> ## Documentation Index > Fetch the complete documentation index at: https://docs.skyfree.io/llms.txt > Use this file to discover all available pages before exploring further. # AI Agents > Create AI agents that handle conversations, follow your instructions, and hand off to your team. ## What is this? AI Agents (beta) lets you create AI-powered agents that automatically handle conversations on your connected channels — answering questions from knowledge sources, taking actions like updating contacts or handing off to a human, and following the instructions and guardrails you define, without needing a manual automation flow for every scenario. The AI Agents list page showing the Total/Active/Inactive stat tiles, Agentic Mode toggle, and the agents table ## What can I do here? * See all AI agents for the active channel with **Total Agents**, **Active Agents**, and **Inactive** stat tiles you can click to filter. * Search agents by name or description, and filter by type (**Support**, **Sales**, **FAQ**, **Booking**, **Custom**). * Toggle **Agentic Mode** on or off for the channel from the top toolbar. This is the channel's master switch: when it's off, no agent answers incoming messages, even if the agent itself is **Active**. * Create a new agent (subject to your plan's agent limit, shown as a counter on the Create button). * For each agent in the table: **Edit**, **Test** (opens the agent builder), **Export** (downloads the agent as a JSON file), **Activate/Pause**, and **Delete**. * Select multiple agents to bulk-select and delete. * **Import** an agent from a previously exported JSON file into any channel you choose. * Refresh the agent list. ## How to use it New to AI agents? Follow [Create Your First AI Agent](/workspace/ai-agents/create-your-first-agent) — a step-by-step guide with a full example. Come back here afterward for the full detail on any one tab. 1. Go to **AI Agents** in the sidebar (`/ai-agents`). You need an active channel connected to WhatsApp, Instagram, Facebook, or Web Chat. 2. Click **Create** to start a new agent (or **Edit**/**Test** on an existing row to open the same builder). The builder has one tab for each area of the agent. The AI agent builder page showing the full row of tabs across the top ### Every tab, in its own page Save the agent first — the Capabilities, External Capabilities, Skills, and Workflows tabs only unlock once the agent has been created. | Tab | What it's for | | ------------------------------------------------------------------------ | ---------------------------------------------------------- | | [General](/workspace/ai-agents/tabs/general) | Name the agent and describe its job | | [Behavior](/workspace/ai-agents/tabs/behavior) | Tone, priority, and status | | [Instructions](/workspace/ai-agents/tabs/instructions) | How it should think and act | | [Knowledge](/workspace/ai-agents/tabs/knowledge) | Facts it can look things up in | | [Capabilities](/workspace/ai-agents/tabs/capabilities) | Real actions it can take, including triggering automations | | [External Capabilities](/workspace/ai-agents/tabs/external-capabilities) | Your own APIs or MCP tools | | [Skills](/workspace/ai-agents/tabs/skills) | A specific procedure for one situation | | [Workflows](/workspace/ai-agents/tabs/workflows) | Scripted, multi-step flows bound to this agent | | [Channels](/workspace/ai-agents/tabs/channels) | Where it runs and how it talks | | [Guardrails](/workspace/ai-agents/tabs/guardrails) | Safety checks | | [Test](/workspace/ai-agents/tabs/test) | Try it before customers do | See the full [Builder Tabs](/workspace/ai-agents/tabs/overview) section for all eleven, with worked examples. ### Export and import an agent Back on the list page, use **Export** to download an agent's configuration as JSON, and **Import** to bring that JSON into another channel — this creates brand-new agent, source, and knowledge records rather than overwriting anything. ### Working with more than one agent When a channel has two or more active agents, the platform automatically adds a hidden router that reads each customer message and hands it to the agent whose [Description](/workspace/ai-agents/tabs/general) fits best — clear, different descriptions per agent are what make this accurate. Priority (set in [Behavior](/workspace/ai-agents/tabs/behavior)) decides who goes first when more than one could plausibly answer. ## Troubleshooting / Technical Notes * **The agent doesn't reply at all.** Check the three master switches: the agent's **Status** is Active, **Agentic Mode** is on for the channel, and the agent's **Channels** tab includes the channel the message came from. * **I can't create another agent.** Your plan limits how many agents you can create — the limit shows on the **Create** button. * **A customer is stuck with the agent.** Any teammate can take over the conversation in the Inbox, and you can **Pause** the agent from the list at any time. ## In this section * [Create Your First AI Agent](/workspace/ai-agents/create-your-first-agent) * [Builder Tabs](/workspace/ai-agents/tabs/overview) ## Related docs * [Automation Overview](/workspace/automation/overview) * [Inbox](/workspace/inbox/overview) * [Analytics](/workspace/analytics) — AI Usage tab * [AI Agent Settings](/platform/settings/ai-agent-settings)