AgentX and Parallel Integration

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

Keep AgentX and Parallel matched by integrating their events and actions. When ai events happen in AgentX, update the Parallel automatically - without any line of code in visual workflow builder.

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

Learn about AgentX and Parallel

Detailed info you need to know about AgentX and Parallel 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]

  • Parallel

    • AI
    • 1 trigger
    • 17 searches
    • 19 actions

    Web search, page extraction and deep research for agents and workflows.[6]

How to connect AgentX to Parallel

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

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

WEXTL exposes actions and triggers for AgentX and Parallel 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.

Parallel triggersAgentX actions

Parallel modules

  • Add an Enrichment to a FindAll Run Extends the candidates of a FindAll run with extra data described by an Output Schema. Use Processor to choose the tier and MCP Servers to let the enrichment call outside servers.
  • Add Runs to a Task Group Queues several task runs in one batch from a JSON array of Inputs. Use Default Task Spec for runs without their own, and turn on Refresh Status to bring the group status up to date.
  • Cancel a FindAll Run Stops a FindAll run that is still searching and marks it as cancelled.
  • Cancel a Monitor Cancels a monitor and ends its checks on the set Frequency.
  • Clear Memory Empties a whole memory scope, removing everything stored under its Memory Scope Key.
  • Create a Chat Completion Answers a conversation sent as Messages, each with a Role and Content, from a Parallel Model. Use Previous Interaction ID to continue earlier context and Max Tokens to cap the reply length.
  • Create a FindAll Run Starts a search for entities matching an Objective, an Entity Type and Match Conditions. A heavier Generator searches more thoroughly. Use Exclude List to leave out entities you already know.
  • Create a FindAll Spec from an Objective Turns a plain-language Objective into a ready FindAll spec with an Entity Type, Match Conditions and a Generator. Review it before starting a run.
  • Create a Monitor Sets up a recurring watch on the web with a Type and a Frequency. Give a Query to follow a search, or a Task Run ID to follow a run, and add a Webhook URL to be called on events.
  • Create a Response Produces an answer to the text of Input, guided by optional Instructions. Use Reasoning Effort to set how much the model thinks and Previous Response ID to carry earlier context forward.
  • Create a Task Group Opens an empty container for batching task runs, optionally tagged with Metadata. The Taskgroup Id it gets is used by the other group modules.
  • Create a Task Run Researches a question or task given as Input with the chosen Processor. Heavier tiers dig deeper. Use Include Domains or Exclude Domains to restrict sources and Output Type to shape the answer.
  • Evict from Memory Removes one task run, monitor or FindAll run from memory, by its Kind and ID. Use Memory Scope Key to act on a specific scope.
  • Extend a FindAll Run Raises the target of an earlier FindAll run by the Additional Match Limit, so it keeps searching for more matches.
  • Extract Web Page Content Reads each web page from the list of URLs and returns excerpts. Add an Objective or Search Queries to focus them, Max Characters to bound their length, and turn on Full Content or Links for more.
  • Get a FindAll Run Checks how a FindAll run is going and shows its Status, Generator and Metadata.
  • Get a FindAll Run Result Downloads the Candidates found by a FindAll run along with the Run record itself.
  • Get a FindAll Run Schema Shows how a FindAll run was set up, from its Objective and Entity Type to Match Conditions and Enrichments.
  • Get a Monitor Looks up one monitor to see its Frequency, Processor, Webhook, Settings and when it last ran.
  • Get a Task Group Reads the Status and Metadata of a batch of task runs, for the Task Group ID that Create a Task Group gave you.
  • Get a Task Group Run Fetches one run that belongs to a group, using both the Task Group ID and the Run ID. Its Status tells you how far along it is.
  • Get a Task Run Polls a task run by Run ID to see its Status, its Processor and whether it is still active.
  • Get a Task Run Input Recalls what a task run was asked, returning its Input, Task Spec and Processor.
  • Get a Task Run Result Collects the Output of a task run. Use Wait Seconds, up to 600, to hold the call until the run finishes.
  • Get Monitor Stats Counts all monitors in the account as a Total, with a split by processor.
  • List Monitor Events Lists what a monitor has detected, each with Event Type, Event Date and Output. Use Event Group ID to stay with one execution and Include Completions to see runs without changes.
  • List Monitors Lists monitors with their Type, Status and Frequency, up to Limit. Without a Status filter only active monitors appear.
  • Make a Decision Answers up to 100 Questions about a State using researched evidence. Use Published After to ignore older sources and Include Excerpts to attach the supporting quotes to the Citations.
  • Make an API Call Sends a free-form request to the Parallel REST API, signed with your saved credential.
  • Retrieve Memories Searches stored memories. Use Query to narrow what is found, Kind and Since to filter by type and date, and Limit to hold the count between 1 and 25.
  • Search Entities Quickly locates entities of a given Entity Type that fit an Objective. Use Match Limit to set how many are returned, from 5 to 1000.
  • Search Images Finds pictures for one or more Search Queries. Use Objective to sharpen the ranking, Mode to trade speed against depth and Max Results to limit the haul.
  • Search Places Looks for businesses and venues matching a Query around a Location or a Latitude and Longitude. Turn on Open Now or set Max Distance (km) to narrow the hits.
  • Search Web Runs web searches for short Search Queries and returns Results with excerpts. Restrict sources with Include Domains, and bound excerpt size with Max Characters.
  • Trigger a Monitor Run Runs a monitor right now instead of waiting for its next scheduled check.
  • Update a Monitor Adjusts a monitor with a new Frequency, a deeper Processor or a revised Query. Use Include Domains to replace the domains it watches.
  • Watch Events Starts the workflow when Parallel posts a webhook event, with its Event Type, Timestamp and Data.

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 Parallel integrations. Pick any from the list below if the current combination isn't the one you need.

Automate AgentX and Parallel on WEXTL®

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

Cancel anytime.

Frequently asked questions

Common questions about connecting AgentX and Parallel.

How do I connect AgentX and Parallel?

Connect your AgentX and Parallel 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 Parallel?

Example: when the "Watch Events" trigger in Parallel fires, WEXTL can "Create a Conversation" in AgentX. AgentX has 19 actions (including Create a Conversation, Create Speech, and Create Speech Stream). Parallel has 36 actions (including Add an Enrichment to a FindAll Run, Add Runs to a Task Group, and Cancel a FindAll Run). Add filters and transforms between steps when you need them.[1]

Can AgentX trigger actions in Parallel, and Parallel 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 Parallel?

No. AgentX-to-Parallel 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 Parallel in real time?

Yes. Trigger-based automations start the moment AgentX (or Parallel) 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 + Parallel 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 Parallel?

You can build your AgentX + Parallel 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 Parallel integration.

  1. AgentX and Parallel integration source code, module specs and credentials implementation.
  2. Our AgentX and Parallel integration documentation, structured input and output parameters, scopes, and authentication methods.
  3. Official vendor API documentation for AgentX and Parallel, 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. Parallel 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 Parallel integration page documentation. Used sources, the role of AI, and how the team validates the result.

Explore AgentX and Parallel, or get started