From the makers of spaCy and Prodigy
Your virtual
NLP engineer
You’ve heard all about vibe coding – now say hello to vibe NLP. With Ellf, your team can take back control and build custom and fully private AI solutions in-house.
✳︎Claude Code
› We need to extract products and pricing from press releases. We started with an LLM API but it's slow and expensive, and our data needs to stay private. How can we train our own model? ⏺︎Let me analyze your requirements and put together a project plan for you.
TasksText classification
TasksAnnotate entities
AgentsGPT-5
Datasetslegal-contracts
Datasetsmedical-records
AssetsDocuments
Assign @Agents/Gemini to @|
Project planning
Break your business problem down into actionable steps.
Distillation
Use LLMs to create better, smaller, faster and fully private task-specific components.
Model training and analysis
Train and fine-tune task-specific models, analyze the logs and diagnose problems.
Data preparation and exploration
Convert raw data, cluster information and iterate on label schemes for your task.
Data development
Collaborate on annotation and automate data labeling with agents
Annotation guidelines
Write comprehensive labelling manuals to scale up the data creation process.
Pattern generation
Determine what to extract with rule-based logic and create patterns interactively.
QA and evaluation
Test your system with real-world and synthetic data.
Coding assistance
Build custom solutions with spaCy, Prodigy and the powerful Python ecosystem.
Ellf for Prodigy users
Already using the Prodigy annotation tool? Here’s how you can scale up, automate and supercharge your annotation.
Ellf for universities
Use Ellf to collaborate on research and experiments, and speed up and automate development and data collection.
Frequently Asked Questions
Any other questions that are not covered here? Email us!
Ellf’s modules cover all aspects of the NLP development process, including project planning and advice, data preparation and annotation, machine learning and rule-based logic, and model training and evaluation. In combination with your AI-assisted coding tool like Claude Code, it can build end-to-end NLP pipelines for you and develop standalone AI systems that are accurate, fast and run entirely under your control.
The Ellf platform lets you run and monitor annotation tasks, processes like training and evaluation, and automated agents for working with data, powered by your own data-private cluster running locally or in the cloud. Data annotation workflows are powered by our popular annotation tool Prodigy and cover all common NLP tasks, including named entity recognition, span categorization, text classification, relation extraction and more.
Ellf is designed for both beginners and experienced NLP developers. If you’re just getting started, Ellf will guide you through the end-to-end process, answer any questions that come up and help you set up your project from scratch. More experienced developers can use Ellf to get feedback on their solution, automate tasks and iterate faster. Ellf integrates seamlessly into your workflow, wherever you are in the development cycle.
Ellf lets you plug in your own data processing cluster hosted locally or on your cloud infrastructure and under your control. The cluster provides all data, models and custom code you use and create, and serves the annotation interface and performs actions like model training or data analysis. This means that no sensitive data ever leaves your servers or has to pass through our servers in the process.
The cluster can be set up in your cloud account (e.g. AWS, Google Cloud or Azure) or on a local workstation in a few simple steps, without requiring specific DevOps or infrastructure expertise.