ESG Report Extractor

Extract Scope 1, 2, and 3 emissions, water, waste, workforce diversity, and governance metrics from an ESG or sustainability report PDF.

The full guide: Scope 1, 2, and 3 emissions from a sustainability report

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 ESG Report Extractor.

Which ESG metrics does the extractor read?

The environmental fields cover Scope 1, Scope 2, and Scope 3 greenhouse gas emissions (in metric tons of CO2 equivalent), water consumption, waste generated, the waste recycled percentage, and the renewable energy percentage. The social fields cover employee count, turnover rate, the women and women-in-management percentages, health and safety incidents, the lost-time injury frequency rate (LTIFR), and training hours per employee. The governance fields cover board size, independent members, and the executive compensation ratio.

Are the emissions and metrics returned as tables?

Yes. The greenhouse gas emissions table returns the year, scope, category, and emissions in mtCO2e; and separate environmental metrics, resource consumption, employee demographics, health and safety, governance structure, and stakeholder engagement tables each come back with their own rows.

Does it capture the reporting framework and assurance?

The reporting standards used (such as GRI, SASB, or TCFD) come back as an array, alongside the reporting organization, the reporting period start and end, and the publication date. The assurance fields record whether the report was third-party verified, the verification provider, and the assurance level (limited, reasonable, or high).

Does it read the ESG goals and governance flags?

The sustainability goals table returns each goal with its category, target year, baseline value, and progress status, and boolean flags record whether the organization ran a materiality assessment, engaged stakeholders, performed human rights due diligence, and operates an ethics and compliance program and supplier screening, alongside any data privacy certification held.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The report 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.