Scope of work

Everything a growth team does, running every day.

A connector is only the surface. Below is the work itself: what an analyst, a lifecycle manager, a data scientist and an experimentation lead would do between them, running continuously against your own data.

Scope of work

Everything a growth team does, running every day.

Read the estate

Normally a data engineer, once, then never refreshed.

Map every customer, account, subscription and plan in the systems you already run.
Rebuild the revenue baseline from orders, payments, refunds and credits.
Derive behavioural features from event history without a new pipeline.
Reconcile the same customer across billing, CRM, product and support identities.
Read consent, subscription and channel eligibility state before anything else.
Read contact history so past sends count as pressure on the customer.
Track catalogue, pricing and plan changes as they happen.
Flag data quality breaks that would make a decision unsafe.

Find where revenue is leaking

Normally a quarterly analyst deep dive.

Watch ARPU by cohort, plan, market, channel and tenure for drift that clears noise.
Detect churn risk building in a segment before it shows in the monthly number.
Detect involuntary churn from failed payments, card expiry and retry behaviour.
Spot onboarding steps where activation falls off and revenue never starts.
Spot pricing and packaging mismatch between what people buy and what they use.
Spot product friction that correlates with downgrade and cancellation.
Spot channels and campaigns spending into audiences that would have converted anyway.
Size every finding in revenue, not in percentage points.

Explain why

Normally a two-week investigation pulled off the roadmap.

Run the investigation automatically and return the drivers with their evidence.
Separate mix effects from real behaviour change.
Rank drivers by how much of the movement each one accounts for.
Check whether the same driver is present in comparable segments.
Show the counter-evidence, not only the supporting cut.
Keep the query trail so an analyst can reproduce every number.

Write hypotheses worth funding

Normally a workshop, limited to the ideas in the room.

Write hypotheses continuously across marketing, product, pricing and technical health.
Attach the expected revenue effect and the population it applies to.
Attach the evidence and the assumption each one depends on.
Rank the portfolio by expected value, not by seniority.
Drop hypotheses that a past experiment already answered.
Keep the full portfolio visible, including what was deliberately not funded.

Decide per customer

Normally segment rules refreshed when someone has time.

Choose the next best action for each customer, for each moment.
Arbitrate between every action competing for that same customer.
Apply frequency caps, fatigue and quiet hours before anything is committed.
Respect eligibility, consent, locale and channel preference.
Pick the channel, timing and incentive level, not only the message.
Cap discount and margin exposure at the level finance agreed.
Attach a plain-language reason and an expiry to every decision.
Suppress an action rather than send a weak one, and log why.

Execute in the tools you already run

Normally a ticket, then a slot in next month's calendar.

Write decisions into the CRM, engagement and warehouse systems already in production.
Trigger journeys and campaigns that your lifecycle team owns and can edit.
Update audiences, lists and segments without hand-built rules.
Route offers, retention plays and save flows to the right surface.
Open the work as a draft for approval where a human should sign off.
Recompute idempotently so a replay never double-sends.
Roll a decision batch back cleanly when something looks wrong.
Leave the estate exactly as it was if Markin stops writing.

Prove it caused the revenue

Normally argued about, rarely measured.

Hold back a randomised control group on every decision, not one global holdout.
Read uplift in revenue per customer against that control.
Report retention, ARPU, margin and contact pressure side by side.
Detect and discount cannibalisation between competing actions.
Stop an experiment early when the evidence is conclusive either way.
Refuse to call a result that has not cleared the evidence standard.
Publish the readout in the same place for every experiment.

Retire, govern and hand over

Normally nobody's job, so nothing is ever switched off.

Retire programmes automatically when they stop beating control.
Re-test assumptions that decay, such as price sensitivity and seasonality.
Log every read, decision and write with its reason for audit.
Keep personal data in your systems and act on it in place.
Show the whole decision trail when legal, finance or an auditor asks.
Hand the team a portfolio they can read, question and overrule.