Frequently Asked Questions

Traditional AutoML tools are limited to predefined models, basic feature engineering, and hyperparameter tuning. Genematon generates custom code, exploring solutions that traditional AutoML can't reach. Genematon also handles multi-table data natively, while most AutoML tools require you to flatten everything into a single table first.

Genematon can solve virtually any problem where your data is in tabular format, whether it's demand forecasting, churn prediction, risk modeling, fraud detection, predictive maintenance, or countless other prediction and classification tasks.

It also excels at creating GenAI pipelines and embedding models for similarity search, RAG (Retrieval-Augmented Generation), semantic analysis, and intelligent document processing. Your data can include both numerical and textual features, making it flexible for real-world datasets.

Yes. Genematon exposes RESTful API endpoints that allow AI agents to programmatically create pipeline jobs, check status, retrieve results, and manage deployments. This means your agents can autonomously provision ML and GenAI capabilities without any human intervention.

Each agent authenticates with scoped credentials and all actions are fully auditable.

Agents can create new pipeline jobs by specifying data sources and goals, monitor job progress, retrieve predictions and results from deployed pipelines, and manage pipeline lifecycle (pause, resume, retrain).

The API is designed for machine consumption with structured JSON requests and responses, making it straightforward to integrate into any agentic framework.

Your data security is our top priority. Here's how we protect it:

• Encryption: All data is encrypted both in transit and at rest
• Access Controls: Role-based permissions ensure only authorized users can access your data
• Isolated Execution: LLM-generated code runs in ephemeral, isolated containers that are destroyed after each run, preventing data persistence between executions
• Network Security: Containers have strict egress filtering and can only communicate with pre-approved services. They cannot post data to external IPs or unauthorized endpoints

Pipeline generation typically takes a few hours, though this varies based on your data complexity and the specific problem you're solving. Genematon automates the code generation, testing, and optimization work that would normally take a team of AI engineers weeks or months to complete.

Yes! Genematon can work with multiple tables, whether they're related or completely independent. You don't need to manually join or flatten your data. Genematon handles it automatically, regardless of how your tables are structured.

Genematon allows you to upload your data in various formats, including CSV, Excel, JSON, and Parquet. You can also connect cloud storage (AWS S3, Azure Blob), APIs, and more.

Yes. Genematon includes monitoring, automatic retraining when performance degrades (if data is available), and pipeline versioning. You can also select from your pool of generated solutions if you need to roll back or switch approaches.

Our early access program gives early users free access to Genematon in exchange for feedback. Early access users get priority support and direct input on product roadmap. The program includes some usage limits to ensure fair access for all participants. Spots are limited.

Enter your email on our homepage to join the waitlist. We'll contact you with access details and next steps.

Yes, early access is free but includes usage limits (such as number of pipelines and data size). These limits ensure all early access users can access the platform fairly. Pricing for the full product will be announced closer to public launch.