Talk to sales

/ Our platform

The AI protein engineering software built for scientists

Cradle makes it easy for scientists to train and run protein AI that produces successful candidates 1.5 to 12x faster than traditional workflows.

Wet lab validated AI

Used by leading R&D teams

Introducing Cradle

2 minutes

Explore platform

Endless cycles. Slow progress.
Money, time, wells — wasted.

"This is how it's always
been…" you keep hearing.

For decades, it held true.

Today, it changes.
Scientists, meet Cradle.

Endless cycles. Slow progress.
Money, time, wells — wasted.

"This is how it's always
been…" you keep hearing.

For decades, it held true.

Today, it changes.
Scientists, meet Cradle.

The AI engineering
platform for biology

Scientists in pharma and industrial bio use Cradle to shorten protein R&D timelines up to 12x while growing overall pipeline success.

Save months of R&D time

Customers achieve 2-12x speedups across 50+ programs. We help you reach your targets in fewer rounds by solving complex trade-offs faster.

See case studies

Higher program success

Scientists consistently rate Cradle's AI-engineered protein candidates 8/10 —delivering sequences that perform in the real world, not just in silico.

See case studies

Built for scientists

Designed for pharma, industrial bio, foodtech and beyond. Our agnostic approach works across modalities and data types—if you can measure it, you can use Cradle.

Explore Biopharma

Explore Industrial Bio

Wet lab verified AI

Our Amsterdam wet lab constantly validates and improves the platform's AI core, ensuring customers get AI that "just works" without worrying about maintenance or infrastructure.

Learn more

Three ways AI unlocks
faster R&D timelines

See how Cradle handles multiple complex objectives in parallel, adapts to your data and automatically de-risks every plate.

Solves property trade-offs simultaneously with AI

Traditional methods force sequential optimization—improve binding, then thermostability, then expression. Cradle's AI understands how your target properties interact and optimizes them simultaneously, finding solutions that balance competing objectives instead of sacrificing one for another.

Solves property trade-offs simultaneously with AI

Use AI to learn from your
unique experimental data

AI protein engineering explores unseen parts of the protein landscape where pretrained models fail. After each round, Cradle automatically builds a custom model trained on public datasets, our wet lab data, and your project results—ensuring accurate predictions no matter how far your designs drift from nature.

Use AI to learn from your
unique experimental data

AI that designs de-risked
plates by default

Cradle designs curated libraries that balance hitting your objectives, learning from results, and exploring alternatives. The system runs tens of thousands of simulations to optimize between exploiting known winners and exploring new possibilities—getting you to your final candidate in the fewest rounds.

AI that designs de-risked
plates by default

All your teams
in one workspace

With everyone is in the same workspace, results compound across your organization. Same data. Same models. Same learning loop. New results.

API and Web App

Granular access controls

Unlimited seats

Web interface

Wet lab

Add your domain expertise and AI generate candidates for lab testing in just a few clicks. Upload experimental results to improve your project-specific AI automatically.

API Access

Computational

Run Cradle with an API and scale your expertise without the DevOps overhead. Focus on novel design strategies, not routine requests and endless configuration.

Web interface

Wet lab

Add your domain expertise and AI generate candidates for lab testing in just a few clicks. Upload experimental results to improve your project-specific AI automatically.

API Access

Computational

Run Cradle with an API and scale your expertise without the DevOps overhead. Focus on novel design strategies, not routine requests and endless configuration.

Web interface

Wet lab

Add your domain expertise and AI generate candidates for lab testing in just a few clicks. Upload experimental results to improve your project-specific AI automatically.

API Access

Computational

Run Cradle with an API and scale your expertise without the DevOps overhead. Focus on novel design strategies, not routine requests and endless configuration.

Same workflow.
Upgraded results.

Your experimental workflow stays the same, your results don't.

Learn

Generate

Review

Import your data

To begin, upload wet lab data from screening or optimization experiments. If you're starting a project from scratch, simply define your goals and assays to get going.

Explore your data quality

Cradle automatically analyses your experimental data to determine data quality and AI’s ability to learn from it. This helps you to understand how to improve your workflows and assays to get to optimal sequences faster.

Models learn with you

Every time you upload lab results, Cradle gets better at understanding your protein. This means increasingly performant variants that get you closer to your goals— every round.

Learn

Generate

Review

Import your data

To begin, upload wet lab data from screening or optimization experiments. If you're starting a project from scratch, simply define your goals and assays to get going.

Explore your data quality

Models learn with you

Every time you upload lab results, Cradle gets better at understanding your protein. This means increasingly performant variants that get you closer to your goals— every round.

Learn

Generate

Review

Import your data

To begin, upload wet lab data from screening or optimization experiments. If you're starting a project from scratch, simply define your goals and assays to get going.

Explore your data quality

Models learn with you

Every time you upload lab results, Cradle gets better at understanding your protein. This means increasingly performant variants that get you closer to your goals— every round.

"Cradle’s AI-based protein design platform provides easy access and acceleration to protein optimization for the discovery pipeline."

Eswar Narayanan

Director, Corteva Catalyst

Latest
updates

Latest updates

Data & Workflow Management

Flexible data management
Upload data your way—define custom schemas that match your lab workflows and create focused views for specific analyses, all through our UI and API.

Complete provenance tracking
See exactly who did what, when, and with which data—full audit trails for every table, task, and configuration across your projects.

Full API access
Connect Cradle directly to your existing pipelines and automate protein engineering workflows programmatically.

Multi-modality support
Engineer enzymes, peptides, and single- or multi-chain antibodies all within the same platform using both UI and API.

Design and Optimization

Multi-property optimization
Optimize multiple protein properties simultaneously—balance activity, stability, expression, and more in a single round to reach your target product profile faster.

Modular task system
Run multiple training and generation configurations side-by-side within each round to compare approaches and identify the best path forward.

Advanced sequence design controls
Steer your designs with template sequences, blocked mutations, regional constraints, and custom optimization objectives tailored to your project needs.

Intelligent plate design
Get complete experimental plates that balance achieving your objectives with exploring alternative strategies—designed through thousands of virtual simulations.

Hit identification
Analyze high-throughput screening and panning data to quickly identify promising candidates from large libraries.

AI and model updates

Automated model finetuning
Let Cradle automatically build fit-for-purpose models for each round using public data, our proprietary wet lab data, and your specific company and project data. (Cradle models trained on your data will always be private to you. More about security and privacy on our security page.)

De-risked plate generation
Engineer proteins far from wild-type sequences with models trained on your experimental data to accurately predict performance in uncharted sequence space.

Wet lab proven technology
Our models are tested and validated continuously in our Amsterdam wet lab—every feature is built on real experimental feedback.