AgentX and BigML Integration

Demonstration of how apps are integrated in WEXTL workflow builder[4]

Connect AgentX and BigML to automate ai workflows. Trigger events from one app, run actions in the other and use AI to make smart decisions. Integrate apps in 3 simple steps - no code required.

  • 3-day trial
  • Cancel anytime
  • Up to 10 minutes quick set up
  • GDPR
  • Data Encryption
  • 2FA
  • Local Data Region

Learn about AgentX and BigML

Detailed info you need to know about AgentX and BigML integrations in WEXTL. Explore which modules apps support and how you connect them.

  • AgentX

    • AI
    • 7 searches
    • 12 actions

    Hosted AI agents for starting conversations, sending messages and reading traces.[5]

  • BigML

    • AI
    • 2 triggers
    • 67 searches
    • 81 actions

    Build datasets, train models and get predictions with BigML machine learning.[6]

How to connect AgentX to BigML

Set up your AgentX and BigML integration in 3 simple steps[2]. No coding required. Up to 10 minutes setup.

How does the integration between AgentX and BigML work in WEXTL?

WEXTL exposes actions and triggers for AgentX and BigML that help you connect apps and automate repetitive tasks[1]. A trigger is an event that happens, and an action is a step that performs when the event has occurred.

BigML triggersAgentX actions

BigML modules

  • Create a Batch Anomaly Score Scores each row of a Dataset with an anomaly detector. Turn on Output Dataset to keep the results as a dataset, and All Fields to carry the original columns along.
  • Create a Batch Centroid Assigns each row of a Dataset to the nearest centroid of a cluster. Turn on Header to add a header row to the output file.
  • Create a Batch Prediction Predicts for each row of a Dataset with a model of the chosen Model Type. Turn on Probabilities or Confidence to add those columns, and give the prediction column a Prediction Name.
  • Create a Batch Projection Projects a Dataset onto a PCA, row by row. Set Max Components to cap the number of components produced.
  • Create a Batch Topic Distribution Computes the topic mix of each text row in a Dataset with a topic model. Turn on Output Dataset to keep the results as a dataset.
  • Create a Centroid Finds the closest centroid of a cluster for one record, from its Input Data.
  • Create a Cluster Groups the observations in a Dataset into clusters. Set Number of Clusters to fix the group count, or leave it blank to let BigML choose with G-means.
  • Create a Dataset Creates a dataset out of your Source. Set Objective Field to mark the column to predict and Size to cap the dataset in bytes.
  • Create a Dataset from SQL Runs an SQL Query over existing Datasets and saves the result as a new dataset.
  • Create a Deepnet Trains a deep neural network on a Dataset. Set Objective Field to choose the column it predicts.
  • Create a Forecast Projects a time series forward for one record of Input Data. Use Intervals to ask for prediction intervals.
  • Create a Fusion Combines several Models into one fusion model that predicts together.
  • Create a Library Stores reusable WhizzML code from Source Code. Add Imports to pull in other libraries.
  • Create a Linear Regression Fits a linear regression on a Dataset, predicting the Objective Field. Use Input Fields to choose the predictors.
  • Create a Logistic Regression Fits a logistic regression on a Dataset, predicting the class chosen as the Objective Field. Add Excluded Fields to leave columns out of the fit.
  • Create a Model Trains a decision tree on a Dataset. Use Objective Field to pick the target, Sample Rate to train on part of the rows and Optimize to tune it.
  • Create a PCA Runs principal component analysis on a Dataset. Pick columns with Input Fields, or drop some with Excluded Fields.
  • Create a Prediction Predicts for one record from its Input Data, using a model of the selected Model Type. Turn on Explain to get the reasoning as well.
  • Create a Project Adds a project to hold related BigML resources. Use Name, Description and Tags to title, summarise and label it.
  • Create a Projection Projects one record onto a PCA from its Input Data, keeping at most Max Components components.
  • Create a Script Saves a WhizzML script from Source Code, optionally with Imports.
  • Create a Source from a File Uploads a data File in CSV, ARFF, JSON or Excel form, or a compressed copy. Use Source Parser to control how it is read.
  • Create a Source from a URL Has BigML fetch a source from a web address given as URL, with no upload from your side.
  • Create a Source from External Data Reads rows from an external Connector with a Query. Add Tables, Fields, Limit or Offset to narrow what is pulled.
  • Create a Source from Inline Data Makes a source straight from the pasted Data, with no file upload.
  • Create a Source from Synthetic Data Generates a source of synthetic data. Set Number of Fields and Number of Rows for its size.
  • Create a Time Series Fits a time series on a Dataset for the Objective Field. Use Horizon to set how far ahead it forecasts and Period for the seasonal length.
  • Create a Topic Distribution Computes the topic mix of one text record with a topic model, from its Input Data.
  • Create a Topic Model Finds topics in the text of a Dataset. Fill Number of Topics with how many to extract.
  • Create an Anomaly Detector Trains an anomaly detector on a Dataset with a chosen Forest Size, and lists the Top N anomalies it finds.
  • Create an Anomaly Score Scores one record against an anomaly detector, using the Input Data of that record.
  • Create an Association Builds association rules from a Dataset. Set Min Support for the support threshold and Max Associations to cap the rules found.
  • Create an Association Set Finds the associations that apply to one record from its Input Data. Use Max Results to cap how many are returned and Score By to choose the ranking.
  • Create an Ensemble Trains a group of models on a Dataset. Use Number of Models to set the size, Sample Rate for the data share per model, and Randomize for randomized trees.
  • Create an Evaluation Scores a model of the selected Model Type against a Dataset. Use Missing Strategy to set how missing values are treated.
  • Create an Execution Runs a Script. Pass values through Inputs and ask for specific variables with Outputs.
  • Create an External Connector Saves a database login from an Engine and a Host. Add Port, Database, User and Password to finish the login.
  • Create an OptiML Searches for the best model for the Objective Field of a Dataset. Use Max Training Time to cap the search and Metric to set what is optimized.
  • Delete a Batch Anomaly Score Deletes a run that scored a whole dataset with a detector.
  • Delete a Batch Centroid Removes a run that assigned dataset rows to clusters.
  • Delete a Batch Prediction Deletes a run that predicted for every row of a dataset.
  • Delete a Batch Projection Removes a run that projected dataset rows onto a PCA.
  • Delete a Batch Topic Distribution Deletes a run that worked out topics for each row of a dataset.
  • Delete a Centroid Removes a stored lookup of the nearest cluster centroid for one record.
  • Delete a Cluster Deletes a cluster that grouped dataset rows.
  • Delete a Dataset Removes a dataset that was prepared from a source.
  • Delete a Deepnet Deletes a neural network trained on a dataset.
  • Delete a Forecast Removes a forecast computed from a time series.
  • Delete a Fusion Deletes a fusion that combined several models.
  • Delete a Library Removes stored WhizzML code that scripts can import.

AgentX modules

  • Create a Conversation Opens a new conversation on one of your AgentX agents. Set Type to Chat, Search or Ecommerce to decide how the agent will handle it.
  • Create Speech Turns Text into spoken audio through the AgentX voice API. Set Language, Gender, Speed or Accent to shape the voice, and turn on Robot for a mechanical tone.
  • Create Speech Stream Synthesizes Text as a streamed audio response from the voice API, so playback can begin before the whole clip exists. Use Language, Gender, Speed or Accent to adjust the voice.
  • Delete a Conversation Context Clears the memory context stored for a conversation held with an agent in AgentX.
  • Get a Conversation Reads one conversation of an agent together with its messages. Create a Conversation or List Conversations gives you the conversation to read.
  • Get a Message Trace Looks up the prompt trace linked to a message by its Message ID. Pass the result to Get a Trace for the full detail.
  • Get a Trace Looks up the detailed prompt trace for a Trace ID, the record of how an agent built its answer. Get a Message Trace finds the ID for a given message.
  • Get an Agent Fetches the details and current configuration of a single agent in your AgentX account.
  • Get Your Profile Reads the profile of the user who owns the API key this credential uses, which shows which AgentX account a credential belongs to.
  • List Agents Finds every agent your API key is allowed to use in AgentX, each coming back as a separate result.
  • List Conversations Collects the conversations held with one agent, ready to read or continue in later steps.
  • Make an API Call Makes an authorized free-form request to the AgentX REST API with your saved credential.
  • Send a Message Posts a Message into an existing conversation and returns the Status and Response of the agent. Use Agent Mode to switch between Chat and Search, and Context to set how much history counts, with 0 meaning as much as possible.
  • Send a Message and Wait Sends a Message and holds until the agent finishes the whole reply, buffered up to 10 MiB or 180 seconds. Use Context to cap how much earlier conversation counts.
  • Send a Message and Wait for JSON Sends a Message, optionally with Attachments or Audio, and waits until the agent completes a JSON reply. Set Context to restrict the history the agent draws on.
  • Send a Message with an Attachment Uploads a File into a conversation for the agent to read. Add a Message to go along with the file, and use Context to control how much earlier chat is considered.
  • Send Speech Recognition Submits an audio Sample (Base64) for transcription under a Call ID and Seq ID. AgentX posts the recognized text to your Callback URL, and you can leave Language empty for auto detection.
  • Update a Conversation Context Seeds a conversation with earlier user and assistant Messages as memory, without triggering a chat turn.
  • Update a Message Vote Sets the Vote on a message, found by its Message ID. Use Agent and Trace ID to tie the vote to the exchange it rates.

Explore alternative integrations

There are other apps[9] supported by WEXTL that can be paired with AgentX and BigML integrations. Pick any from the list below if the current combination isn't the one you need.

Automate AgentX and BigML on WEXTL®

Claim your 3-day trial to build AgentX with BigML integration and access every WEXTL® feature.

Cancel anytime.

Frequently asked questions

Common questions about connecting AgentX and BigML.

How do I connect AgentX and BigML?

Connect your AgentX and BigML accounts once, pick a trigger in one app and an action in the other, then map the fields so data flows automatically between them.[3]

What can I automate between AgentX and BigML?

Example: when the "Watch Finished Resources" trigger in BigML fires, WEXTL can "Create a Conversation" in AgentX. AgentX has 19 actions (including Create a Conversation, Create Speech, and Create Speech Stream). BigML has 148 actions (including Create a Batch Anomaly Score, Create a Batch Centroid, and Create a Batch Prediction). Add filters and transforms between steps when you need them.[1]

Can AgentX trigger actions in BigML, and BigML in AgentX?

Yes. The integration works in both directions. Use the triggers of each app to start a workflow and the actions of the other app to update it.[2]

Do I need to write code to integrate AgentX and BigML?

No. AgentX-to-BigML automations are built visually on the canvas. You can optionally add custom JavaScript with Functions when you need advanced logic.[4]

Does AgentX integrate with BigML in real time?

Yes. Trigger-based automations start the moment AgentX (or BigML) fires a new event. Webhook-backed apps run within seconds, and polling-only apps re-check on a schedule you control.[7]

How long does it take to set up a AgentX + BigML integration?

A first automation typically takes 5–10 minutes: connect the credential of each app once, drop a trigger + action onto the canvas, map the fields, and turn the workflow on.

Do I need a paid plan to connect AgentX with BigML?

You can build your AgentX + BigML automation on a 3-day trial with every feature unlocked. Cancel anytime.[8]

References

List of sources used to gather information about the AgentX and BigML integration.

  1. AgentX and BigML integration source code, module specs and credentials implementation.
  2. Our AgentX and BigML integration documentation, structured input and output parameters, scopes, and authentication methods.
  3. Official vendor API documentation for AgentX and BigML, used to verify field meanings, authentication flows, and anything our own specs don't fully capture.
  4. WEXTL® visual workflow builder, anonymized data from our technical support team.
  5. AgentX integration information
  6. BigML integration information
  7. WEXTL® Scheduling
  8. WEXTL® Pricing and Trial
  9. WEXTL® Apps Library

How we write our apps documentation

Explore how WEXTL® crafted AgentX and BigML integration page documentation. Used sources, the role of AI, and how the team validates the result.

Explore AgentX and BigML, or get started