A playbook for the Customer 360 Product Lead
If you are a Customer 360 Product Lead, this is your playbook. It covers what your team ships, where its week goes today, the use cases agents take over first, the autonomy you can safely grant in each domain, and what to show leadership after the first quarter.
Key takeaways
- •Who this is for. Teams that unify customer identity across CRM, commerce, marketing, support and product into one profile and activate it: Salesforce Data Cloud and CDP owners, Customer 360 product teams, martech data engineering.
- •The problem today. Opted-out customers reaching ad platforms, household collisions found through complaints and broken ingestion after source changes.
- •What changes. Consent freshness is checked before every audience sync, so no opted-out customer is ever targeted. Merge and match rates are monitored, so a bad identity rule is caught on its first spike.
- •What stays with your people. Identity rules, consent logic and live audiences: these decide who receives what, so the CDP owner approves.
- •The result. A CDP team whose audiences convert and never violate consent.
The PRD for agentic Customer 360 and CDP teams
This is the requirements document we would write with you for your team. Everything below expands on it.
| Who | CDP, Customer 360, martech and CRM data teams at retailers, brands, banks and SaaS companies |
| The job | One customer profile every system agrees on. |
| Environment | Salesforce Data Cloud or a composable CDP on Snowflake/BigQuery; Segment or RudderStack; Hightouch or Census; dbt; consent platforms. |
| Constraints | Identity rules, consent logic and live audiences always go to a named approver. Privacy laws require opt-outs to be honored and personal data to be tracked. |
| Success is measured by | Bad merge traced: from about 3 days to 15-20 min; Segment jump explained: from about 2 days to 15-20 min; Consent freshness restored: from about a day to 8-15 min; catalog upkeep closed autonomously 88% of the time. |
| Owned by | A Customer 360 Product Lead, with domain owners as named approvers. |
| Pilot scope | Consent freshness and merge monitoring on one brand at L3. |
What going fully agentic and autonomous means for Customer 360 and CDP teams
- •Put your data pipeline on autopilot. Consent freshness is checked before every audience sync, so no opted-out customer is ever targeted.
- •Run the data back office without the busywork. The work that fills the week today moves to agents: opted-out customers reaching ad platforms, household collisions found through complaints and broken ingestion after source changes.
- •Scale data without scaling headcount. Merge and match rates are monitored and source changes are mapped on arrival, so the data you manage grows without the team having to.
- •Get the plumbing off your plate. A CDP team whose audiences convert and never violate consent.
Who this is for
Teams that unify customer identity across CRM, commerce, marketing, support and product into one profile and activate it: Salesforce Data Cloud and CDP owners, Customer 360 product teams, martech data engineering. Titles include Salesforce PM (Marketing & Data Clouds), Customer 360 Lead and CDP Product Owner.
The shift
Every company now runs a customer data platform and expects AI agents to personalize on top of it. The profile is only as good as identity resolution, consent and freshness behind it, and those break quietly. Agents can keep identity, consent and segments correct so marketing and service teams trust what they activate.
The product you ship
- •Unified customer profiles
- •Segments and audiences for activation
- •Consent and preference data
- •Customer context for AI agents in service and sales
Where the week goes
- •Identity merges go wrong and profiles collide.
- •Consent changes are slow to reach audiences.
- •Source schema changes break ingestion.
- •Segment counts jump without explanation.
- •Every new source needs mapping.
Add it up and upkeep is most of the team's week. Here is how a typical week splits today, and once agents own the back office:
Time spent on new data products moves from 16% of the week to 50%. Most of the rest becomes review: people steer and approve agent work instead of doing it by hand.
Then and now
| Work | Today | With Data Workers |
|---|---|---|
| Identity resolution | Merges debugged after complaints | Match rates monitored, bad merges traced |
| Consent propagation | Hours or days | Freshness SLA on suppression |
| Source changes | Broken ingestion | Mapped on arrival |
| Segment jumps | Investigated for days | Traced on the first jump |
| New sources | Weeks | Days |
These are the impact metrics we move for Customer 360 and CDP teams:
- •Bad merge traced: from about 3 days to 15-20 min
- •Segment jump explained: from about 2 days to 15-20 min
- •Consent freshness restored: from about a day to 8-15 min
Across the routine work in this domain:
The biggest change is Bad merge traced: from about 3 days to 15-20 min.
Use cases, in depth
Profiles that collided
Today. A shared email merges two households; offers go to the wrong person.
With Data Workers. Quality Monitoring watches merge rates, Incident Debugging traces the rule, and Conductor proposes the fix at L2.
What changes. Bad merges are caught on the first spike.
Opt-outs before the next audience
Today. A consent change must reach audiences before the next sync.
With Data Workers. set_sla on the suppression table; a failing check blocks the sync.
What changes. No audience goes out with an opted-out customer.
Customer context for service agents
Today. AI service agents need the same profile as marketing.
With Data Workers. Context Wizard exposes governed profile definitions to every agent.
What changes. Agents and humans see the same customer.
Agents working together: Opt-outs that reach every audience
Minute by minute
This is an illustrative example. Consent lands from a preference center into Snowflake; a dbt model builds audiences synced by reverse ETL at 21:00.
| Time | Who | What happens |
|---|---|---|
| 18:00 | Preference center | 1,200 opt-outs recorded |
| 19:30 | Quality Monitoring agent | Suppression table stale against SLA |
| 19:32 | Incident Debugging agent | diagnose_incident: consent export failed |
| 19:40 | Incident Debugging agent | Export rerun; table fresh |
| 20:10 | Quality Monitoring agent | Audience check passes |
| 21:00 | Reverse ETL | Sync runs without suppressed IDs |
Without the agents, the sync sends opted-out customers to ad platforms.
The agents on the job
| Agent | What it does for you | Tools it calls |
|---|---|---|
| Connectors and Data Ingestion | Land CRM, commerce, support and product sources | get_connector_status, trigger_airflow_dag, get_dbt_run_history |
| Schema Evolution | Maps source changes into the profile model | detect_schema_change, validate_schema_compatibility, generate_migration, rollback_migration |
| Quality Monitoring | Match rates, merge anomalies and consent freshness | set_sla, run_quality_check, get_anomalies, create_quality_tests_for_pipeline |
| Incident Debugging | Traces segment jumps and bad merges | diagnose_incident, get_root_cause, prepare_backfill, execute_backfill |
| Data Security | Classifies personal data | scan_pii, review_pii_writes, pci_card_data_masking |
| Data Context & Catalog | Governed profile and segment definitions | trace_cross_platform_lineage, blast_radius_analysis, define_business_rule, generate_documentation |
Data Context Wizard keeps one governed graph of definitions, lineage and owners that every agent and person answers from. Autonomous Data-Conductor runs each job from detection to a verified result. Spellbook Data Catalog is where your team approves, audits and rolls back, and asks questions in plain English.
What goes on autopilot
Once a domain has earned it, this work runs on its own, and each item removes a problem your team deals with today:
- •Consent freshness is checked before every audience sync, so no opted-out customer is ever targeted.
- •Merge and match rates are monitored, so a bad identity rule is caught on its first spike.
- •Source changes are mapped on arrival, so profiles stop breaking when a commerce field moves.
Where your people stay in charge
Agents never get blanket access. Each domain has its own autonomy level, set by you, and it only rises when the receipts show the agents are reliable. Everything starts at L1, observing only; reversible upkeep such as reruns, staging fixes, documentation and cleanup is usually first to run on its own.
- •Identity rules, consent logic and live audiences always goes to a named approver: these decide who receives what, so the CDP owner approves.
- •Campaign decisions: these stay with marketing.
Once a deployment has matured, here is how that ladder plays out across task classes:
Catalog upkeep closes autonomously 88% of the time. For Identity rules and live audiences, autonomous closure is 0% by design.
What happens when an agent is wrong
- •At L2 propose, nothing changes until a named person approves. The proposal shows the full diff, the blast radius and how to roll it back. Unanswered requests expire and escalate.
- •At L3 act, reversibly, every change keeps a rollback point, and Conductor verifies the downstream number after the change. If verification fails, the change is reversed and the domain drops a level.
- •No agent approves or promotes its own work. Autonomy only grows on evidence, per repair class, and repeated errors shrink scope automatically.
- •One org-wide stop halts all autonomous dispatch, and every action lands in a hash-chained audit trail you can export with generate_audit_report.
How it fits your stack
Data Workers connects to what you already run: Salesforce Data Cloud or a composable CDP on Snowflake/BigQuery; Segment or RudderStack; Hightouch or Census; dbt; consent platforms. Each agent is an MCP server, so the same agents work inside Claude Code, Cursor or Codex and in Slack or Teams through Spellbook. Nothing migrates.
- •Runs in your infrastructure with your credentials and your model key. The hosted Autonomous Data-Conductor sees workflow metadata only, never rows.
- •Uses the access you already govern. Agents act under scoped service identities and your existing roles; every grant goes through provision_access and is logged.
- •Proposes changes as diffs in your dbt project, orchestrator and warehouse, with blast radius, tests and a rollback point, and applies them only at the autonomy level you set for that domain.
- •Open-source core. The Apache-2.0 community edition ships 11 agents and 160+ MCP tools, so your engineers can read exactly what the agents call.
Governance and regulation
Privacy laws require opt-outs to be honored and personal data to be tracked. Data Workers keeps consent tables fresh, blocks syncs that fail checks and maps personal data flows; your consent platform records the choice.
Data Workers doesn't make you compliant; your controls, people and assessors do. It supplies controls and evidence wherever agents touch data. Not legal advice.
The alternatives Customer 360 and CDP teams weigh
Build it yourselves. A strong team can wire a coding agent to MCP servers for the warehouse and dbt. The work is everything around it: routing approvals to the right owner, blast radius, rollback, receipts, and current context about every other system.
Observability, catalogs and point tools. Observability alerts, catalogs document, and quality tools test. Data Workers takes their signals, diagnoses, proposes the fix, verifies it and leaves the receipt.
Platform-native agents. Snowflake made its managed MCP server and Cortex Agents generally available on Nov 4, 2025, and Databricks made Genie One generally available on Jun 16, 2026. They are excellent inside their platform; this work crosses the source systems, orchestrator, warehouse and BI, and Data Workers works across all of them.
In this space specifically. CDPs unify and activate; Data Workers keeps the data under them correct and the consent checks enforced.
The case for your CTO
What this replaces. Opted-out customers reaching ad platforms, household collisions found through complaints and broken ingestion after source changes.
What your team gets back. A CDP team whose audiences convert and never violate consent.
Integration effort. Connecting is configuration, not a migration. The agents attach over MCP to the warehouse, orchestrator, dbt project and source systems you already run, under the roles you already govern, inside your own infrastructure. Your engineers can read every tool the agents call in the open-source core.
Risk and control. Autonomy is set per domain. Everything starts at L1, observing only; reversible work moves up only when the receipts justify it; identity rules, consent logic and live audiences stay at L2 with a named approver; and one org-wide stop halts all autonomous work.
Why now. AI personalization raises the cost of a bad profile.
The first win. Consent freshness and merge monitoring on one brand at L3. The pilot below lays out the scope, what you see each week and the cost.
The climb: from assisted to autonomous to agentic
Our thesis is that the data platform climbs the way analytics did, in stages, and that the hard part of data work was never knowing what to do but doing it. For Customer 360 and CDP teams, the climb looks like this:
- •Assisted. Agents work alongside your team. They read the whole stack, show what needs doing and propose every fix with a receipt; identity rules, consent logic and live audiences always go to a named approver.
- •Autonomous, under your governance. Routine work runs on its own: consent freshness is checked before every audience sync, merge and match rates are monitored, and source changes are mapped on arrival. Your team governs the agents instead of doing the upkeep.
- •The agentic enterprise. CDPs will become the customer context layer for every AI agent in the company, and consent will be enforced by the data itself. Teams that automate identity and consent checks first will personalize fastest with the least risk.
You choose the altitude, every step is visible and reversible, and the pilot below is the first rung.
The pilot: how Customer 360 and CDP teams start
The pilot is how your team proves the value on its own data before committing.
- •What we connect. Salesforce Data Cloud or a composable CDP on Snowflake/BigQuery; Segment or RudderStack; Hightouch or Census; dbt; consent platforms, over MCP, inside your infrastructure. Nothing migrates.
- •Scope. Consent freshness and merge monitoring on one brand at L3.
- •First week. Agents run at L1 across the scoped domain. They map every pipeline, definition and lineage path and show the fixes they would have made, with receipts, so your team sees the value before anything changes.
- •By week two. Consent freshness is checked before every audience sync and merge and match rates are monitored start running on reversible work. Identity rules, consent logic and live audiences stay at L2 with a named approver.
- •At day 30. We review the impact metrics against your baseline:
- •Bad merge traced: from about 3 days to 15-20 min
- •Segment jump explained: from about 2 days to 15-20 min
- •Consent freshness restored: from about a day to 8-15 min
- •the share of catalog upkeep closed autonomously, targeting 88% as the deployment matures
- •What you decide. Whether to expand to the next domain. The pilot fee is credited in full against the first year.
- •Cost. Start with a pilot ($7,500 one-time, credited in full against the first year). Scale is from $1,000 a month and Enterprise from $3,000 a month, billed annually, with unlimited seats, no usage meter and no markup on model spend. See pricing.
The pilot is the start of a longer curve:
By month 12, more than 44% of agent actions run fully autonomously while identity rules and live audiences stay with a named approver.
FAQ
Does it replace our CDP? No; it keeps the data under it correct.
Can it push opt-outs to ad platforms? Syncs stay with your tools; Data Workers checks them first.
What about identity rules? Rule changes are proposed at L2.
Where do the agents run? In your infrastructure, with your credentials and model key. The hosted Conductor sees workflow metadata only.
Do we have to migrate anything? No. Your warehouse, dbt project, orchestrator, catalog and BI stay where they are.
Sources
- •Salesforce, PM/Sr PM Marketing Cloud posting: https://careers.salesforce.com/en/jobs/jr337926/product-managersr-product-manager-marketing-cloud/
- •AAA, Salesforce PM – Marketing & Data Clouds: https://careers.mwg.aaa.com/salesforce-product-manager-marketing-data-clouds/job/44BEEFB043BA253BA930C4D5A92D52EA
- •Data Workers pricing: https://dataworkers.io/pricing/
- •Data Workers open-source repository (tool registrations): https://github.com/DataWorkersProject/dataworkers-claw-community
- •Snowflake, managed MCP server and Cortex Agents GA release note (Nov 4, 2025): https://docs.snowflake.com/en/release-notes/2025/other/2025-11-04-cortex-agents-mcp
- •Databricks, Genie One launch (Jun 16, 2026): https://www.databricks.com/company/newsroom/press-releases/databricks-launches-genie-one-all-new-agentic-coworker-every-team