Client documents read into the plan, with every figure traced to the page it came from.
Bluegrass builds document extraction systems for RIAs and wealth managers. They read held-away statements, tax returns, estate documents and policies into your CRM and planning software, linking each figure to its page and holding anything uncertain for a person.
A financial plan is only as good as its data, and most firms key that data by hand from PDFs, so plans are often built on figures that are months old.
What gathering client data involves today
Someone has to read each statement, return and document, key the figures into the planning software and check that the totals agree. A new household can bring dozens of documents, and each annual review brings new versions.
The work is repetitive and exact, a poor use of a planner's time, and errors in it carry straight into the advice. Because every figure can be checked against its source, AI can do it reliably while a person reviews the exceptions.
How automated document extraction works
- 01
Collect the documents
Documents are picked up from the client portal, email and the document store, identified by type, client and date and matched to the household they belong to.
- 02
Read every page
Holdings, balances, cost basis, income, deductions, beneficiaries, trustees and policy terms are read from statements, returns, trusts, wills and policies, whether native PDFs or scans.
- 03
Check and reconcile
Totals are checked against each document and against what the CRM and planning software already hold, and anything that disagrees or can't be read confidently goes to a person.
- 04
Update the systems
Approved figures are written into the planning software and CRM, each linked to its source page, so a planner can trace any number without opening the file.
- 05
Flag what matters
Changes worth the advisor's attention, such as a beneficiary that differs from what the client said or a large move in a held-away account, are noted for the next review.
Where people stay in the loop
Planners review the extracted data before it is used in a plan, and the system is first measured on a labeled set of your clients' documents.
The systems it works with
The system works with your client portal, document store, CRM and the planning, tax and estate software you use, writing approved figures into each through its own interfaces.
When to build it, and when to buy it
Planning software and advisor tools increasingly read common documents themselves, and for a firm whose clients mostly send standard statements, those features may be enough.
A custom build makes sense when clients' documents are varied, as with business owners and complex estates, when the data must reach several systems, or when extraction should also feed account opening.
We hold no reseller agreements, partner quotas or revenue share with any vendor, so a recommendation to buy is made on its merits.
What this work costs you today
A quick way to put a number on the problem before talking to anyone, using your own figures rather than ours.
Enter your volume and the minutes each one takes to see what the work costs in a year.
The numbers stay in your browser and are not stored or sent anywhere. Bring the figure to the first call, since it is the baseline any system should be measured against.
Questions about client document extraction
- Can it read tax returns and estate documents?
- It reads individual and business returns, trusts, wills and powers of attorney, and the evaluation measures its accuracy on your own clients' documents before anything is promised.
- Where do the documents go?
- They stay in your own document store and cloud account, where the system reads them. The model and its data retention terms are agreed with your compliance team before any client data is processed.
- Does it replace the planner's review?
- It replaces the keying rather than the review. The planner checks the extracted figures with the source page a click away and decides what they mean for the plan.
Related systems
A senior team that has done this before
We are a small, entirely senior team with fifty years of combined AI engineering, multiple granted patents and Y Combinator founders, from Yale, MIT, McKinsey, Goldman Sachs, Microsoft and Vista Equity Partners. The people who scope your work are the people who write the code.
Selected work
We built the AI transformation roadmap for a top-50 P&C brokerage, and it is saving the firm millions of dollars in vendor fees it did not need to pay.
Clients include some of the largest banks, RIAs, fintechs and AI labs, as well as a top-3 P&C carrier, a top-10 P&C brokerage, a top-5 trucking brokerage, a leading specialty MGA and a leading trucking MGA.
We run only 3 to 5 engagements at a time, so that every client works directly with the senior team.
About the team- Dozens
- of insurance companies, RIAs, banks and fintechs we have worked with
- 50 yrs
- combined AI engineering experience
- 10+ Patents
- granted to members of the team
- 100%
- of the IP we build is assigned to you
Find out whether this is worth building for your business.
A 30-minute call with an engineer usually shows whether this is worth building. Within a week you will have a free written point of view, including whether a packaged product would serve you better.