How people and workforce data teams go fully agentic and autonomous
Going fully agentic and autonomous does not mean adding a chatbot to the warehouse. For people and workforce data teams, it means climbing from agents that assist, to agents that run the routine work under your governance, to a data back office that largely runs itself: building and fixing pipelines, catching bad data before it reaches a number, keeping definitions and access governed and verifying every outcome, while people set direction and approve what matters. This is what that climb looks like, step by step.
Key takeaways
- •Who this is for. Teams that own employee, candidate and labor-market data: people analytics inside large employers and labor-market insights teams at professional networks and HR platforms.
- •The problem today. Small-cell exposures in releases, weeks of wrong headcount after HRIS migrations and research request queues.
- •What changes. Privacy thresholds are enforced before every release, so no small cell ever ships. HRIS changes are mapped overnight, so headcount stays right through migrations.
- •What stays with your people. Access to sensitive fields and external releases: these expose people, so the people analytics lead approves.
- •The result. Workforce insights that are trusted and private by construction.
The PRD for agentic people and workforce data teams
This is the requirements document we would write with you for your team. Everything below expands on it.
| Who | People analytics, HR data, workforce insights and labor-market data teams at platforms and large employers |
| The job | Workforce and labor-market data that is private, governed and trusted. |
| Environment | Workday or SuccessFactors; ATS systems; Snowflake or BigQuery; dbt; BI. |
| Constraints | Access to sensitive fields and external releases always go to a named approver. Employee and member data are protected by privacy laws. |
| Success is measured by | Definition question: from about a day to seconds; Sensitive access: from about a week to 5 min; Threshold check: from about 2 days to minutes; catalog upkeep closed autonomously 88% of the time. |
| Owned by | A Head of People Data Products, with domain owners as named approvers. |
| Pilot scope | Threshold enforcement on one release at L2. |
What going fully agentic and autonomous means for people and workforce data teams
- •Put your data pipeline on autopilot. Privacy thresholds are enforced before every release, so no small cell ever ships.
- •Run the data back office without the busywork. The work that fills the week today moves to agents: small-cell exposures in releases, weeks of wrong headcount after HRIS migrations and research request queues.
- •Scale data without scaling headcount. HRIS changes are mapped overnight and partner extracts are built as missions, so the data you manage grows without the team having to.
- •Get the plumbing off your plate. Workforce insights that are trusted and private by construction.
Who this is for
Teams that own employee, candidate and labor-market data: people analytics inside large employers and labor-market insights teams at professional networks and HR platforms. Titles include People Data Product Manager, Workforce Insights Lead and Economic Graph data roles.
The shift
Employers want workforce planning and skills insight, platforms sell labor-market data, and both depend on personal data with strict rules. Agents can enforce privacy thresholds and access policies while keeping the data fresh and consistent.
The product you ship
- •Workforce and skills datasets
- •Aggregated labor-market metrics
- •People analytics for HR and leadership
- •Data shared with public-sector partners
Where the week goes
- •Privacy thresholds checked by hand.
- •HRIS changes break models.
- •Access requests for sensitive fields.
- •Definitions of headcount and attrition differ.
- •Research requests queue up.
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 |
|---|---|---|
| Privacy thresholds | Reviewed by hand | Enforced in the pipeline |
| HRIS changes | Broken models | Mapped on arrival |
| Sensitive access | Tickets | Policy-based |
| Headcount definitions | Many | One |
| Research requests | Queue | Days |
These are the impact metrics we move for people and workforce data teams:
- •Definition question: from about a day to seconds
- •Sensitive access: from about a week to 5 min
- •Threshold check: from about 2 days to minutes
Across the routine work in this domain:
The biggest change is Sensitive access: from about a week to 5 min.
Use cases, in depth
A labor-market release
Today. Each release is checked for small cells by hand.
With Data Workers. Threshold rules fail any cell below minimum before publish.
What changes. Releases ship on schedule.
An HRIS migration
Today. A new HRIS changes job codes.
With Data Workers. Schema Evolution maps codes; Quality Monitoring checks headcount ties.
What changes. Workforce dashboards stay right.
A partner data request
Today. A government partner asks for regional skills data.
With Data Workers. Pipeline Building builds an aggregated extract; Access & Governance scopes it.
What changes. Partners get data in days.
Agents working together: An HRIS migration that changed job codes
Minute by minute
Illustrative example. HRIS data lands in Snowflake nightly; workforce dashboards refresh at 07:00.
| Time | Who | What happens |
|---|---|---|
| Mon 01:00 | HRIS | New job codes go live |
| 01:10 | Autonomous Data-Conductor | Code changes detected |
| 01:40 | Pipeline Building agent | Mapping with tests proposed |
| 06:40 | Spellbook Data Catalog | Lead approves |
| 07:00 | Dashboards | Headcount ties |
Without the agents, headcount is wrong for weeks.
The agents on the job
| Agent | What it does for you | Tools it calls |
|---|---|---|
| Data Security | Classifies personal and sensitive fields | scan_pii, review_pii_writes, pci_card_data_masking |
| Data Access & Governance | Role- and purpose-based access | provision_access, check_policy, request_governance_review, generate_audit_report |
| Quality Monitoring | Threshold and tie-out checks | set_sla, run_quality_check, get_anomalies, create_quality_tests_for_pipeline |
| Schema Evolution | HRIS and source changes | detect_schema_change, validate_schema_compatibility, generate_migration, rollback_migration |
| Pipeline Building | Aggregated products | generate_pipeline, validate_pipeline, sandbox_test, deploy_pipeline |
| Data Context & Catalog | Governed definitions of headcount, attrition and skills | 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:
- •Privacy thresholds are enforced before every release, so no small cell ever ships.
- •HRIS changes are mapped overnight, so headcount stays right through migrations.
- •Partner extracts are built as missions, so requests are answered in days.
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.
- •Access to sensitive fields and external releases always goes to a named approver: these expose people, so the people analytics lead approves.
- •Policy decisions: these stay with people.
Once a deployment has matured, here is how that ladder plays out across task classes:
Catalog upkeep closes autonomously 88% of the time. For Sensitive access and releases, 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: Workday or SuccessFactors; ATS systems; Snowflake or BigQuery; dbt; BI. 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
Employee and member data are protected by privacy laws. Data Workers enforces thresholds and access policy and logs every grant.
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 people and workforce data 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. HR analytics tools report; Data Workers keeps the data under them correct and private.
The case for your CTO
What this replaces. Small-cell exposures in releases, weeks of wrong headcount after HRIS migrations and research request queues.
What your team gets back. Workforce insights that are trusted and private by construction.
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; access to sensitive fields and external releases stay at L2 with a named approver; and one org-wide stop halts all autonomous work.
Why now. AI skills planning needs clean people data.
The first win. Threshold enforcement on one release at L2. 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 people and workforce data 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; access to sensitive fields and external releases always go to a named approver.
- •Autonomous, under your governance. Routine work runs on its own: privacy thresholds are enforced before every release, hRIS changes are mapped overnight, and partner extracts are built as missions. Your team governs the agents instead of doing the upkeep.
- •The agentic enterprise. People data teams will publish workforce and skills insight on a regular cadence with privacy enforced by construction, and AI workforce planning will run on governed data.
You choose the altitude, every step is visible and reversible, and the pilot below is the first rung.
The pilot: how people and workforce data teams start
The pilot is how your team proves the value on its own data before committing.
- •What we connect. Workday or SuccessFactors; ATS systems; Snowflake or BigQuery; dbt; BI, over MCP, inside your infrastructure. Nothing migrates.
- •Scope. Threshold enforcement on one release at L2.
- •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. Privacy thresholds are enforced before every release and hRIS changes are mapped overnight start running on reversible work. Access to sensitive fields and external releases stay at L2 with a named approver.
- •At day 30. We review the impact metrics against your baseline:
- •Definition question: from about a day to seconds
- •Sensitive access: from about a week to 5 min
- •Threshold check: from about 2 days to minutes
- •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 40% of agent actions run fully autonomously while sensitive access and external releases stay with a named approver.
FAQ
Is employee data safe? Access is policy-based and logged.
Can it enforce small-cell rules? Yes, as blocking checks.
Does it handle HRIS migrations? Yes, as a mission.
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
- •LinkedIn Engineering, From the Economic Graph to economic insights: https://engineering.linkedin.com/blog/2023/from-the-economic-graph-to-economic-insights--building-the-infra
- •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