AI & Machine Learning
Connect Honeyhive to Your AI Agents
Enable your Wkil agents to log LLM events, run evaluations, and manage datasets through a secure Honeyhive integration.
Authentication: API key
What you can do
- Track LLM events and sessions
- Run and compare evaluation experiments
- Manage datasets and datapoints
Available capabilities may vary by authentication and workspace configuration.
Actions supported by the connector
Create Event
Log a new evaluation or observability event for a project.
Start Evaluation Run
Kick off a new experiment run against a dataset.
Get Evaluation Runs
Retrieve past evaluation runs and their results.
Compare Experiment Runs
Compare two evaluation runs side by side.
Add Datapoints to Dataset
Append new datapoints to an existing dataset.
Practical agent use cases
- An agent logs every model call for later evaluation review.
- An agent triggers a new evaluation run after a prompt change.
How it works with Wkil
- 1Choose the integrationAdd HoneyHive to your agent from inside the Wkil platform.
- 2Grant the permissions it needsDefine precisely what the agent can access and perform.
- 3Test, then run itTest actions before they go live, with human approval where needed.
Permissions always stay in your control — you can scope access and require human approval before any sensitive action.
Related integrations
FAQ
Does this need my Honeyhive API key?
Yes — authentication uses an API key scoped to your Honeyhive account.
Can an agent start an evaluation automatically?
Yes, and every action can require human approval before it runs.