How government data teams go fully agentic and autonomous

Key takeaways

• •Who this is for. Teams that own program data (claims, enrollment, benefits), web analytics and open data in agencies, often with contractor and digital-service teams.
• •The problem today. Releases that slip a month, per-file privacy reviews and documentation that lags.
• •What changes. Releases run as missions with quality and threshold checks, so the monthly release ships on schedule. De-identification rules apply consistently, so only exceptions need review.
• •What stays with your people. Releases and access to identified data: these carry public trust, so the program lead approves.
• •The result. More releases, on time, with privacy enforced.

The PRD for agentic government data teams

This is the requirements document we would write with you for your team. Everything below expands on it.

What going fully agentic and autonomous means for government data teams

• •Put your data pipeline on autopilot. Releases run as missions with quality and threshold checks, so the monthly release ships on schedule.
• •Run the data back office without the busywork. The work that fills the week today moves to agents: releases that slip a month, per-file privacy reviews and documentation that lags.
• •Scale data without scaling headcount. De-identification rules apply consistently and documentation is generated as data changes, so the data you manage grows without the team having to.
• •Get the plumbing off your plate. More releases, on time, with privacy enforced.

Who this is for

Teams that own program data (claims, enrollment, benefits), web analytics and open data in agencies, often with contractor and digital-service teams. Titles include Chief Data Officer, Data Product Manager and Data Strategy PM.

The shift

Agencies are asked to release more data, support AI and protect privacy at once, often with small teams and contractors. Agents can automate the profiling, de-identification, documentation and quality work behind every release.

The product you ship

• •Program data for analytics and research
• •Public and open data releases
• •De-identified research files
• •Web analytics across sites

Where the week goes

• •Releases assembled by hand.
• •De-identification reviewed per file.
• •Documentation lags.
• •Data requests queue.
• •Legacy systems change formats.

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 14% 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

These are the impact metrics we move for government data teams:

• •Access decision: from about 2 weeks to ~1 h
• •Documentation: from about a week to ~1 h
• •Partner layout mapped: from about 3 days to under 1 h

Across the routine work in this domain:

The biggest change is Access decision: from about 2 weeks to ~1 h.

Use cases, in depth

A quarterly program release

Today. Analysts assemble and check each release.

With Data Workers. Autopilot runs it with quality, threshold and documentation checks.

What changes. Releases ship on schedule.

Preparing data for ML

Today. A program wants claims data ready for ML.

With Data Workers. Profiling, de-identification and documentation run as a mission.

What changes. Data is ML-ready in weeks.

A legacy format change

Today. A state system changes its file layout.

With Data Workers. Schema Evolution maps it with tests.

What changes. No broken loads.

Agents working together: A partner state file that changed layout

Minute by minute

Illustrative example. State files land in a government cloud; releases publish monthly.

Without the agents, the release slips a month.

The agents on the job

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:

• •Releases run as missions with quality and threshold checks, so the monthly release ships on schedule.
• •De-identification rules apply consistently, so only exceptions need review.
• •Documentation is generated as data changes, so every release is documented.

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.

• •Releases and access to identified data always goes to a named approver: these carry public trust, so the program lead approves.
• •Policy decisions: these stay with people.

Once a deployment has matured, here is how that ladder plays out across task classes:

Documentation closes autonomously 88% of the time. For Releases and identified data, 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: Government cloud environments; Databricks or Snowflake; SAS and legacy systems; open data portals; analytics for public websites. 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

Agencies must protect personal data and document releases. Data Workers runs in your environment, applies de-identification rules and logs every action.

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 government 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. Data portals publish; Data Workers prepares, checks and documents what they publish.

The case for your CTO

What this replaces. Releases that slip a month, per-file privacy reviews and documentation that lags.

What your team gets back. More releases, on time, with privacy enforced.

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; releases and access to identified data stay at L2 with a named approver; and one org-wide stop halts all autonomous work.

Why now. AI mandates and transparency rules raise the volume.

The first win. One monthly 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 government 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; releases and access to identified data always go to a named approver.
• •Autonomous, under your governance. Routine work runs on its own: releases run as missions with quality and threshold checks, de-identification rules apply consistently, and documentation is generated as data changes. Your team governs the agents instead of doing the upkeep.
• •The agentic enterprise. Agencies will publish program data on schedule with privacy and documentation built in, and prepare data for AI programs without large new teams.

You choose the altitude, every step is visible and reversible, and the pilot below is the first rung.

The pilot: how government data teams start

The pilot is how your team proves the value on its own data before committing.

• •What we connect. Government cloud environments; Databricks or Snowflake; SAS and legacy systems; open data portals; analytics for public websites, over MCP, inside your infrastructure. Nothing migrates.
• •Scope. One monthly 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. Releases run as missions with quality and threshold checks and de-identification rules apply consistently start running on reversible work. Releases and access to identified data stay at L2 with a named approver.
• •At day 30. We review the impact metrics against your baseline:

• •Access decision: from about 2 weeks to ~1 h
• •Documentation: from about a week to ~1 h
• •Partner layout mapped: from about 3 days to under 1 h
• •the share of documentation 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 34% of agent actions run fully autonomously while releases stay with a named approver.

FAQ

Can it run in a government cloud? Agents run in your environment.

Who approves releases? A named program lead.

Does it document releases? Documentation is generated and kept current.

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

• •USAJOBS, CMS Office of Enterprise Data and Analytics: https://www.usajobs.gov/job/483258500
• •GSA TTS, Data Analytics Product Managers: https://federalist-a2423046-fe43-4e75-a2ef-2651e5e123ca.sites.pages.cloud.gov/preview/gsa-tts/tts.gsa.gov/echo-summer20203/join/Data-Analytics-Product-Managers/
• •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

Related: Best practices for agentic public program and government data