Markin + Census integration
Decision tables synced by the pipeline you already trust.
What is a Census AI agent?
A Markin and Census setup uses a table as the integration surface. Markin writes decisions to the warehouse; Census syncs them to the tools that need them. Turning the sync off returns the estate to exactly its previous state.
The integration surface is a table, not an API contract. That keeps the connection reversible: turn the sync off and the estate is exactly as it was.
What Markin reads
- Sync definitions and field mappings
What Markin writes back
- Warehouse decision tables consumed by existing syncs
How the connection works
| Pattern | What it means here |
|---|---|
| Attribute write-back | Markin writes the decision onto the customer profile; your existing journeys read it as an entry condition. Latency is the platform's sync interval. |
What can you ask Markin to do in Census?
- How do I activate model output through Census?
- Can Census sync a next best action to Salesforce and Braze?
- How do I keep an AI decision layer reversible?
- What table shape should a decision sync use?
What Markin does in Census
- 01Read sync definitions and field mappings.
- 02Write decision tables in the shape the syncs already read.
- 03Attach a reason and an expiry to every decided action.
- 04Keep holdout membership beside the decision to prevent leakage.
- 05Recompute idempotently so re-syncs never duplicate sends.
- 06Version each write so a bad batch can be rolled back.
- 07Leave delivery, retries and alerting with Census.
- 08Remove the table and nothing downstream changes shape.
Scope of work
The growth work behind Census
The list above is what Markin touches in Census. 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.
Read the estate
Normally a data engineer, once, then never refreshed.
- Derive behavioural features from event history without a new pipeline.
- Reconcile the same customer across billing, CRM, product and support identities.
Find where revenue is leaking
Normally a quarterly analyst deep dive.
- 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.
Explain why
Normally a two-week investigation pulled off the roadmap.
- 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.
- Keep the full portfolio visible, including what was deliberately not funded.
- Write hypotheses continuously across marketing, product, pricing and technical health.
Decide per customer
Normally segment rules refreshed when someone has time.
- 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.
- Recompute idempotently so a replay never double-sends.
- Roll a decision batch back cleanly when something looks wrong.
Prove it caused the revenue
Normally argued about, rarely measured.
- Report retention, ARPU, margin and contact pressure side by side.
- Detect and discount cannibalisation between competing actions.
Retire, govern and hand over
Normally nobody's job, so nothing is ever switched off.
- Keep personal data in your systems and act on it in place.
- Show the whole decision trail when legal, finance or an auditor asks.
Census questions
- How does Markin connect to Census?
- Attribute write-back. Markin writes the decision onto the customer profile; your existing journeys read it as an entry condition. Latency is the platform's sync interval.
- What does Markin read from Census?
- Sync definitions and field mappings.
- What does Markin write back into Census?
- Warehouse decision tables consumed by existing syncs
- Do we have to move our data to Markin?
- No. Markin reads from your warehouse, product events and operational systems in place, on your compute, under the access rules your data team already set. Nothing is copied into a separate customer base and there is no vendor-side profile store to migrate off later.
- Does Markin replace our engagement platform or CDP?
- No, and it should not. Your engagement platform keeps the channel, the templates, the deliverability and the governance. Your CDP keeps identity and consent. Markin adds the layer neither has: deciding which action deserves to exist for each customer, and proving it against a holdout.
- What if the system we use is not listed?
- The four activation patterns cover almost everything: attribute write-back, triggered event, decision API and direct surface rendering. Any system that exposes an API, accepts a table, or can read a warehouse column can receive decisions. New connectors are built during deployment, typically in days.