End-to-end ML pipeline
Distill AI into
lightweight inference
Use AI to build and label your training data. MLPotion learns from it and deploys a fast, deterministic scikit-learn pipeline — no GPU, no API costs, no latency at inference time.
Pipeline
Six stages, fully integrated. Work done in each phase directly feeds the next.
Describe what you need to the AI assistant. It proposes a dataset schema — columns, types, validation constraints — and creates it for you.
Upload CSV, paste from a spreadsheet, ingest via API, or generate synthetic rows through the assistant. Bulk writes up to 50 rows per call.
Consensus labelling with three independent AI annotators. Majority-vote agreement determines the label. Disagreements flagged for human review.
Per-column constraints enforced on every write — required fields, allowed values, numeric bounds. Training blocked until all errors resolve.
33 scikit-learn estimators evaluated via stratified k-fold cross-validation. Automatic text vectorisation via TF-IDF. Best pipeline selected by primary metric.
REST endpoint live immediately. JSON in, prediction out. Interactive playground for testing. Pipeline artifact downloadable as .joblib.
Embedded assistant
Conversational interface
at every stage
An AI agent is available in every view. It can inspect your data, generate rows, set validation rules, trigger training, run predictions, and diagnose model performance.
strategy_review column for the individual votes.
Integration
Standard HTTP interface
No client library required. The prediction endpoint accepts POST requests with a JSON body. A data ingestion API is also available for programmatic row insertion.