New: every message picks a fast or a slow model

Honeyhive

HoneyHive is a modern AI observability and evaluation platform that enables developers and domain experts to collaboratively build reliable AI applications faster.

What agents can do

Actions24

  • Add datapoints to dataset

    Tool to add datapoints to a dataset.

  • Create batch model events

    Tool to create multiple model events in a single request.

  • Create batch tool events

    Tool to log a batch of external API calls as tool events.

  • Create dataset

    Tool to create a dataset.

  • Create tool

    Tool to create a new tool.

  • Delete datapoint

    Tool to delete a specific datapoint by its ID.

  • Delete dataset

    Tool to delete a dataset by ID.

  • End evaluation run

    Tool to mark an evaluation run as completed.

16 more
  • Get configurations

    Tool to retrieve a list of configurations.

  • Get datasets

    Tool to retrieve a list of datasets.

  • Get metrics

    Tool to retrieve all metrics.

  • Get projects

    Tool to retrieve projects.

  • List tools

    Tool to list all available Honeyhive tools.

  • Retrieve datapoint

    Tool to retrieve a specific datapoint by its ID.

  • Retrieve datapoints

    Tool to retrieve a list of datapoints.

  • Retrieve events

    Tool to retrieve events by filters.

  • Retrieve experiment result

    Tool to retrieve the result of a specific experiment run.

  • Start evaluation run

    Tool to initiate an evaluation run using external datasets.

  • Start session

    Tool to start a new session.

  • Update datapoint

    Tool to update a specific datapoint.

  • Update dataset

    Tool to update an existing dataset.

  • Update event

    Tool to update an event.

  • Update metric

    Tool to update an existing metric.

  • Update project

    Tool to update a project's name or description.

How it connects

You paste an API key from Honeyhive on a page Composio hosts, so the key never passes through Definable.

Keep the connection to yourself or share it with your workspace. Any action that writes or sends can wait for your approval.