Extract the adviser, CRD number, assets under management, regulatory status, fee structure, and disciplinary history from a Form ADV filing PDF.
The full guide: CRD number and assets under management on a Form ADV
Need to scale? Create an API key, then run this from your own code or an agent.
Create an API keyFree account required
Upload a file or pick a sample, and see the fields come back.
No signup · nothing stored
The file or CRD number, the document date, the adviser name, address, phone, and website, the total assets under management (AUM), the regulatory status (enum, such as SEC-registered, state-registered, or exempt), the business type, the ownership structure, the year established, and the form type (enum, such as Part 1A or Part 2A).
A Form ADV is the registration disclosure an investment adviser files with the SEC or a state regulator — it describes the advisory business, AUM, fees, conflicts, and disciplinary history. A Form D is a notice of an exempt private securities offering, and a Form 10-K is a public company annual report. For those use the Form D or SEC 10-K extractors.
The fee structure type (enum), the minimum account size, whether the adviser charges performance-based fees, whether it has discretionary authority, whether it uses soft dollars, whether it takes compensation from third parties, whether it uses sub-advisers, the material conflicts of interest, and the investment restrictions each come back as fields.
Yes. A control persons table returns each name, title, percent ownership, and business experience; a fee schedule table returns each service type, fee basis, rate, and minimum fee; a disciplinary history table returns each date, type, description, and resolution; and advisory services, key personnel, and affiliates tables come back too.
PDF only, up to 10MB and 100 pages. The filing is processed via the Talonic API for extraction only, is not retained for training, and is not shared.
The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.
See PDF to Markdown if you run this for data and platform teams, or the extraction API if you are building it in.