The End-to-End AI Automations Platform for building and deploying AI workflows, pipelines, chatbots, and knowledge bases.
The End-to-End AI Automations Platform for building and deploying AI workflows, pipelines, chatbots, and knowledge bases. On Nagent, Vectorshift is exposed as a fully-configurable developer tools integration that any agent can call — 11 actions, and API key authentication. No code is required to wire Vectorshift into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Vectorshift to automate the kinds of tasks developer tools teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Vectorshift into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Vectorshift, with input parameters and output schema. Drop these into any step of an agent built in Helix.
VECTORSHIFT_CREATE_CHATBOTTool to create a new chatbot. Chatbots are conversational AI interfaces built on pipelines. Use when you need to create a new chatbot with a specific pipeline configuration.
Input parameters
Name of the chatbot (required by API, defaults to empty string)
Input configuration (required by API, defaults to empty string)
Output configuration (required by API, defaults to empty string)
Whether the chatbot is deployed. Must be explicitly set to true or false
Pipeline configuration object with 'id' and 'version' fields. The 'id' is the pipeline ID (can be obtained from LIST_PIPELINES endpoint), and 'version' is typically 'latest'
Description of the chatbot (required by API, defaults to empty string)
Slack integration configuration (required by API, defaults to empty dict)
Access configuration (required by API, defaults to empty dict)
Twilio integration configuration (required by API, defaults to empty dict)
Deployment options configuration (required by API, defaults to empty dict)
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
VECTORSHIFT_DELETE_CHATBOTTool to delete a chatbot by its ID. Permanently removes the chatbot from the account. Use when you need to remove a chatbot that is no longer needed.
Input parameters
The ID of the chatbot to delete. This is the unique identifier for the chatbot that was returned when the chatbot was created or listed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
VECTORSHIFT_GET_CHATBOTTool to fetch an existing chatbot by its ID or name. Returns chatbot configuration and metadata. Use when you need to retrieve details about a specific chatbot. Either chatbot ID or name must be provided.
Input parameters
Chatbot identifier. Required if name is not provided.
Chatbot name. Required if id is not provided.
Organization identifier for name-based lookup. Optional parameter used when fetching by name.
User identifier for name-based lookup. Optional parameter used when fetching by name.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
VECTORSHIFT_GET_KNOWLEDGE_BASETool to fetch an existing knowledge base by its ID or name. Returns knowledge base configuration and metadata. Use when you need to retrieve details about a specific knowledge base.
Input parameters
Knowledge base identifier. Either id or name must be provided.
Name of the knowledge base. Either id or name must be provided.
Optional organization name for name-based search. Only valid when using name parameter.
Optional username for name-based search. Only valid when using name parameter.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
VECTORSHIFT_GET_PIPELINETool to fetch an existing pipeline by its ID or name. Returns pipeline configuration and metadata. Use when you need to retrieve a specific pipeline's details, configuration, or metadata.
Input parameters
Pipeline identifier. Either id or name is required to fetch the pipeline.
Pipeline name. Either id or name is required to fetch the pipeline.
Organization name for name-based search. Used when searching by pipeline name.
Username for name-based search. Used when searching by pipeline name.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
VECTORSHIFT_LIST_CHATBOTSTool to list all available chatbots in the account. Use when you need to retrieve chatbot IDs or full chatbot details.
Input parameters
Include full chatbot objects in the response. When false, only object_ids are returned.
Include shared chatbots in the results.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
VECTORSHIFT_LIST_PIPELINESTool to list all available pipelines in the VectorShift account. Use when you need to retrieve the catalog of pipelines. Supports filtering for shared pipelines and verbose output with full pipeline details.
Input parameters
Include full pipeline objects in the response. When set to true, returns complete pipeline objects instead of just IDs.
Include shared pipelines in the results. When set to true, pipelines shared with the account will be included in the response.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
VECTORSHIFT_LIST_TRANSFORMATIONSTool to list all available transformations in the account. Use when you need to retrieve transformation IDs or complete transformation objects.
Input parameters
Returns complete transformation objects instead of just IDs. Defaults to false.
Incorporates shared transformations into results. Defaults to false.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
VECTORSHIFT_RUN_PIPELINETool to run a VectorShift pipeline with the given inputs. Use when you need to execute a pipeline and get its results or run_id for asynchronous execution. Returns the pipeline execution status, run_id, and outputs if execution completed synchronously.
Input parameters
The ID of the pipeline to run
Input values for the pipeline as key-value pairs. The keys should match the input names defined in your pipeline configuration.
Optional conversation ID for maintaining context across multiple pipeline runs
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
VECTORSHIFT_RUN_PIPELINE_BULKTool to run a VectorShift pipeline in bulk with multiple sets of inputs. Use when you need to batch process multiple pipeline executions in a single API call. Returns the overall status and an array of outputs with run_id for each execution.
Input parameters
The ID of the pipeline to run in bulk
Array of run configurations, each containing inputs for one pipeline execution. Multiple runs will be processed in bulk.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
VECTORSHIFT_TERMINATE_PIPELINETool to terminate a running pipeline execution. Use when you need to stop a pipeline run by its run_id.
Input parameters
The ID of the pipeline whose run should be terminated.
The run ID to terminate.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 63 agents privately built on Nagent that already use Vectorshift.
Build on Nagent
Connect Vectorshift to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Vectorshift, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Vectorshift is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Vectorshift is connected, you configure its 11 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Vectorshift steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Vectorshift event fires, the agent kicks off automatically.
Every Vectorshift action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Vectorshift ships with 11 pre-built developer tools actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Vectorshift together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Vectorshift-based workflows tailored to your business.