Nexie
Sign up

Analytics & Learning Agent

Campaigns that get smarter with every send.

Nexie learns from campaign performance at the micro-segment level — what tone, offer, and message works for whom — and applies those learnings to future campaigns, with your approval.

Book a call →Sign up for free
Self-improvement loopRunning · continuous
  1. ProposedPropose

    Two angles drafted for loyalists

    VIP early accesspicked
    15% off winback
  2. SentSend

    VIP early access sent to 412

    VIP early access · 24h

    Hi Mara, your pick is held until midnight…

  3. AnalysedAnalyse

    Early access earned 34% more

    MRMara R.→ loyalists
    Revenue/recipient+$1.84
    Click rate9.2%
  4. Learned ruleLearn

    Early access beats 15% off

    Offer depth locked at 0% for loyalists

    +34% revenue per recipient · 6 sends

↑ Learnings feed back into propose

Segmentation

Segments that build themselves.

Segments are cut from the metrics that predict spend: LTV, order frequency, discount affinity, category affinity, recency, and churn. Each one recomputes as new data arrives, so membership reflects what a customer is doing now.

  • Built on LTV, frequency, discount affinity, recency, and churn
  • Recomputes as new orders, clicks, and opens land
  • Explainable down to the signal
Live segmentationRebuilt 6 min ago
SegmentLTVFreqDisc

High-LTV loyalists

1,840 profiles

Full-price repeat

3,110 profiles

Discount-led buyers

6,420 profiles

Lapsing after one order

4,205 profiles

Learning

Learns what works for every micro segment

The agent tracks how each micro-segment responds across every send: which angle landed, which offer was unnecessary, which product story earned clicks and revenue.

These learnings don't just sit in repots. They are used automatically in subsequent campaigns for personalization to maximise revenue.

  • Micro-segment level learnings
  • Findings consolidated as reusable rules
  • Applied automatically on the next campaign
Learned in the last 30 days3 rules live
  1. Day 3

    Early access beats any discount for loyalists.

    6 sends to High-LTV loyalists: early access earned +34% revenue per recipient against 15% off.

    Now changesOffer depth locked at 0% for this segment.
  2. Day 8

    Deadlines move this segment, product story does not.

    9 sends to discount-led buyers: time-bound subject lines doubled clicks against product storytelling.

    Now changesAngle set to urgency with a 48-hour window.
  3. Day 14

    First-order category outperforms bestsellers on winbacks.

    4 sends to Lapsing after one order: picks from the first-order category reactivated +22% more customers than bestsellers.

    Now changesProduct picks pinned to the first-order category.

Next action — Every rule above is applied automatically on the next campaign.

Catalog

It knows your catalog, not just your customers.

Products are categorised automatically from your Shopify data, then scored against each other: what gets bought together, what follows what, and what a first order usually leads to.

That map is what makes an up-sell or cross-sell campaign specific. The agent already knows which second product belongs next to the one they own.

  • Automatic categorisation, no manual tagging
  • Co-purchase and sequence correlation across order history
  • Feeds product picks in every generated campaign
Catalog affinityStrongest relationship

Owned

Curl Cream

Next best

Leave-In Conditioner

142 customers bought both within 30 days · 0.61 lift

Campaign slot · Hero product slot · Friday VIP send

Other relationships in this catalog

Starter KitRefill DuoUp-sell · 96 together
Repair MaskScalp SerumCross-sell · 71 together

Next action — the Friday VIP send leads with Leave-In Conditioner for every Curl Cream owner.

Experimentation

Runs micro experiments you never get around to.

For each micro-segment the agent quietly trials one variable at a time: the angle, the language, the tone, the position of the offer. Small holdouts, real sends, honest reads.

Winners are promoted into the segment’s rules and used from then on. Losers are retired. Nothing waits for someone to open a report.

  • One variable per test, per micro-segment
  • Winners promoted into the rules after approval
  • The account keeps improving between campaigns
This week's experimentFull-price repeat · 2,140

Hypothesis

Scarcity moves this segment harder than a personal restock note.

Variant A

“Back in your size”

Variant B · winner

“Restocked, 40 left”

+18% click rate · 72h read · 10% holdout

Saved rule · Scarcity subject lines are the default for Full-price repeat.

Two smaller tests also closed this week: warm personal tone for loyalists, offer in the subject line for discount-led buyers.

Next action — the next send to this segment runs with the winning line, no brief required.

CONTINOUS EVOLUTION

Watch, segment, test, apply. Then again.

No weekly review, no analyst chasing reports. The agent closes its own loop, and every other agent inherits the result.

  1. 01

    Watch

    Orders, browsing and email behaviour are read as they land.

    Continuous
  2. 02

    Segment

    Customers are grouped by value, frequency, affinity and interest.

    Self-updating
  3. 03

    Test

    Each micro-segment gets a small experiment on one variable.

    Per segment
  4. 04

    Apply

    Winning angles and offer depth become the default for the next send.

    Automatic

Get started

See what your data
already knows

Connect Shopify and Klaviyo, and Nexie comes back with your segments, what each one responds to, and the campaigns worth running next.

Book a call →Sign up for free