> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bothive.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Get your first Bothive agent running in 5 minutes — no code required.

<div className="hero-container">
  <h1 className="hero-title">
    Get Running in 5 Minutes
  </h1>

  <p className="hero-subtitle">
    From a blank account to a deployed, observable agent — without writing a single line of code.
  </p>
</div>

## What you'll build

By the end of this guide you'll have:

<CardGroup cols={3}>
  <Card title="A Working Agent" icon="robot" className="glass-effect">
    Clear instructions, a defined scope, and at least one connected tool
  </Card>

  <Card title="A Tested Conversation" icon="flask" className="glass-effect">
    Five real message tests covering happy path, edge cases, and tool failures
  </Card>

  <Card title="A Live Deployment" icon="rocket" className="glass-effect">
    Your agent accessible on Web, Telegram, or via API
  </Card>
</CardGroup>

## Step 1 — Pick one job

The most common mistake is starting too broad.

<Note>
  **Rule of thumb:** If your agent description contains the word "anything" or "everything," narrow it down before writing a single instruction.
</Note>

Use this sentence to define your agent:

```
This agent helps [who] do [task] using [context/tools] and should never [boundary].
```

**Examples:**

| Too broad                      | Just right                                                  |
| ------------------------------ | ----------------------------------------------------------- |
| Be a helpful AI assistant      | Help SaaS customers troubleshoot failed payments            |
| Answer all support tickets     | Handle billing questions and escalate edge cases            |
| Do everything a calendar needs | Schedule meetings based on my availability and send invites |

## Step 2 — Create the agent

<Steps>
  <Step title="Open the Dashboard">
    Navigate to [bothive.cloud/dashboard](https://bothive.cloud/dashboard) and click **Bots** in the sidebar.
  </Step>

  <Step title="Click New Bot">
    Hit **New bot** in the top right corner.
  </Step>

  <Step title="Choose your build path">
    | Path         | Best for                      | Speed    |
    | ------------ | ----------------------------- | -------- |
    | **HiveMind** | Plain English description     | Fastest  |
    | **Builder**  | Manual configuration, no code | Fast     |
    | **HiveLang** | Code-first, maximum control   | Flexible |
  </Step>

  <Step title="Name it specifically">
    Good: `Billing Support Agent` — Bad: `My Bot`
  </Step>
</Steps>

## Step 3 — Write instructions

Your instructions are the single biggest factor in agent quality. Spend time here.

```
You are a billing support agent for [Your Product].

Your job:
- Explain invoice and payment issues clearly and concisely
- Ask one clarifying question when the request is vague
- Guide users to the next safe action step-by-step

Rules:
- Never claim a payment succeeded unless billing data confirms it
- Never expose internal IDs or system details
- If a tool fails, explain what failed and suggest a retry
- Keep responses under 150 words unless detail is explicitly needed
```

<Tip>
  Use bullet points in instructions. Numbered lists help when you want specific ordering. Prose paragraphs tend to get ignored by the model mid-instruction.
</Tip>

## Step 4 — Connect tools (only what's needed)

<Warning>
  Every extra tool adds latency and risk. Add tools one at a time and test after each addition.
</Warning>

| Agent Type          | Recommended Tools                          | Risk Level |
| ------------------- | ------------------------------------------ | ---------- |
| Billing support     | Paystack / Stripe read, subscriptions read | Low        |
| Calendar scheduling | Google Calendar, Gmail                     | Medium     |
| Developer assistant | GitHub read, docs search                   | Low        |
| Community helper    | Telegram read, knowledge base              | Low        |
| Code review         | GitHub PR read, write comments             | Medium     |

## Step 5 — Test before deploying

Run at least **five** test messages in the Playground before deploying anywhere.

<CardGroup cols={2}>
  <Card title="Normal Request" icon="check" className="glass-effect">
    "Why did my invoice fail?" — expect a clear explanation and next step
  </Card>

  <Card title="Vague Request" icon="question" className="glass-effect">
    "It didn't work" — expect a useful clarifying question
  </Card>

  <Card title="Tool Needed" icon="plug" className="glass-effect">
    "Check my subscription" — expect correct tool selection with safe arguments
  </Card>

  <Card title="Tool Failure" icon="triangle-exclamation" className="glass-effect">
    Simulate billing lookup failure — expect graceful error message with retry path
  </Card>
</CardGroup>

## Step 6 — Deploy

Start with **one** surface. Add more channels after you've confirmed the first one works.

| Surface             | Best when                                 | Setup time |
| ------------------- | ----------------------------------------- | ---------- |
| **Hosted web link** | You want to share the agent quickly       | 30 seconds |
| **Telegram**        | Users already message you on Telegram     | 5 minutes  |
| **API**             | Your SaaS backend needs to call the agent | 10 minutes |
| **Slack**           | Your team or customers use Slack          | 10 minutes |

## Step 7 — Open observability

After your first real run, open the trace.

<Steps>
  <Step title="Open the Runs tab">
    Go to your bot → **Runs** to see all executions.
  </Step>

  <Step title="Click a run">
    Inspect: user message, context loaded, tools selected, latency, errors.
  </Step>

  <Step title="Use HiveMind Debug">
    If a run went wrong, click **Debug with HiveMind** to get an AI-powered root cause analysis.
  </Step>

  <Step title="Fix and redeploy">
    Update instructions or tool config based on what the trace reveals.
  </Step>
</Steps>

## Launch-ready checklist

<Card title="Before you go live" icon="circle-check" className="glass-effect">
  * [ ] Agent has **one clear job** with a defined audience
  * [ ] Instructions include **what to do**, **what tone to use**, and **what to refuse**
  * [ ] Every tool has a **reason** for being connected
  * [ ] At least **five test cases** passed in the Playground
  * [ ] **Memory** works across a multi-message conversation
  * [ ] **One channel** deployed and tested end-to-end
  * [ ] **Observability** shows meaningful traces
  * [ ] Billing and usage limits are configured
</Card>

## HiveLang starter

If you prefer to define the agent in code:

```hivelang theme={null}
bot BillingSupport {
  description: "Helps customers understand billing and subscription issues"

  capabilities {
    billing.getInvoice
    billing.getSubscription
    support.createTicket
  }

  instructions {
    You are a billing support agent.

    Help users understand failed payments, subscription status,
    and next steps. Always ask for clarification before guessing.
    Never claim a payment succeeded unless billing data confirms it.
  }

  before input {
    log info: "Support request received"
  }
}
```

## Next reads

<CardGroup cols={3}>
  <Card title="Build Your First Agent" icon="hammer" href="./guides/build-your-first-agent" className="glass-effect" />

  <Card title="Deployment Guide" icon="rocket" href="./guides/deployment-guide" className="glass-effect" />

  <Card title="Observability" icon="chart-line" href="./concepts/observability" className="glass-effect" />
</CardGroup>