing traffic to what's working. Most segments now have a clear winner with dominant allocation.
Campaign performance rating
The report shows an overall confidence rating for how the campaign as a whole is performing:
Uncertain / Promising; early stage, not enough data yet. Normal.
Good / Great; the model is confident the campaign is working.
Unlikely to Beat; the campaign is not performing. Consider adding a baseline "Do Nothing" experience so the agent has somewhere to route traffic rather than continuing to serve something that isn't working.
Note: the confidence labels are a useful signal, but the real story is in the allocation numbers. Because the agent uses shared learning across segments, a variant may have low traffic not because it definitively lost, but because the model has already learned, from similar segments, that it's unlikely to work for that audience.