Humanloop helps developers build and refine AI applications, offering user feedback loops, model training, and data annotation to iterate on language model performance
Humanloop helps developers build and refine AI applications, offering user feedback loops, model training, and data annotation to iterate on language model performance On Nagent, Humanloop is exposed as a fully-configurable artificial intelligence integration that any agent can call — 4 actions, and API key authentication. No code is required to wire Humanloop into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Humanloop to automate the kinds of tasks artificial intelligence 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 Humanloop 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 Humanloop, with input parameters and output schema. Drop these into any step of an agent built in Helix.
HUMANLOOP_CREATE_PROJECTThis tool creates a new project in Humanloop. It is an independent action that generates a project by accepting a project's name (required), an optional description, and an optional organization_id. Upon execution, it returns details of the created project, including the project's id, name, description, created_at timestamp, and organization_id.
Input parameters
The name of the project (required).
A description of the project.
ID of the directory to assign the project to.
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
HUMANLOOP_DELETE_PROJECTThis tool allows you to delete a specific project from your Humanloop organization. The deletion is permanent and cannot be undone. All associated data, including sessions, datapoints, and evaluations linked to the project, will be permanently removed.
Input parameters
The ID of the project to delete (must start with 'pr_')
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
HUMANLOOP_LIST_EXPERIMENTSThis tool retrieves an array of experiments associated with a specific project in Humanloop. It requires a project_id (starting with 'pr_') and returns details including experiment_id, name, description, creation timestamp, status, configuration details, and metrics/results. It is useful for monitoring experiments, analyzing results, tracking model configurations, and comparing experimental setups.
Input parameters
Page offset for pagination. Defaults to 1.
Number of experiments per page. Defaults to 10.
The unique identifier of the project (must start with 'pr_')
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
HUMANLOOP_LIST_SESSIONSThis tool retrieves a paginated list of sessions for a specific project in Humanloop. It requires a project_id (and optionally, page and size for pagination) and returns session details such as id, reference_id, project information, datapoints_count, first_inputs, last_output, created_at, and updated_at. This enables users to monitor and analyze historical project interactions.
Input parameters
Page offset for pagination. Defaults to 1.
Number of sessions per page. Defaults to 10.
The unique identifier of the project (starts with 'pr_')
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 61 agents privately built on Nagent that already use Humanloop.
Build on Nagent
Connect Humanloop 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 Humanloop, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Humanloop is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Humanloop is connected, you configure its 4 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Humanloop 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 Humanloop event fires, the agent kicks off automatically.
Every Humanloop 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 Humanloop ships with 4 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Humanloop together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Humanloop-based workflows tailored to your business.