Connect Future AGI integrations
VerifiedAI agent evaluation platform for datasets, evals, simulations and annotation queues, connected to WEXTL workflows and AI agents. Your workflows can send Future AGI results straight into the tools that act on them. Start with Check the Health, then use Compare Eval Summaries or Export an Annotation Queue to turn the output into a next step.
- 3-day trial
- Cancel anytime
- Up to 10 minutes quick set up
- GDPR
- Data Encryption
- 2FA
- Local Data Region
Supported triggers and actions for Future AGI integration
Triggers can detect changes in Future AGI and run actions that can create, search or modify data inside Future AGI automatically[3], exactly how you set them.
- Check the Health Pings the Future AGI API to confirm it is up.
- Compare Eval Summaries Lines up the eval summaries of several test executions of one run test, using the Execution IDs.
- Export an Annotation Queue Exports queue annotations in the chosen Export Format. Use Status to export only items in one state.
- Fetch an Assistant from a Provider Reads a voice assistant from its provider with the Assistant ID and API Key, returning its Name, Prompt and Provider.
- Find Queues for a Source Finds the annotation queues that contain a given source, set with Source Type and Source ID. Use Sources to check several at once.
- Get a Custom Eval Config Reads a custom eval config including its Eval Template, Config and Mapping for a project.
- Get a Dataset Annotation Summary Summarises annotation work on a dataset, broken down by Labels and by Annotators.
- Get a Dataset Column Config Reads the setup of one column through its Template, Template Config and Config.
- Get a Dataset Explanation Summary Shows the generated explanation of a dataset with its Last Updated time, Row Count and Min Rows Required.
- Get a Performance Summary Shows Test Run Performance Metrics and the Top Performing Scenarios of a test execution.
- Get a Run Prompt Column Config Reads the saved Config that drives a run prompt column of a dataset.
- Get a Scenario Fetches a scenario with its Source, Scenario Type and Dataset ID.
- Get a Version Eval Summary Reads how an agent version scored in its evals, across the runs made with it.
- Get an Agent Definition Reads an agent definition with its Agent Name, Agent Type and Contact Number.
- Get an Agent Version Looks up one saved version of an agent with its Version Number, Version Name and Status.
- Get an Annotation Item Detail Opens a queue item with its Labels, Annotations, Review Comments and Review Threads.
- Get an Annotation Label Fetches a label with its Name, Type and Settings.
- Get an Annotation Queue Pulls a queue with its Instructions, Status and Assignment Strategy.
- Get an Eval Structure Fetches how a dataset eval is laid out for the chosen Eval Type, returned as Eval.
- Get an Eval Summary Reads the eval summary for a run test. Fill Execution ID to look at a single execution.
- Get an Eval Task Pulls an eval task with its Project, Filters, Sampling Rate and Last Run.
- Get Annotation Queue Analytics Reads queue statistics: Throughput, Annotator Performance, Label Distribution and a Status Breakdown.
- Get Annotation Queue Progress Counts queue items that are Pending, In Progress, In Review, Completed or Skipped.
- Get Call Execution Details Shows one simulated call with its Call Type, Status and Service Provider Call ID.
- Get Dataset Column Details Returns every column of a dataset, as the Columns list with their types and settings.
- Get Dataset Eval Stats Reads the evaluation statistics collected for a dataset by Future AGI.
- Get Eval Task Aggregations Computes usage figures for an eval task over a Period or between Start Date and End Date. Add Include Summary for a short digest alongside the Stats, Evals, Chart and Logs.
- Get Eval Template Names Lists eval template names, narrowed with Search Text.
- Get Model Voices Retrieves the voices available for models, each with a Name and Created At. Use Limit to cap the count.
- Get or Create the Default Queue Returns the default annotation queue for a Project ID, Dataset or Agent Definition, creating it when missing. The result says through Created which happened.
- Get Queue Item Annotations Reads every annotation that annotators stored on one item of an annotation queue, with its details.
- Get Run Prompt Column Values Reads the Result of run prompt columns for the Column Placeholders passed along.
- Get Run Prompt Options Lists what a run prompt column can use, such as Models, Available Tools, Output Formats and Tool Choices.
- Get Run Prompt Stats Shows average usage of the prompt columns in a dataset: Avg Tokens, Avg Cost and Avg Time.
- Get Run Test Details Reads a run test with its Agent Definition, Agent Version and Description.
- Get Scores for a Source Lists annotation scores on one source, matched by Source Type and Source ID. Add Label ID or Annotator ID to cut the list down.
- Get Simulation Analytics Reads results of simulation runs by Run Test Name or Execution ID, with the Eval Results and Eval Averages. Turn on Summary to add the explanation summary and critical issues.
- Get Simulation Metrics Reads call timing for a run test: the Duration Seconds, Started At and Completed At of each call.
- Get Simulation Runs Lists calls of a run test with their Scenario Name and Status. Filter with Eval Name or Call Execution.
- Get Test Execution Details Pages through the calls of one test execution. Use Search, Filters and Group Keys to narrow and group them.
- Get the Inter-Annotator Agreement Measures how closely annotators of a queue agree, reporting the Overall Agreement, the Labels and the Annotator Pairs.
- Get the Next Annotation Queue Item Fetches the next item an annotator should work on in a queue. Use Review Status to focus on a review stage and Exclude to skip chosen items.
- Get the Test Execution KPIs Reads headline numbers of a test execution: Total Calls, Completed Calls, Avg Score and Avg Response.
- Get Version Call Executions Lists the calls made with one agent version, each with its Phone Number and Status.
- List Agent Definitions Shows agent definitions with their Agent Name and Agent Type. Use Search to find one by text.
- List Agent Versions Lists the saved versions of an agent definition, each with its Version Number and Status.
- List Annotation Labels Browses annotation labels with their Name and Type. Filter by Search, Type or Project ID, and add archived ones with Include Archived.
- List Annotation Queue Items Collects queue items with their Source Type and Status. Narrow with Assigned To or Review Status, and sort through Ordering.
- List Annotation Queues Finds queues with their Status and Assignment Strategy. Use Search for text, or Archived to look at archived ones.
- List Annotation Scores Pulls scores with their Label Name and Label Type. Filter by Source Type, Source ID, Annotation Label or Annotator ID.
- List Custom Eval Configs Gets custom eval configs with their Eval Template and Name. Focus on one project with Project ID or one task with Eval Task ID.
- List Dataset Evals Looks through the evals attached to a dataset, filtered by Search Text, Eval Type or Eval Categories.
- List Datasets Reads datasets with their Name and Created At. Use Search Text to find one by name, and Sort to set the order.
- List Eval Tasks Retrieves eval tasks, narrowed by Project ID, Name or Filters, and ordered with Sort Params.
- List Personas Lists simulated caller profiles with their Name, Gender and Persona Type.
- List Run Test Scenarios Shows the scenarios attached to one run test, with each Row Count.
- List Run Tests Finds run tests with their Agent Definition and Description. Narrow with Search, Simulation Type or Prompt Template ID.
- List Scenarios Browses scenarios with their Source and Scenario Type. Narrow with Search, Agent Definition or Agent Type.
- List Test Executions Lists executions of a run test with their Status, Start Time and Duration. Narrow by Search text or Status.
- List TTS Voices Reads text-to-speech voices with their Provider, Model and Voice ID.
- Add a Dataset as New Saves an existing dataset as a separate dataset under a Name, optionally limited to chosen Columns. Reports the new Dataset ID.
- Add a Dataset Eval Attaches an evaluation to a dataset from a Template ID and a Config. Turn on Run to start it at once, and Save As Template to keep it for reuse.
- Add a Label to an Annotation Queue Links an annotation label to a queue. Turn on Required so annotators must fill it in, and read Reopened Items and Queue Status in the result.
- Add a Run Prompt Column Adds a dataset column that fills itself by running a prompt. Give it a Name and set up the prompt run with Config.
- Add a Static Column to a Dataset Adds one fixed column to a dataset with a New Column Name and Column Type, then reports its Status.
- Add AI Rows to a Scenario Asks Future AGI to generate Num Rows extra rows for a scenario dataset, steered by an optional Description. Returns the Scenario ID and Dataset ID.
- Add Columns to a Dataset Appends new columns to a dataset, with each column taken from New Columns Data.
- Add Columns to a Scenario Adds the listed Columns to a scenario dataset and returns the Scenario ID and Dataset ID.
- Add Empty Rows to a Dataset Appends blank rows to a dataset. Use Num Rows to set how many.
- Add Eval Configs to a Run Test Attaches the Evaluations Config entries to a run test, then reports the Created Eval Configs and any Warnings.
- Add Items to an Annotation Queue Puts records into an annotation queue, either as an explicit list of Items or as a Selection. Reports how many were Added, which were Duplicates and any Errors.
- Add Multiple Static Columns Adds several static columns to a dataset in a single call. Each entry of Columns describes one column.
- Add Rows from a File Reads a File and adds its rows to a dataset. Set Model Type to say what kind of dataset it is.
- Add Rows from an Existing Dataset Copies rows from a Source Dataset into a dataset, matching columns with Column Mapping. Reports how many Rows Added arrived.
- Add Rows from HuggingFace Pulls rows into a dataset from a Hugging Face Dataset Name, using the chosen Hugging Face Dataset Config and Hugging Face Dataset Split. Use Num Rows to take only part of it.
- Assign Queue Items to an Annotator Hands queue items to annotators using Item IDs and User IDs. Set Action to add, set or remove the assignment, and read Assigned for the outcome.
- Bulk Annotate Spans Writes annotations for many trace spans from a list of Records and reports Annotations Created, Annotations Updated and Notes Created.
- Bulk Create Annotation Scores Saves many Scores against one source in a single call, using Source Type and Source ID. Add Notes to store free text and read any Errors that came up.
- Bulk Delete Eval Tasks Deletes many tracing eval tasks in one call, one per entry from Eval Task IDs.
- Bulk Remove Queue Items Removes several items from an annotation queue using their Item IDs, and reports how many were Removed.
- Cancel a Test Execution Cancels a simulation test execution and reports Success with a Message.
- Check an Eval Config Exists Looks for a custom eval config matching the Eval Template and Project, optionally narrowed by Name, Mapping or Filters. A match comes out with its ID.
- Clone a Dataset Makes a full duplicate of a dataset and names it with New Dataset Name. Returns the Dataset ID and Dataset Name of the clone.
- Complete an Annotation Queue Item Marks one queue item as finished and moves on. The result shows the Completed Item ID and the Next Item to annotate.
- Create a Custom Eval Config Sets up an eval on a Project from an Eval Template under a Name. Use Mapping to connect template keys to your data, and Filters to limit what it scores.
- Create a Custom Eval Template Defines your own evaluation by Name and Required Keys. Add Criteria to describe the check, Output Type to shape the result, and Choices for fixed answers.
- Create a Dataset Makes a dataset with a Dataset Name and an optional Number Of Rows and Number Of Columns, then reports the Rows Created and Columns Created.
- Create a Dataset from HuggingFace Creates a dataset out of a Hugging Face Dataset Name and Hugging Face Dataset Split. Use Num Rows to import only part of it.
- Create a Persona Defines a simulated caller with a Name and Description. Set traits such as Accent, Personality and Conversation Speed to shape how it behaves.
- Create a Run Test Builds a simulation test from a Name, an Agent Definition and a set of Scenario IDs. Eval Config IDs add the evaluations to score each call.
- Create a Scenario Defines a test scenario by Name. Set Kind to graph, script or dataset, link a Dataset or Agent Definition, and add No Of Rows with Custom Instruction to generate rows.
- Create an Agent Definition Registers an agent under an Agent Name and Agent Type, with a Commit Message for its first version. A voice agent also needs a Provider.
- Create an Agent Version Saves a new version of an agent definition, with a changed Agent Name, Provider, Language or Contact Number if needed.
- Create an Annotation Label Defines a label annotators can apply, by Name and Type. Use Settings for type options, Project to scope it, and Allow Notes to permit comments.
- Create an Annotation Queue Opens a queue for human review with a Name and the Label IDs to annotate. Use Assignment Strategy and Annotations Required to control how work is spread, and Requires Review to add a review step.
- Create an Annotation Score Records one Value for an Annotation Label on a source, using Source Type and Source ID. Add Notes to include a comment.
- Create an Empty Dataset Starts a dataset with no data under a New Dataset Name. Turn on Is Sdk to mark it for SDK use, and use Model Type to set the dataset type.
- Create an Eval Task Schedules evaluation of a Project under a Name, scoring a Sampling Rate share of traffic with the chosen Evals. Set Run Type to continuous or historical.
- Delete a Custom Eval Config Removes a custom eval config that scored traces. Its ID is returned.
- Delete a Dataset Column Deletes one column from a dataset schema and reports its ID.
- Delete a Dataset Eval Removes an evaluation attached to a dataset, with its ID as the result.
- Delete a Persona Removes a simulated caller with its ID as the result.
- Delete a Run Test Deletes a simulation test and returns its stored ID.
- Delete a Scenario Removes a test scenario and gives the scenario ID.
- Delete Agent Definitions Deletes several agent definitions at once from the Agent IDs, and reports the Agents Updated and Versions Updated.
- Delete an Annotation Label Deletes an annotation label and reports Deleted with its ID.
- Delete an Annotation Queue Removes an annotation queue from Future AGI, giving its ID as the result.
- Delete an Annotation Score Deletes one recorded score by its Annotation Score ID.
- Delete an Eval Config Removes one eval config attached to a run test and returns its ID.
- Delete an Eval Task Deletes an eval task from tracing and reports its ID.
- Delete Dataset Rows Deletes rows from a dataset. Turn on Delete All Rows to clear every row, or fill Row IDs for specific ones.
- Delete Datasets Removes several datasets in one call from the Dataset IDs.
- Delete Test Executions Deletes test executions of a run test, either the Test Execution IDs given or all of them with Select All. Reports the Deleted Count.
- Duplicate a Dataset Copies a dataset under a Name. Use Row IDs to copy only some rows, or Selected All Rows for every row. The result reports Columns Copied and Rows Copied.
- Duplicate a Persona Copies a persona under a new Name and returns the copy with its Description, Gender and Age Group.
- Duplicate Dataset Rows Makes extra copies of rows inside a dataset. Use Num Copies to set how many copies each row gets, and Row IDs to choose the rows.
- Edit a Run Prompt Column Alters a prompt-driven dataset column. Rename it with Name or swap its prompt setup through Config.
- Edit a Scenario Rewrites a scenario: Name, Description, Graph or Prompt.
- Edit and Run a Dataset Eval Rewrites the Config of a dataset eval and runs it again. Use Model to change the model that runs the evaluation.
- Execute a Run Test Starts a run of a simulation test. Use Scenario IDs to run only some scenarios or Select All for all of them. Reports the Execution ID and Total Calls.
- Export a Queue to a Dataset Writes queue results into an existing Dataset or a new one titled by Dataset Name. Use Column Mapping to shape the columns and read Rows Created for the count.
- Make an API Call Runs a free-form request against the Future AGI REST API using your saved credential.
- Merge a Dataset Combines a dataset into a Target Dataset. Pass Row IDs to move only some rows. The result counts Rows Added and New Columns Created.
- Pause an Eval Task Stops an eval task from running until it is started again.
- Release an Annotation Queue Item Gives up the reservation on a queue item so another annotator can take it, and confirms with Released.
- Remove a Label from a Queue Detaches an annotation label from a queue and confirms with Removed.
- Rerun Call Executions Runs calls of a test execution again, either the Call Execution IDs provided or all of them with Select All. Use Rerun Type to rerun only the evals or the calls and the evals, and read Successful Reruns and Failed Reruns for the totals.
- Rerun Test Executions Runs executions of a run test again, either the Test Execution IDs provided or all with Select All. Use Rerun Type to rerun only the evals or the calls and the evals, and read Overall Success Count for the tally.
- Restore an Annotation Label Brings back an archived annotation label and returns it with its Name and Type.
- Resume an Eval Task Lets a paused eval task run again.
- Run New Evals on Executions Scores past executions with extra evals from Eval Config IDs. Pick executions with Test Execution IDs or Select All, then check Dispatched to see what started.
- Skip an Annotation Queue Item Skips a queue item and moves to the next one. The result names the Skipped Item ID and the Next Item.
- Start the Evals Process Runs the dataset evals for the User Eval IDs. Turn on Failed Only to rerun just the ones that failed.
- Submit Item Annotations Saves the Annotations an annotator made on a queue item. Add Item Notes to leave a note on the item and read Submitted to confirm.
- Update a Custom Eval Config Alters a custom eval config. Change its Name, Config, Mapping or Filters, or point it at another Eval Template or Project.
- Update a Dataset Cell Value Writes a New Value into one cell at a chosen Row and Column.
- Update a Dataset Column Name Renames a dataset column to the New Column Name and reports its Status.
- Update a Dataset Column Type Converts a column to a New Column Type. Turn on Preview to check for Invalid Count first, and Force Update to convert anyway.
- Update a Persona Revises the Name, Description or traits such as Gender, Accent and Languages of a persona.
- Update an Annotation Label Alters a label: Name, Type, Settings or Description. Use Clear Fields to blank values and Allow Notes to permit comments.
- Update an Annotation Queue Modifies a queue: Name, Instructions or Assignment Strategy, plus rules such as Annotations Required and Requires Review.
- Update an Annotation Queue Status Moves a queue to a new Status and returns the updated queue.
- Update an Eval Config Modifies an eval config on a run test, such as its Config, Mapping, Model or Name. Turn on Run to run it after the update.
- Update an Eval Task Adjusts an eval task by Name, Filters, Sampling Rate or Spans Limit. Set Edit Type to say what kind of change it is.
- Upload a Dataset from a File Creates a dataset from a local File and titles it with New Dataset Name. Set Model Type for the kind of dataset.
How to integrate Future AGI in automation workflow?
Future AGI in three steps: start with "Check the Health", connect one credential, then add your next step.
STEP 1
Select Future AGI in workflow
Add the "Check the Health" action from Future AGI to the canvas[4].
STEP 2
Connect Future AGI
Fill in the Future AGI credential once. All 144 Future AGI modules use it[3].
STEP 3
Build a workflow
Add "Compare Eval Summaries" or "Export an Annotation Queue" after it, then connect any app[5] or the HTTP node.
How Future AGI connects and integrates with WEXTL
Save and approve your credentials once. WEXTL® stores authorization information encrypted and reuses the authentication whenever Future AGI app is called in workflows. That allows your ai automations to run without your attention, per defined schedule[7]. See the integration guide[6] for a detailed list of fields that Future AGI supports.
Full Future AGI API documentationThe following table illustrates what fields Future AGI integration require during authorization flow inside our workflow builder[4].
Connect Future AGI
API Key*Text
••••••••
Secret Key*Text
••••••••
| Field | Type | Help |
|---|---|---|
API KeyRequired | password | In Future AGI open the dashboard, go to Keys, and copy the API key. |
Secret KeyRequired | password | The secret key that belongs to the API key. It is shown next to it in Keys. |
Connect Future AGI to popular apps on WEXTL
Enter a name of the other app you want to sync with Future AGI below. Click on selected app to explore integration options with Future AGI. If the app you search for is not available in WEXTL yet, you can use HTTP node[10] instead to integrate it directly.
Example automation with Future AGI integration
Select Check the Health action from Future AGI - this will be a starting point in your automation. Whenever event happens in Future AGI, workflow will start[7] from Check the Health node.
Search for Check an Eval Config Exists, connect it as the next step of integration sequence. You can use filters between Check the Health and Check an Eval Config Exists, so only important data pass from Check the Health to the next step. WEXTL gives you full control over the process of Future AGI automation. All parts of workflow are visible on the canvas[4].
Future AGI on WEXTL has 145 modules for combining ai automations. Explore Future AGI documentation for more.
- Future AGICheck the Health
- OpenAIPerforms action
OR
- OpenAITriggers
- Future AGICheck an Eval Config Exists
Frequently asked questions
Common questions about automating Future AGI in your workflows.
What triggers does Future AGI support?
Future AGI has no triggers, but it provides 145 actions including "Check the Health", "Compare Eval Summaries", and "Export an Annotation Queue". Pair them with triggers from other apps to automate Future AGI tasks.
What actions can I run in Future AGI?
Integration has 145 actions, including "Check the Health", "Compare Eval Summaries", and "Export an Annotation Queue", and more. Refer to our Future AGI Documentation for detailed inputs and outputs.
Do I need to write code to build automations?
No. The 144 Future AGI modules, like "Check the Health", are forms on the canvas: pick a field, map data from an earlier step. Code is optional[4].
Is the integration secure?
Yes. You fill in the Future AGI credential once. WEXTL encrypts it at rest, and only your team can use it.
How does WEXTL integrate with Future AGI?
Through the official Future AGI API: 144 modules, plus "Make an API Call" for any endpoint they don't cover[3].
Can I use webhooks with Future AGI?
Future AGI has no triggers here. Point Future AGI at a Custom Webhook node URL, or run the workflow on a schedule.
Why use WEXTL platform for Future AGI automation?
WEXTL is an AI-first visual canvas: describe the Future AGI flow in plain words and AI wires the nodes[4].
References
List of sources used to gather information about the Future AGI integration.
- Future AGI integration source code, module specs and credentials implementation.
- Internal Future AGI integration documentation, structured input and output parameters, scopes, and authentication methods.
- Official Future AGI vendor API documentation, used to verify field meanings, authentication flows, and anything our own specs don't fully capture.
- WEXTL® Visual Workflow Builder, anonymized data from our technical support team.
- WEXTL® Apps Library
- WEXTL® Future AGI App Documentation
- WEXTL® Workflow Scheduler
- WEXTL® HTTP node documentation
How we write and maintain Future AGI app documentation
Explore how WEXTL® crafted Future AGI integration page documentation. Used sources, the role of AI, and how the team validates the result.





















