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

# Creating Agents

> Create a SlackHive agent with the two-step flow, then use Coach, Slack, tools, and permissions after creation.

Click **New Agent** to open the two-step creation flow. It is intentionally short: create the teammate first, then tune the machinery from the agent page.

Before you start, skim [Concepts - What Goes Where](/agents/concepts). It explains the four layers of an agent's brain: system prompt, skills, memory, and wiki.

## Step 1: Identity

Identity defines how the agent appears in the dashboard and how it fits into your AI team.

| Field          | What it is                                                      |
| -------------- | --------------------------------------------------------------- |
| **Agent name** | Display name shown in Slack and the dashboard                   |
| **Role**       | **Specialist** does the work; **Boss** delegates to specialists |
| **Reports to** | For specialists, choose one or more Boss agents                 |
| **Tags**       | Optional labels for dashboard filtering and team organization   |

Boss agents skip persona selection. Their operating prompt is generated from the team registry so it stays synchronized with the specialists that report to them.

## Step 2: Profile or Launch

For specialist agents, choose a starting brain:

| Option            | Use when                                                      |
| ----------------- | ------------------------------------------------------------- |
| **Persona**       | You want a strong starter prompt and skills for a common role |
| **Blank**         | You know the job and want Coach to draft the details          |
| **Import config** | You have an exported agent config with prompt and skills      |

For Boss agents, Step 2 is a launch review. Create the boss, then add specialists and let the team registry drive the orchestrator prompt.

<Tip>
  The creation flow does not need to capture every rule. After creation, open **Coach** and describe what you want in plain English. Coach can draft or refine system prompts, skills, memory, evaluation cases, and operating rules.
</Tip>

## Configure after creation

The creation flow sets the agent identity and starting profile. Everything operational is configured from the agent page after creation.

| Area                          | Where to configure it                   |
| ----------------------------- | --------------------------------------- |
| Slack connection              | Agent page → Overview                   |
| Model                         | Agent page → Overview                   |
| MCP servers                   | Agent page → Tools                      |
| Internet / shell access       | Agent page → Tools                      |
| System prompt, skills, memory | Agent page → Instructions               |
| Wiki folders                  | Agent page → Wiki                       |
| Access control                | Agent page → Settings / access controls |
| Sensitive-data monitoring     | Agent page → Settings → General         |
| Evals and regression cases    | Agent page → Settings → Evals           |
| Test conversation             | Agent page → Test                       |

This keeps creation fast while keeping each setup area easy to find.

## After creation

SlackHive opens the agent page. A typical setup sequence is:

1. **Connect Slack** - create or reuse a Slack app, then save bot credentials.
2. **Tune with Coach** - ask Coach to build or improve the system prompt and skills.
3. **Assign tools** - add MCP servers and capabilities from the Tools tab.
4. **Assign knowledge** - attach shared Knowledge Library folders.
5. **Set safety controls** - configure sensitive-data monitoring and redaction for agents that touch private data.
6. **Test and evaluate** - use Test Mode, then add eval cases for behavior that must not regress.
7. **Invite to Slack** - invite the bot and start mentioning it.

## Agent page tabs

| Tab              | What you manage                                                        |
| ---------------- | ---------------------------------------------------------------------- |
| **Overview**     | Identity, model, Slack connection, status, satisfaction, configuration |
| **Instructions** | System prompt, skills, and memory                                      |
| **Tools**        | MCP servers, internet access, shell access                             |
| **Wiki**         | Shared Knowledge Library folders assigned to this agent                |
| **Audiences**    | Group-specific prompt overrides                                        |
| **Settings**     | Access and operational settings                                        |

Changes hot-reload within seconds. You do not need to restart SlackHive after editing an agent.

## Specialist vs Boss

| Agent type     | Behavior                                                                                               |
| -------------- | ------------------------------------------------------------------------------------------------------ |
| **Specialist** | Receives direct mentions, uses tools, answers users, can report to one or more Boss agents             |
| **Boss**       | Receives high-level requests, delegates to specialists in the Slack thread, and summarizes the outcome |

See [Boss Agents](/agents/boss-agents) for delegation patterns and team registry behavior.

## Next steps

<CardGroup cols={2}>
  <Card title="Coach" icon="comments" href="/agents/coach">
    Build prompts, skills, memories, and operating rules through chat.
  </Card>

  <Card title="AI Backends" icon="server" href="/configuration/ai-backends">
    Choose whether agents run on Codex/OpenAI or Claude/Anthropic.
  </Card>

  <Card title="Knowledge Library" icon="book" href="/agents/knowledge-base">
    Build shared wiki folders from repos, files, or URLs.
  </Card>

  <Card title="Tools & Permissions" icon="shield" href="/agents/tools">
    Configure MCP servers, internet access, shell access, and tool safety.
  </Card>

  <Card title="Agent Evals" icon="shield-check" href="/agents/evals">
    Add healthchecks and regression cases before going live.
  </Card>

  <Card title="Sensitive Data" icon="shield-alert" href="/features/sensitive-data">
    Configure detection, redaction, and audit workflows.
  </Card>
</CardGroup>