Proxy Statement Extractor

Extract the company, meeting date, director nominees, executive compensation, and shareholder proposals with voting results from a DEF 14A proxy PDF.

The full guide: Record date and board nominees in a DEF 14A proxy

How should we start?

Build with Talonic

Need to scale? Create an API key, then run this from your own code or an agent.

Create an API key

Free account required

Start with a document

Upload a file or pick a sample, and see the fields come back.

No signup · nothing stored

Questions about Proxy Statement Extractor.

What company and meeting details does the proxy statement extractor read?

The company name, its CIK (SEC Central Index Key), ticker, and state of incorporation, the shareholder meeting date, time, and location, the record date that fixes who may vote, the distribution date, and the filing date and document number of the DEF 14A.

Are the director nominees and executives returned as tables?

Yes. The board members table returns each director with their position, committee membership, and independence status, an executive officers table returns each officer with their position, and a committee memberships table maps members to committees and roles.

Does it capture executive compensation?

The compensation summary table returns one row per named executive officer with the annual salary, bonus, stock awards, non-equity incentive plan compensation, and total compensation, so the pay disclosures reconcile without re-keying.

How are proposals and voting results handled?

The proposals table returns each proposal with its number, title, description, type (such as Director Election, Say-on-Pay, or Charter Amendment), and the board recommendation (For, Against, Abstain, or No Recommendation), and the voting results table returns the votes for, votes against, votes abstain, broker non-votes, and the result (Passed or Failed).

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The filing is processed via the Talonic API for extraction, is not retained for training, and is not shared.

Doing this to one file, or to ten thousand?

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.