Skip to content
Changelog

Report a bug

Parallel integration: operations for AI agents

Parallel connects to Type.com as an integration. This page lists the 37 operations documented for Claude and Codex in Type.com: 18 read, 17 write, 2 destructive.

About Parallel

Parallel offers a Task API for automated, structured web research, transforming natural language queries into precise, schema-compliant outputs.

Categories: Analytics & Data

How to connect Parallel to Type.com

Access
Organization connection: one shared account for the workspace.

To add the connection, follow the steps in Space connections.

Documented operations

37 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.

37 operations listed.

Search

  • Read

    Search

    Searches the web.

Image Search

  • Write

    Image search

    Searches the web for images.

Extract

  • Write

    Extract

    Extracts relevant content from specific web URLs.

Tasks

  • Read

    Retrieve Task Group

    Retrieves aggregated status across runs in a TaskGroup.

  • Read

    Stream Task Group Events

    Streams events from a TaskGroup: status updates and run completions. The connection will remain open for up to an hour as long as at least one run in the group is still active.

  • Read

    Fetch Task Group Runs

    Retrieves task runs in a TaskGroup and optionally their inputs and outputs. All runs within a TaskGroup are returned as a stream. To get the inputs and/or outputs back in the stream, set the corresponding includeinput and includeoutput parameters to true.

  • Read

    Retrieve Task Group Run

    Retrieves run status by runid. This endpoint is equivalent to fetching run status directly using the retrieve() method or the tasks/runs GET endpoint. The run result is available from the /result endpoint.

  • Read

    Retrieve Task Run

    Retrieves run status by runid. The run result is available from the /result endpoint.

  • Read

    Stream Task Run Events

    Streams events for a task run. Returns a stream of events showing progress updates and state changes for the task run. For task runs that did not have enableevents set to true during creation, the frequency of events will be reduced.

  • Read

    Retrieve Task Run Input

    Retrieves the input of a run by runid.

  • Read

    Retrieve Task Run Result

    Retrieves a run result by runid, blocking until the run is completed.

  • Write

    Create Task Group

    Initiates a TaskGroup to group and track multiple runs.

  • Write

    Add Runs to Task Group

    Initiates multiple task runs within a TaskGroup.

  • Write

    Create Task Run

    Initiates a task run. Returns immediately with a run object in status 'queued'. Beta features can be enabled by setting the 'parallel-beta' header.

Find All

  • Read

    Retrieve FindAll Run Status

    Retrieve a FindAll run.

  • Read

    Stream FindAll Events

    Stream events from a FindAll run. Args: request: The Shapi request findallid: The FindAll run ID lasteventid: Optional event ID to resume from. timeout: Optional timeout in seconds. If None, keep connection alive as long as the run is going. If set, stop after specified duration.

  • Read

    FindAll Run Result

    Retrieve the FindAll run result at the time of the request.

  • Read

    Get FindAll Run Schema

    GET /v1beta/findall/runs/{findall_id}/schema

  • Write

    Fast Entity Search

    Return ranked entities matching a natural language objective. This endpoint performs a best-effort search optimized for low latency. To keep responses fast, it returns a fixed set of attributes and supports queries of limited complexity.

  • Write

    Ingest FindAll Run

    Transforms a natural language search objective into a structured FindAll spec. The generated specification serves as a suggested starting point and can be further customized by the user.

  • Write

    Create FindAll Run

    Starts a FindAll run. This endpoint immediately returns a FindAll run object with status set to 'queued'. You can get the run result snapshot using the GET /v1beta/findall/runs/{findallid}/result endpoint.

  • Write

    Add Enrichment to FindAll Run

    Add an enrichment to a FindAll run.

  • Write

    Extend FindAll Run

    Extend a FindAll run by adding additional matches to the current match limit.

  • Destructive

    Cancel FindAll Run

    Cancel a FindAll run.

Monitor

  • Read

    List Monitors

    List monitors ordered by creation time, newest first. Monitors are sorted by createdat descending. limit defaults to 100. Use nextcursor from the response and pass it as cursor to fetch the next page. Pagination ends when nextcursor is absent.

  • Read

    Monitor Stats

    Return aggregate counts of your monitors. Counts every monitor across all statuses, broken down by status and then by processor and run frequency (e.g. '1h', '1d') within each status. Statuses, processors, and frequencies with zero monitors are omitted.

  • Read

    Retrieve Monitor

    Retrieve a monitor. Retrieves a specific monitor by monitorid. Returns the monitor configuration including status, frequency, query, and webhook settings.

  • Read

    List Monitor Events

    List events for a monitor, newest first. Pass eventgroupid to narrow results to a single execution. Otherwise returns all executions newest-first; use nextcursor to paginate. Set includecompletions=true to also include no-change executions.

  • Write

    Create Monitor

    Create a monitor. Monitors run on a fixed frequency to detect material changes in web content. Set type=eventstream to monitor a search query, or type=snapshot to monitor a specific task run's output.

  • Write

    Trigger Monitor Run

    Trigger an immediate monitor run. Enqueues a one-off execution of the monitor outside its normal schedule. The monitor's regular schedule is not affected. An event is only emitted if the execution detects a material change. Cancelled monitors cannot be triggered.

  • Write

    Update Monitor

    Update a monitor. Only fields explicitly included in the request body are changed. Pass null to clear webhook, metadata, or settings.advancedsettings; every other field rejects null, so omit it to leave it unchanged.

  • Destructive

    Cancel Monitor

    Cancel a monitor. Permanently stops the monitor from running. Cancellation is irreversible — create a new monitor to resume monitoring. Cancelling an already-cancelled monitor is a no-op.

Memory

  • Read

    Retrieve Memory

    Retrieves relevant or recent runs from the selected memory. Provide a query to rank results by relevance; leave it empty to return the most recent runs.

  • Write

    Clear Memory

    Clears all entries from the selected memory without deleting the underlying tasks, monitors, or FindAll runs.

  • Write

    Evict from Memory

    Removes a task run, monitor, or FindAll run from the selected memory without deleting the original resource.

Chat API (Beta)

  • Write

    Chat Completions

    Chat completions. This endpoint can be used to get realtime chat completions. It can also be used with the Task API processors to get structured, research outputs via a chat interface.

Responses API

  • Write

    Create Response

    Create a response. Generates an answer to the given input, grounded in live web research and annotated with URL citations. Set model to parallel; reasoning.effort (low/medium/high/auto) controls how much research is performed, trading response time for answer quality.

See How connections work for access and permissions, or browse all integrations.