A playbook for the Head of Underwriting and Claims Data

Key takeaways

• •Who this is for. Teams that own policy, quote, exposure, bordereaux and claims data and the products built on it: rating inputs, portfolio views, claims analytics and reinsurance submissions.
• •The problem today. Monthly bordereaux mapping, short premium found on day eight and two claims numbers.
• •What changes. Every bordereau is mapped and tied to control totals on arrival, so shortfalls are caught on day five, not day eight. Exposure enrichment runs on freshness SLAs, so cat models run on complete exposure.
• •What stays with your people. Pricing inputs, reserves and financial numbers: these carry regulatory accountability, so actuaries approve.
• •The result. An underwriting data team that closes the month on time and tests pricing ideas in weeks.

The PRD for agentic underwriting and claims 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 underwriting and claims data teams

• •Put your data pipeline on autopilot. Every bordereau is mapped and tied to control totals on arrival, so shortfalls are caught on day five, not day eight.
• •Run the data back office without the busywork. The work that fills the week today moves to agents: monthly bordereaux mapping, short premium found on day eight and two claims numbers.
• •Scale data without scaling headcount. Exposure enrichment runs on freshness SLAs and claims are tied between claims and finance daily, so the data you manage grows without the team having to.
• •Get the plumbing off your plate. An underwriting data team that closes the month on time and tests pricing ideas in weeks.

Who this is for

Teams that own policy, quote, exposure, bordereaux and claims data and the products built on it: rating inputs, portfolio views, claims analytics and reinsurance submissions. Titles include Lead PM for MGA Data, Product Manager (Data), Claims Data Lead and Head of Underwriting Data.

The shift

Insurers now take more business through delegated authority and enrich more decisions with third-party, geospatial and catastrophe data. Each partner and vendor adds a format, and every month-end depends on mapping them correctly. Agents can make that mapping, tying out and enrichment continuous, so underwriting and claims teams get data on day one.

The product you ship

• •Policy, exposure and premium data
• •Bordereaux from MGAs and coverholders
• •Claims data for analytics and reserving
• •Enriched exposure data for pricing and cat modeling

Where the week goes

• •Bordereaux arrive in new layouts every month.
• •Written premium does not tie to partner totals.
• •Geospatial enrichment runs late.
• •Claims extracts differ between claims and finance.
• •New rating factors take a quarter.

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 15% 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 underwriting and claims data teams:

• •Bordereau change mapped: from about 4 days to 15-30 min
• •Premium tied to controls: from about 2 days to 8-15 min
• •Enrichment rerun: from about a day to ~1 h

Across the routine work in this domain:

The biggest change is Bordereau change mapped: from about 4 days to 15-30 min.

Use cases, in depth

The bordereau that changed shape

Today. A coverholder reorders columns; written premium loads short.

With Data Workers. Ingestion flags the layout, Schema Evolution maps it, Quality Monitoring ties premium to control totals, Conductor holds the actuarial refresh.

What changes. Month-end on time.

Exposure enrichment for cat modeling

Today. Geocodes and hazard scores arrive late before a renewal season.

With Data Workers. set_sla on enrichment tables; Conductor reruns and verifies coverage.

What changes. Cat models run on complete exposure.

One claims number

Today. Claims and finance report different incurred.

With Data Workers. Context Wizard governs incurred, paid and reserve definitions; Quality Monitoring ties them daily.

What changes. Reserving starts from one number.

Agents working together: A coverholder bordereau that changed shape

Minute by minute

This is an illustrative example. Bordereaux land in an S3 bucket and load into Snowflake; dbt builds premium and claims marts read by actuarial on day 7.

Without the agents, the shortfall is found in the day-8 pack.

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:

• •Every bordereau is mapped and tied to control totals on arrival, so shortfalls are caught on day five, not day eight.
• •Exposure enrichment runs on freshness SLAs, so cat models run on complete exposure.
• •Claims are tied between claims and finance daily, so reserving starts from one number.

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.

• •Pricing inputs, reserves and financial numbers always goes to a named approver: these carry regulatory accountability, so actuaries approve.
• •Underwriting and claims 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 Pricing and reserve inputs, 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: Snowflake, Databricks or BigQuery; policy admin and claims systems (Guidewire, Duck Creek); partner portals and SFTP; geospatial and cat vendors; dbt; Airflow. 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

Insurers answer to regulators and auditors for reserves and financial reporting. Data Workers provides lineage, named approvals on pricing and reserve inputs and an audit trail; your controls decide sufficiency.

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 underwriting and claims 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. Bordereaux tools ingest partner files; Data Workers also maps changes, ties to controls and keeps every downstream mart governed.

The case for your CTO

What this replaces. Monthly bordereaux mapping, short premium found on day eight and two claims numbers.

What your team gets back. An underwriting data team that closes the month on time and tests pricing ideas in weeks.

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; pricing inputs, reserves and financial numbers stay at L2 with a named approver; and one org-wide stop halts all autonomous work.

Why now. Delegated authority keeps growing.

The first win. Bordereaux tie-out for 10 coverholders 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 underwriting and claims 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; pricing inputs, reserves and financial numbers always go to a named approver.
• •Autonomous, under your governance. Routine work runs on its own: every bordereau is mapped and tied to control totals on arrival, exposure enrichment runs on freshness SLAs, and claims are tied between claims and finance daily. Your team governs the agents instead of doing the upkeep.
• •The agentic enterprise. Carriers will treat every partner feed as a contract enforced on arrival, close the month on schedule every month and test new rating factors in weeks. Underwriting data teams will spend their time on pricing and portfolio insight.

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

The pilot: how underwriting and claims data teams start

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

• •What we connect. Snowflake, Databricks or BigQuery; policy admin and claims systems (Guidewire, Duck Creek); partner portals and SFTP; geospatial and cat vendors; dbt; Airflow, over MCP, inside your infrastructure. Nothing migrates.
• •Scope. Bordereaux tie-out for 10 coverholders 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. Every bordereau is mapped and tied to control totals on arrival and exposure enrichment runs on freshness SLAs start running on reversible work. Pricing inputs, reserves and financial numbers stay at L2 with a named approver.
• •At day 30. We review the impact metrics against your baseline:

• •Bordereau change mapped: from about 4 days to 15-30 min
• •Premium tied to controls: from about 2 days to 8-15 min
• •Enrichment rerun: from about a day to ~1 h
• •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 38% of agent actions run fully autonomously while pricing and reserve inputs stay with a named approver.

FAQ

Does it work with Guidewire? Through your warehouse and its APIs over MCP.

Can it change reserves? No; reserve inputs are L2 and decisions are manual.

Can it onboard new coverholders? Yes, as a mission with mapping, tests and docs.

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

• •Hippo, Lead Product Manager, MGA Data: https://www.builtinsf.com/job/lead-product-manager-mga-data/6880830
• •Core Specialty, Product Manager, Data: https://www.insurancepond.com/job/943259/product-manager-data/
• •Chubb, Head of Data Products, Commercial Insurance NA: https://www.dreamworkhq.com/job/a310ec2e-591e-4031-af1a-8a200e3aba71
• •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 underwriting and claims data