Getting Started with Bothive
Bothive is where you build AI bots and use them anywhere — your website, your app, your backend. You build a bot once (in plain language or in HiveLang), and Bothive hosts it so any app can call it. This guide gets you from zero to a working bot.
1. Create your account
Head to the sign-up page and create an account. You land on the Dashboard — your home base for bots, workflows, integrations, and keys.
2. Get your bearings
A quick tour of the places you'll use most, all in the left sidebar:
- HiveMind — an AI copilot. Describe what you want and it builds bots, integrations, and workflows for you.
- Bots / My Bots — create and manage your bots.
- Orchestrator — the visual workflow builder for chaining bots and steps.
- Integrations — connect apps (Slack, Gmail, Notion, GitHub…) and your own API.
- Knowledge — upload documents your bots can search.
- API Keys (under Developer) — keys your app uses to call bots.
- Billing / Usage — your plan and credit usage.
3. Build your first bot
The fastest path:
- Go to Bots → New Bot (
/dashboard/bots/new). - Describe what the bot should do, or write a short HiveLang definition.
- Use the test pane to chat with it and iterate.
- Save it.
Prefer to talk it out? Open HiveMind and say "Build me a support bot that answers questions about my product." It scaffolds the bot and drops it into the builder.
4. Give it knowledge (optional)
A bot is only as good as what it knows. Under Knowledge, create a knowledge base and upload a PDF or docs. Attach it to your bot, and it can answer from your content.
5. Use it anywhere
Once a bot works, call it from your own app with an API key. See Connect a bot to your app for the full walkthrough.
That's the loop: build → test → use anywhere. Next, dig into Build your first bot for a deeper, step-by-step build.
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.