> ## 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.

# Launch Checklist

> Everything to verify before your agent goes live to real users.

<Warning>
  Complete every section before deploying to real users. Skipping even one item is how production incidents happen.
</Warning>

## 1. Agent Quality

<Card title="Agent Quality Checks" icon="robot" className="glass-effect">
  * [ ] Agent has **one clear, specific job** — not "be helpful with everything"
  * [ ] Instructions include: what to do, what tone to use, what to refuse
  * [ ] Instructions include explicit rules for **edge cases** you've identified
  * [ ] Agent doesn't hallucinate answers when tools return no results
  * [ ] Agent asks a useful clarifying question when the request is vague
  * [ ] Response format matches the deployment channel (markdown for web, Telegram format for Telegram)
  * [ ] Responses are under 200 words for simple questions
</Card>

## 2. Tools & Integrations

<Card title="Tool & Integration Checks" icon="plug" className="glass-effect">
  * [ ] Every connected tool has a clear **reason** for being connected
  * [ ] Read-only tools are used where write access isn't needed
  * [ ] High-risk write tools (payments, email sends) require explicit confirmation in instructions
  * [ ] All integration credentials are stored as environment variables — not hardcoded
  * [ ] OAuth tokens are connected and not expired
  * [ ] Each tool was tested in the Playground at least once with real data
  * [ ] Tool failure responses are tested — agent should gracefully explain failures
</Card>

## 3. Memory

<Card title="Memory Checks" icon="brain" className="glass-effect">
  * [ ] The agent remembers context across **at least 3 messages** in a test conversation
  * [ ] Sensitive data (payment cards, one-time codes) is **not** stored in persistent memory
  * [ ] Memory keys have descriptive names, not generic ones (`"user_name"`, not `"name"`)
  * [ ] Session IDs are stable and user-scoped (for API channel)
  * [ ] Memory TTLs are set appropriately for the use case
</Card>

## 4. Deployment

<Card title="Deployment Checks" icon="rocket" className="glass-effect">
  * [ ] Agent deployed to **one channel** and tested end-to-end
  * [ ] Webhook is live and verified (for Telegram and Slack)
  * [ ] API key is set in environment — not exposed in client code
  * [ ] Rate limits are configured: runs/user/hour and runs/day
  * [ ] A rollback plan exists: know which deployment to revert to
  * [ ] Staging environment tested before production deploy
</Card>

## 5. Observability

<Card title="Observability Checks" icon="chart-line" className="glass-effect">
  * [ ] A test run trace is visible in the **Runs** tab
  * [ ] The trace shows: user input, context loaded, tools called, response
  * [ ] Error runs show useful failure information — not just "Error"
  * [ ] At least one alert is configured (high error rate, slow latency)
  * [ ] You know how to use **HiveMind Debug** to diagnose a bad run
</Card>

## 6. Security

<Card title="Security Checks" icon="shield" className="glass-effect">
  * [ ] No secrets in HiveLang source files or version control
  * [ ] API channel requires authentication — public endpoint is not exposed
  * [ ] Agent refuses requests that are clearly outside its scope
  * [ ] Agent does not expose other users' data
  * [ ] High-risk actions (refunds, account changes) require explicit user confirmation
  * [ ] You have tested a prompt injection attempt — agent should not follow malicious instructions
</Card>

## Post-launch monitoring

<Steps>
  <Step title="Watch the first 50 runs">
    Open the **Runs** tab and review each run manually for the first 50 real user interactions. Fix anything that looks wrong immediately.
  </Step>

  <Step title="Check error rate daily for week 1">
    A healthy error rate is under 5%. If you see spikes, open the traces immediately — don't wait.
  </Step>

  <Step title="Review user confusion patterns">
    Look for repeated clarifying questions from users — this signals a gap in your instructions. Fix it the same day.
  </Step>

  <Step title="Set a weekly review cadence">
    Every week, spend 15 minutes reviewing runs and looking for improvement opportunities. The best agents are iterated, not launched and forgotten.
  </Step>
</Steps>

## Common pre-launch mistakes

| Mistake                           | Why it matters                          | Fix                                     |
| --------------------------------- | --------------------------------------- | --------------------------------------- |
| Vague instructions                | Agent gives inconsistent answers        | Add specific rules and examples         |
| Missing failure handling          | Agent crashes silently on tool errors   | Add "if tool fails, say X" instructions |
| No rate limits                    | One user can exhaust your quota         | Set per-user limits before launch       |
| Untested edge cases               | Real users always hit edge cases        | Test 10 edge cases before launch        |
| Deploying to all channels at once | Each channel has unique bugs            | Deploy and verify one at a time         |
| No alerting                       | You find out about incidents from users | Set up error rate and latency alerts    |

## Next reads

<CardGroup cols={3}>
  <Card title="Deployment Guide" icon="rocket" href="./deployment-guide" className="glass-effect" />

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

  <Card title="Connect Channels & Tools" icon="link" href="./connect-bot-channels-and-tools" className="glass-effect" />
</CardGroup>