Do we need to build a template per hospital or lab?

No. anyformat is zero-shot. A new centre's discharge summary or lab report works the first time, no template setup, no labelled training data. The same engine handles all the layouts you receive today.

Does it normalise to ICD-10 or CIE?

Yes. anyformat can return both the raw extracted text and a normalised coded value: ICD-10 / CIE-10 for diagnoses, CPT / CIE for procedures, ATC for medications, LOINC for lab tests. Confidence scores are attached at the field level.

Can it integrate with our EHR and LIS?

Yes. REST API or HL7 FHIR endpoints into Epic, Cerner, OpenMRS, Selene, HCIS and in-house EHRs; lab integrations into Modulab, Roche Cobas, Sysmex via standard interfaces. Output drops onto the patient record without copy-paste.

What about handwritten notes and scanned papers?

anyformat handles scans, photos and partially handwritten notes. Pure handwriting (entire pages of cursive) is harder for any system, but anyformat's confidence scoring will flag those for human review rather than guess silently.

Is on-premise really the same as the cloud product?

Yes. The on-premise build is the same engine, deployed on your infrastructure with the same accuracy. You give up only managed updates and shared compute. We support both VPC-isolated cloud and air-gapped on-prem.

Yourclinical ops teamshouldn't bea data entryteam.

Every clinical note, discharge summary, lab report and insurance form arrives in a format the originating centre invented. anyformat reads them all and pushes structured data into your EHR, LIS or billing system, without a template per hospital.

Book a demo

Clinical staff working with patient records and lab reports

ISO 27001 certified|On-premise deployment available|99% extraction accuracy

CLINICAL NOTE

LAB REPORT

DISCHARGE

EHR

LIS

Billing

THE PROBLEM

Clinical documents arrivein every format imaginable,and your team types them in.

Each hospital, lab and specialty produces documents in formats nobody agreed on. Discharge summaries from one centre have nothing in common with another's. Lab reports are PDFs with embedded tables. Insurance forms are paper.

Volume

1 per

centre, every one with a different template

A discharge summary from HM Hospitales doesn't look like one from Quirónsalud or Vithas. Lab reports vary by lab, by specialty, by year. Hardcoding a template per centre doesn't scale past a handful.

Sensitivity

PHI

every document is regulated health data

Patient identifiers, diagnoses, treatments, prescriptions. anyformat processes documents with zero retention, on EU infrastructure, ISO 27001 certified, with on-premise deployment available for centres that need it.

Throughput

Hours

between admission and structured data

A hospital that admits 500 patients a day generates thousands of documents. Manual triage and data entry delay everything downstream, from billing to outcomes research. The structured data shouldn't take hours to materialise.

Accuracy

Coded

outputs that match your EHR's vocabulary

Free text isn't enough. anyformat extracts and normalises diagnoses to ICD-10, procedures to CPT/CIE, medications to ATC. Your EHR receives codes, not strings, with confidence scores attached.

Trusted by clinical operations at

Built for clinical documents

Trained on the documentsyour clinical operationsactually receive.

Not generic PDFs. The specific clinical artifacts that flow through hospitals, labs, clinics and payors every day.

Clinical notes

Note #	Patient	Author	Setting	Date
NT#82041	#4729	Dr. García	ER	2026-05-12
NT#82052	#8132	Dr. Pérez	ICU	2026-05-13
NT#82063	#5943	Dr. López	Cardiology	2026-05-13
NT#82074	#2156	Dr. Ruiz	Internal med.	2026-05-14
NT#82085	#7188	Dr. Vega	Neurology	2026-05-14
NT#82096	#9402	Dr. Soto	Oncology	2026-05-15

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

Overview

Reliable Document Data.
Built for Production.

anyformat handles the formats, edge cases, and integrations that break traditional pipelines, so your workflows stay reliable as data scales.

Any format in

Ingest data from PDFs, documents, images, and many more.

Multiple document format icons including PDF, DOC, and images

API-first by design

REST API, webhooks, and structured JSON output, plus pre-built connectors for SharePoint, OneDrive, Google Drive, and Salesforce.

Integration diagram showing connections to SharePoint, OneDrive and API endpoints

Designed to scale

Process high volumes of data with reliable performance, monitoring, and analytics built for production workloads.

Performance metrics dashboard showing scaling capabilities

Built-in validation

Catch errors, handle edge cases, and ensure consistent output with validations and monitoring at every step.

Data validation interface showing error checking and quality monitoring

Build workflows visually

Create and manage parsing, validation, and routing logic in the visual Studio, or define them programmatically via API.

Visual workflow builder showing nodes and connections for document processing

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 grounding: every value cited to its source

–

Confidence scoring and human-in-the-loop

–

EU data residency, ISO 27001, zero retention

–

Questions about healthcare document AI

How anyformat fits into a hospital, lab or payor operation.

Yes. anyformat is ISO 27001 certified, EU-native, with zero-retention processing and contractual GDPR alignment. Documents are processed in memory and not stored after the response. On-premise deployment is available for centres that require it.

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

Note #

Patient

Author

Setting

Date

NT#82041

#4729

Dr. García

2026-05-12

NT#82052

#8132

Dr. Pérez

ICU

2026-05-13

NT#82063

#5943

Dr. López

Cardiology

2026-05-13

NT#82074

#2156

Dr. Ruiz

Internal med.

2026-05-14

Yourclinical ops teamshouldn't bea data entryteam.

Clinical documents arrivein every format imaginable,and your team types them in.