AI & Machine Learning

Connect BigML to Your AI Agents

Enable your Wkil agents to browse models, datasets, predictions, and evaluations through BigML.

Authentication: API key

Build with BigML

What you can do

Browse machine learning models and datasets
Retrieve predictions and evaluation results
Organize work into projects

Available capabilities may vary by authentication and workspace configuration.

Actions supported by the connector

45 verified tools

List Models

List machine learning models available in the workspace.

List Datasets

List datasets available for training or evaluation.

List Predictions

List predictions generated by a model.

Create Project

Create a new project to organize models and datasets.

List Evaluations

List evaluation results measuring model performance.

List Sources

List raw data sources uploaded for modeling.

List Clusters

List unsupervised clustering models.

List Ensembles

List ensemble models combining multiple predictors.

List Forecasts

List time-series forecasts generated from a model.

Get Source

Retrieve details for a specific uploaded data source.

View all verified tools (search)

Create External ConnectorCreate ProjectDelete ProjectGet ConfigurationGet External ConnectorGet ProjectGet SourceList Anomaly DetectorsList Anomaly ScoresList AssociationsList Association SetsList Batch Anomaly ScoresList Batch CentroidsList Batch PredictionsList Batch ProjectionsList Batch Topic DistributionsList CentroidsList ClustersList CompositesList ConfigurationsList CorrelationsList DatasetsList DeepnetsList EnsemblesList EvaluationsList ExecutionsList ForecastsList FusionsList LibrariesList Linear RegressionsList Logistic RegressionsList ModelsList OptiMLsList PCAsList PredictionsList ProjectionsList ProjectsList SamplesList ScriptsList SourcesList Statistical TestsList Time SeriesList Topic DistributionsList Topic ModelsUpdate Source

Practical agent use cases

An agent retrieves a model's latest evaluation before deciding whether to use its predictions.

How it works with Wkil

1
Choose the integration
Add BigML to your agent from inside the Wkil platform.
2
Grant the permissions it needs
Define precisely what the agent can access and perform.
3
Test, then run it
Test actions before they go live, with human approval where needed.

Permissions always stay in your control — you can scope access and require human approval before any sensitive action.

Related integrations

FAQ

Can an agent train a new model?

It can organize projects, datasets, and review predictions and evaluations already produced in BigML.