Understanding HiveLang
HiveLang is our proprietary orchestration language. It's designed to give you deterministic control over non-deterministic AI models.
Why not just use Python?
Python is great, but it requires boilerplate for LLM calls, retries, and tool parsing. HiveLang treats LLMs and tools as first-class primitives.
Syntax Basics
Calling Agents
You can invoke an agent synchronously and wait for its result:
rubylet response = call SupportAgent with { query: "I forgot my password" } say response
Tools and APIs
HiveLang makes calling external APIs trivial.
rubytry let weather = call WeatherAPI.getCurrent { city: "London" } say "It is currently ${weather.temp} degrees." catch say "I couldn't fetch the weather right now." end
Parallel Execution
Need to do three things at once?
rubyparallel call Calendar.check call CRM.lookup call Slack.status end
HiveLang handles the concurrency and joins the results automatically. Dive into the /docs for the full language reference!
Use the test pane to iterate quickly. Every change you make is live — no need to save first.
API keys are shown only once. Store them securely and never commit them to version control.
Test your bot with edge cases before deployment. Try empty inputs, long messages, and special characters.
Chain multiple specialized bots in a workflow for better results than one general-purpose bot.