A playbook for the Head of Investment Data

Key takeaways

• •Who this is for. Teams that own positions, transactions, holdings and performance data across custodians, administrators, order management and accounting books.
• •The problem today. Afternoons spent working custodian breaks, late strikes after restatements and private assets in spreadsheets.
• •What changes. Positions and cash are reconciled on every custodian load, so breaks surface at 8am, not 2pm. Restated custodian files are detected and only affected days reprocessed, so restatements stop derailing the strike.
• •What stays with your people. NAV and performance inputs: the fund accounting lead approves every change.
• •The result. An investment data team that delivers reconciled holdings to every consumer before the strike.

The PRD for agentic investment 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 investment data teams

• •Put your data pipeline on autopilot. Positions and cash are reconciled on every custodian load, so breaks surface at 8am, not 2pm.
• •Run the data back office without the busywork. The work that fills the week today moves to agents: afternoons spent working custodian breaks, late strikes after restatements and private assets in spreadsheets.
• •Scale data without scaling headcount. Restated custodian files are detected and only affected days reprocessed and private asset templates are landed and mapped, so the data you manage grows without the team having to.
• •Get the plumbing off your plate. An investment data team that delivers reconciled holdings to every consumer before the strike.

Who this is for

Teams that own positions, transactions, holdings and performance data across custodians, administrators, order management and accounting books. Titles include Head of Investment Data, Investments Data Product Owner, IBOR Data Lead and Portfolio Data Manager.

The shift

Asset managers run on reconciliations between custodians, administrators and internal books. As products multiply and private assets grow, the reconciliation load grows faster than the team. Agents can run those reconciliations continuously, trace breaks to their cause and keep portfolio data products current.

The product you ship

• •Reconciled positions and transactions across books
• •NAV and performance inputs
• •Portfolio and exposure data for PMs and risk
• •Client and regulatory reporting data

Where the week goes

• •Custodian files arrive late or restated.
• •Position breaks are worked one by one.
• •Private asset data arrives in spreadsheets.
• •Security master changes ripple into holdings.
• •PM copilots disagree with official holdings.

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 investment data teams:

• •Holdings question answered: from about a day to seconds
• •Private asset template mapped: from about 3 days to hours
• •Position break traced: from about 4 hours to 8-15 min

Across the routine work in this domain:

The biggest change is Private asset template mapped: from about 3 days to hours.

Use cases, in depth

A custodian restatement

Today. A custodian restates two days; positions break across 30 funds.

With Data Workers. Data Ingestion detects the restatement, Incident Debugging reprocesses only affected days, Quality Monitoring re-runs reconciliations, and Conductor holds NAV inputs at L2.

What changes. Breaks clear before the strike.

Private assets out of spreadsheets

Today. Capital calls and valuations arrive as spreadsheets from managers.

With Data Workers. Connectors land them, Schema Evolution maps each template, Pipeline Building tests them, and Context Wizard records valuation dates and sources.

What changes. Private assets join the same governed holdings.

A PM copilot on official holdings

Today. PMs see different exposure in the copilot and the risk report.

With Data Workers. Context Wizard serves one governed definition of holdings and exposure with provenance.

What changes. The copilot matches the book.

Agents working together: A custodian restatement before the strike

Minute by minute

This is an illustrative example. Custodian files land in Snowflake by 08:00; reconciliations feed NAV inputs at 11:00. NAV inputs are at L2.

Without the agents, breaks are worked by hand into the afternoon.

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:

• •Positions and cash are reconciled on every custodian load, so breaks surface at 8am, not 2pm.
• •Restated custodian files are detected and only affected days reprocessed, so restatements stop derailing the strike.
• •Private asset templates are landed and mapped, so private assets join governed holdings.

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.

• •NAV and performance inputs always goes to a named approver: the fund accounting lead approves every change.
• •NAV sign-off: this stays with people.

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

Catalog and docs closes autonomously 88% of the time. For NAV 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 or Databricks; custodian and administrator SFTP and APIs; order management and accounting systems; Airflow; dbt; BI and PM tools. 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

Funds answer to auditors and regulators for NAV accuracy. Data Workers gives traceable reconciliations, named approvals on NAV inputs and a tamper-evident audit trail; your controllers decide what satisfies each control.

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 investment 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. Reconciliation platforms match records; Data Workers also traces breaks to cause, fixes the pipeline and keeps holdings governed for every consumer.

The case for your CTO

What this replaces. Afternoons spent working custodian breaks, late strikes after restatements and private assets in spreadsheets.

What your team gets back. An investment data team that delivers reconciled holdings to every consumer before the strike.

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; nAV and performance inputs stay at L2 with a named approver; and one org-wide stop halts all autonomous work.

Why now. Private assets and product launches are growing faster than operations teams.

The first win. Continuous reconciliation on one custodian 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 investment 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; nAV and performance inputs always go to a named approver.
• •Autonomous, under your governance. Routine work runs on its own: positions and cash are reconciled on every custodian load, restated custodian files are detected and only affected days reprocessed, and private asset templates are landed and mapped. Your team governs the agents instead of doing the upkeep.
• •The agentic enterprise. Investment operations will reconcile continuously and explain breaks before anyone asks. Data teams will deliver holdings as a governed product to every PM tool, report and copilot, and private assets will sit beside public ones on the same terms.

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

The pilot: how investment data teams start

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

• •What we connect. Snowflake or Databricks; custodian and administrator SFTP and APIs; order management and accounting systems; Airflow; dbt; BI and PM tools, over MCP, inside your infrastructure. Nothing migrates.
• •Scope. Continuous reconciliation on one custodian 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. Positions and cash are reconciled on every custodian load and restated custodian files are detected and only affected days reprocessed start running on reversible work. NAV and performance inputs stay at L2 with a named approver.
• •At day 30. We review the impact metrics against your baseline:

• •Holdings question answered: from about a day to seconds
• •Private asset template mapped: from about 3 days to hours
• •Position break traced: from about 4 hours to 8-15 min
• •the share of catalog and docs 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 NAV inputs stay with a named approver.

FAQ

Does it replace our reconciliation tool? It can feed and follow it; the break-tracing and pipeline fixes are what it adds.

Can agents change NAV? No. NAV inputs are proposed at L2 and sign-off stays manual.

Does it handle private assets? Yes, by landing and mapping manager templates into governed holdings.

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

• •Liberty Mutual Investments, Investments Data Product Owner: https://ftp.theclm.org/home/jobdetails/63200
• •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 fund accounting and investment data