Book a demo

For full terms & conditions, please read our privacy policy.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
White plus

How does Evolution AI work?

Evolution AI uses generative AI to extract data from PDFs and scans. Our platform is pre-trained on more than 25 million documents and can learn to read new documents without substantial additional training.

Artificial intelligence means our products are self-learning; no explicit configuration is required to learn how to extract information from a new document. Just point and click—our products learn by themselves!

Zero-shot learning icon

Zero-shot learning

Our revolutionary ‘zero-shot’ algorithm enables users to extract data without lengthy training and configuration. The algorithm marks a significant breakthrough for IDP technology, which has historically required many document training examples to extract data from a new document type.

Zero-shot algorithms can transfer understanding from previously-seen training examples to completely new tasks. The algorithms can take on new tasks without additional training data, ensuring the model can quickly adapt to processing your company’s documents.

Improving over time icon

improving over time

Zero-shot learning is powerful but not infallible. To ensure optimal performance, our AI also learns over time. The AI model improves its understanding whenever a user corrects an error, and will never repeat it.

The software performs self-learning automatically. Unlike competing IDP systems, there is no need for a cumbersome ‘training’ stage.

Testing of our self-learning technology shows that after processing just 25 documents the self- learning model quickly improves accuracy to over 90%, reaching 98% once the system has seen 200 documents (Figure 1). During the first few days of production usage, accuracy will quickly reach 98-99%. Any remaining errors can be corrected by human annotators and accuracy will continue to improve over time.

Graph of training documents vs. accuracy



Train the model yourself - no need to get your IT team involved! Our easy-to-use user interface allows you to quickly train the model to your company’s requirements, with our excellent customer service available as needed.

Evolution AI can apply several data post-processing rules to improve and enrich data quality, such as standardised date formats and calculating inferred fields. If you need something unique, just tell us. We do everything to ensure you have your data, your way.


Data needs to be accessible to the right systems to create value. Many companies are concerned about implementing AI technology - but we offer several accessible options for integration. For example, flexible integration via our REST API makes it easy to upload documents and send the output to downstream systems. Alternatively, you can integrate by file transfer using SFTP.

Unsure about which integration method would work best with your pre-existing company architecture? Get in touch with us at

Don't settle for less than completely accurate data

Evolution AI understands accurate data is of the utmost importance: our software supports fully configurable QA workflows. That includes multiple teams, spot or comprehensive checking, customising confidence thresholds, double-checking mandatory fields, and even requiring double-user sign-off prior to data extraction.

A series of automated checks and balances also identifies anomalies in the data. For example, ‘time series analysis’ is used to detect greater variation than would normally be expected and flag potential errors.

workflow of document through data extraction process

Example workflow for extracting from financial statements. Evolution AI supports all required financial concepts such as reporting periods; and currency and multipliers.

You’re in safe hands

Checked by humans
Data integrity without compromises

Custom robustness checks and anomaly detection make sure your data quality is always maintained.

Government backed
UK Government Backed

Evolution AI was funded by one of the largest AI R&D grants ever awarded by Innovate UK, the UK funding body for innovation.

Control and Governance
Detailed control and governance

A full audit trail is stored so the provenance of each data point can be tracked throughout its life cycle.

Padlock icon
ISO 27001 compliant

ISO/IEC 27001 is the international standard for managing information security. Evolution AI is certified ISO 27001 compliant, ensuring that we securely hold information assets.



Advanced AI Models & Annotation Interface
Our advanced AI models work hand in hand with a fully-featured annotation interface.
Pre-built models
Access to a library of pre-trained models
Automatically classify documents
Automatically classify documents according to configurable categories
Confidence scores
Flag extracted data points whose confidence score falls below the confidence threshold and requires human-in-the-loop intervention and validation
One click model retraining and self-learning
After QA is complete, a single click submits corrections and retrains the model. The model learns immediately from the corrected document
Self-learning AI recognizes patterns in data and becomes more intelligent as it sees more data. Corrections from a human in the QA process improve the model immediately to prevent the same error and improve prediction accuracy
Zero-shot learning
System can make predictions on new types of documents without requiring any training examples
Extract data in paragraphs of text
Capturing the exact information contained within a text paragraph
Support for financial data
Support for reporting period (e.g. YTD, LTM, FY), currency and multipliers (eg. thousands and millions)
Complex table extraction
Accurate extraction from complex tables, including nested tables and tables spanning multiple pages
Preview screen
View the uploaded document and extracted / missing fields. Option to view all pages or only those with extracted fields
Split document
Divide a document into separate sub-documents
Easy to use annotation interface
Simply select the data field from the menu and click and drag to select the data point on the page. Checks and approvals ensure the user has selected the correct data field and specified the correct data format where relevant (e.g., date: DD/MM/YY vs MM/DD/YY)
Text filter
Search for specific words within the document
Document alignment
Rotation of pages and automated deskewing
Enterprise IT & integration features
Evolution AI has all the enterprise IT and management features your IT team would expect and the capability to integrate into your existing IT infrastructure.
Pre-built models
Data can automatically be standardised to meet requirements, such as date standardised to ISO8061 format
Split monetary fields
Monetary fields can be split into three letter currency code and the value multiplier
Time series anomaly detection
A series of checks and balances are in place to identify anomalies and ensure data quality, such as:
  • Identify variables with great than expected variation
  • Compare current revenue to last quarter revenue
  • Check to see all multipliers on the page are the same
Summation consistency
After QA is complete, a single click submits corrections and retrains the model. The model learns immediately from the corrected document
Apply custom business logic
Self-learning AI recognizes patterns in data and becomes more intelligent as it sees more data. Corrections from a human in the QA process improve the model immediately to prevent the same error and improve prediction accuracy
Data post processing & transformation
After data is extracted from the document, Evolution AI performs checks and balances to validate data accuracy and standardise the output to your requirements.
Roles based permissions
Add new users and configure permissions to one of three levels (annotator, user, admin)
ISO27001 certified
Compliance with the highest level of information security
Configurable QA workflows
Configure QA workflow allowing flexible approval process for document sign off
Set metadata
Metadata feature enables supplementary data to be included at the document/batch level
Upload log and filter
A full and searchable history of all uploaded documents and details including upload data, processing status and document type
Extract data
Generate an output file in CSV or excel, or JSON via API
Easy auditability
Every extracted data point comes with a hyperlink to the document and the page the data point was extracted
API access
Upload documents and download output via RestAPI
Workato integration
Workato connector means we are integrated with over 1,000 software platforms including all widely used ERP and accounting systems
Post status updates regarding your documents via API
Support downstream automation
Integration via well documented REST API
History log
A date and time-stamped record of all actions taken and by which user for every document. Includes classification, prediction, human-in-the-loop (HITL) annotation
Annotators can leave comments with each document, making it easy to store communications and document intelligence in one place
Monitor and track all project metrics, such as the number of documents processed by document type and total number of pages processed
Golden Set for training
Train new members using a special set of pre-annotated documents
Think Evolution AI is right for you? Book a demo with one of our team and find out how we can revolutionise your document extraction processes.
Book a demo