AI & Machine Learning

Connect AI ML API to Your AI Agents

Let your Wkil agents generate chat completions, stream responses, and ground answers with web search through AI ML API.

Authentication: API key

What you can do

Available capabilities may vary by authentication and workspace configuration.

Completion and Chat Completion

Generate text completions or run an interactive chat session.

Function Calling

Let a model call defined functions as part of its response.

Streaming Mode

Receive model output as a real-time stream.

Web Search

Ground a model's response with live web search results.

Code Generation

Generate code snippets from a natural-language prompt.

Vision in Text Models (Image-to-Text)

Convert an image into a textual description.

Thinking / Reasoning

Run multi-step reasoning tasks through the model.

Model Selection

Fires when a request is routed to a specific model based on the task.

An agent streams a long-form response to a user instead of waiting for the full completion.
An agent grounds an answer with a live web search before responding.

1
Choose the integration
Add AI ML API to your agent from inside the Wkil platform.
2
Grant the permissions it needs
Define precisely what the agent can access and perform.
3
Test, then run it
Test 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.

Can I choose which model handles a request?

Yes — requests can be routed to a specific model based on the task at hand.