Can it abstract a 200-page contract?

Yes. anyformat handles long, complex contracts: MSAs, services agreements, SaaS T&Cs, joint venture agreements, intercompany pacts. It identifies clauses (limitation of liability, IP, indemnity, term, jurisdiction, MAC) and returns the extracted obligations with their source.

Does it integrate with our CLM?

Yes. REST API and webhooks into Ironclad, Agiloft, Onit, ContractWorks, plus matter-management systems used by law firms. Extracted clauses drop onto the contract record without copy-paste.

What languages and jurisdictions does it cover?

European common law and civil law systems: English, Spanish, French, German, Italian, Portuguese. It handles Spanish notarised documents, German GmbH minutes, French SAS bylaws and the equivalents in other EU jurisdictions.

How does it handle redlines and version control?

anyformat extracts from any version of a contract: signed PDF, redlined Word, scanned executed copy. For redlines you can run two versions through and surface the deltas as a structured diff, not just track-changes overlays.

Is it GDPR compliant for client data?

Yes. anyformat is EU-native, ISO 27001 certified, with zero-retention processing. Privileged client data is processed in memory and not stored after the response. On-premise is available for firms with strict data residency requirements.

Yourlegal teamshouldn't bea data entryteam.

Every contract, NDA, court ruling and due-diligence pack still gets read clause by clause by a person. anyformat reads them across formats and languages, extracts the obligations, dates and parties that matter, and pushes structured data into your CLM or matter management.

Book a demo

Legal team reviewing contracts and corporate documents

Clause-level extraction with citations|99% extraction accuracy|EU sovereignty, ISO 27001

CONTRACT

JUDGMENT

DD PACK

CLM

Matter mgmt

Compliance

THE PROBLEM

Legal documents arrivein every format imaginable,and your team reads them line by line.

In-house legal teams, law firms and corporate operations run on contracts, deeds, rulings and corporate records nobody designed for structured extraction. Each counterparty drafts their own way. Each ruling is a different court's template.

Time

of partner time per contract abstract

Senior lawyers spend hours abstracting the same 30 clauses out of every contract that lands on their desk. The economics don't work for high-volume operations, NDAs, vendor agreements, intercompany filings.

Volume

1,000s

of clauses to track for a single transaction

Carve-outs, conditions precedent, MAC clauses, change-of-control triggers. A mid-market M&A diligence pack has thousands of obligations buried across hundreds of PDFs, and the person doing it has two weeks.

Risk

missed clause is a real liability

An indemnity carve-out you didn't notice. A renewal that auto-extended. A jurisdiction clause that flips next month. Manual review catches most. anyformat catches them all and surfaces the source paragraph for verification.

Citations

Every

extraction comes back with the source paragraph

For legal use, an answer without a citation is useless. anyformat returns the extracted value plus the paragraph and page it came from, so the lawyer reviews exactly the text that was the source, not a guess from a black box.

Trusted by legal teams at

Built for legal documents

Trained on the documentsyour legal teamactually receives.

Not generic PDFs. The specific artifacts that flow through in-house legal, law firms and corporate operations every day.

Commercial contracts & NDAs

Contract #	Counterparty	Type	Renews	Liability cap
C#48201	Lactalis FR	MSA	2027-04	3x fees
C#48212	Roca SAU	Vendor	2026-12	12 months
C#48223	Vinci ES	NDA	—	—
C#48234	Pascual Hnos	Supply	2028-02	Capped
C#48245	Volvo Iberia	Reseller	2027-06	3x fees
C#48256	Bergé y Cía	Logistics	2028-09	1x fees

Security and certifications

Enterprise-grade security

anyformat meets enterprise security and compliance requirements out of the box, so teams can run document workflows in production with confidence.

GDPRPersonal data handled to GDPR standards, with EU data residency.

ISO 27001Independently certified to ISO 27001 for information security management.

Self-hosted deploymentRun anyformat in our cloud, in a dedicated VPC, or fully self-hosted in your own infrastructure. Your data stays exactly where your policy requires.

Visit the Trust Center

Built for the agentic era

By engineers and agents
for engineers and agents

Call anyformat workflows straight from your codebase with the SDK or CLI, or drop in the agent skill and let your coding agent build and run them for you in minutes, not months.

Terminal

Claude Code

Opus 4.8

SDKs

Install the SDK to call anyformat workflows straight from your codebase.

npm install @anyformat/sdk

CLI

Use the Python CLI to run and manage your workflows from the terminal.

uv tool install --python 3.13 anyformat && afx --help

Agent Skill

Add this skill to teach your agent the anyformat workflow API.

npx @anyformat/skill

Beyond the model

Everything around the model, built in.

Advanced OCR and parsing, enhanced by the capabilities required to build and run reliable workflows, fast and at scale.

annie builds your workflow

annie configures the whole workflow for you in seconds. No manual setup.

I want to extract info from invoices

Field-level confidence

Every field gets a calibrated score: only review what needs it.

Contract name

99%

Software License Agreement

Date

80%

2026-03-24

Contract type

98%

Employment

Evaluate and monitor

Eval every change against your own dataset before it ships. Once live, track accuracy field by field.

Select the right mode

Switch between Fast, Standard, and Agentic. Optimize for latency or accuracy, depending on what each job needs.

Fast

Standard

Agentic

annie keeps improving it

Ask annie to improve your workflow. She finds the fix and applies it automatically.

Accuracy by iteration

1st Optimization

5 fields · 6 iterations

Completed

92.5%97.0%+4.5p

Why anyformat

Built for production,
not demos

Raw OCR can't read structure. A raw LLM hallucinates and can't be audited. anyformat combines both with deterministic rules, confidence scoring and validation, so the output is structured, traceable and ready for production.

Traditional OCR

Raw LLM

anyformat

Reads layout, tables and structure

–

Long documents, hundreds of pages

–

Complex, multipage tables

–

Poor scans and low-quality inputs

–

Any format and language, no templates

–

Visual citations: every value cited to its exact position on the page

–

Confidence scoring and human-in-the-loop

–

EU data residency, ISO 27001, zero retention

–

Questions about legal document AI

How anyformat fits into in-house legal, law firms and corporate operations.

Yes. Every extracted value comes back with the paragraph and page it came from. The lawyer reviews the exact source text, not a black-box guess. That's a non-negotiable for legal use.

Start with your hardest documents.

anyformat does the heavy lifting on the documents that break other tools. Parse, extract and validate them into clean, reliable data, and get to production in minutes.

No credit card required · 50,000 free credits to start