> ## Documentation Index > Fetch the complete documentation index at: https://docs.xpressbot.org/llms.txt > Use this file to discover all available pages before exploring further. # Capabilities > Turn on real actions the agent can take — and exactly how it decides which automation to trigger, and when. ## What is this? Capabilities are **buttons the agent may press**. Without them, it can only talk. With them, it can also update a contact, hand a chat to a person, or start one of your automations. Each one is a pre-built, tested action — turning one on doesn't require writing any code, just deciding this agent should have that power. \[SCREENSHOT: ai-agent-capabilities-tab — The Capabilities tab with a capability enabled and its confirmation/handoff-assignment options expanded] ## What can I do here? Capabilities are grouped by area: | Group | Examples | What it lets the agent do | | ---------------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------------ | | **Contacts** | Update Contact, Set Custom Field, Add/Remove Label, Move Pipeline Stage | Save what a customer tells it, tag them, move them through your pipeline | | **Conversation** | Hand off to Human, Close Conversation | End its own involvement, one way or another | | **Knowledge** | Search Knowledge, Search Help Articles | Look things up on demand instead of only using what's in its prompt | | **Catalog** | Search Catalog, Get Product | Answer product questions from your real catalog | | **Events** | Search Events, Check Availability, Register, Cancel Registration | Handle event bookings | | **Automation** | Trigger Automation, Send Template | Start an existing automation, or send an approved WhatsApp template | For any enabled capability, you can turn on **Require customer confirmation** — the agent asks "Shall I go ahead?" before it acts. For **Hand off to Human** specifically, set the **Handoff Assignment**: Unassigned, Fixed team member, Round robin, or Least busy. ## How to use it ### Turn on only what this agent actually needs Each capability already comes with its own built-in description telling the model when it's appropriate — you don't write that part. You're deciding which powers this particular agent should have, not how it should use them. ### Set Custom Field only writes to fields you've already created The agent can save information a customer shares — a name, an email, a budget — into a [custom field](/workspace/contacts/custom-fields). It can **only** write into fields that already exist for this channel, and it checks the value against that field's type (a real email for an Email field, an allowed option for a Dropdown). It **cannot create a new custom field on its own** — create the field first, then tell the agent when to save into it in [Instructions](/workspace/ai-agents/tabs/instructions), for example: *"If the customer mentions their company name, save it to the matching custom field."* ### Trigger Automation This is the capability people find least obvious, so here's exactly how it works. The moment you enable **Trigger Automation**, the agent is handed a live, always-current list of this channel's active automations — each with its own name and **Description** — every time a customer messages. This happens automatically. It has **nothing to do with what you wrote in Instructions.** The agent compares the customer's message against each automation's Description and starts whichever one fits. If nothing matches clearly, it's told not to guess — it simply doesn't call anything. Write each automation's Description like a one-sentence instruction to a new employee — "Use this when the customer asks for a demo" — not just a name. A vague or blank description is the most common reason an agent never uses an automation you expected it to. ### What happens once a triggered automation is running Control passes to the automation completely. If it includes an [Ask](/workspace/automation/steps/ask-questions) step — collecting an email, a concern, anything — the agent steps entirely aside and isn't consulted again until that automation reaches an end (**Submitted** or **Not Submitted**). Every reply the customer sends in that window goes to the automation, not the agent. This is deliberate: it's what keeps a structured flow — say, collecting a name, email, and issue before raising a support ticket — from being interrupted halfway through. The trade-off is that the automation won't recognize an unrelated question while it's mid-flow; it treats whatever the customer sends next as the answer to its current question. Keep automations the agent triggers narrow and focused, and always connect the **Not Submitted** path so a customer who goes off-script isn't left stuck — see [Ask Questions](/workspace/automation/steps/ask-questions). ### Triggering a sequence Trigger Automation also works for [Sequence](/workspace/automation/steps/sequences)-type automations — the agent starting one counts as an **Assign Sequence** action, including the same protection against enrolling a contact who's already in that sequence twice. ## Troubleshooting / Technical Notes * **The agent isn't using an automation I expected.** Check that automation is **Active**, bound to this agent, and has a specific, clear Description — not the agent's Instructions. * **It asked something unrelated to what I just said, mid-conversation.** A triggered automation with an Ask step is running and has taken over — see "What happens once a triggered automation is running" above. * **No capabilities are listed, or the tab looks locked.** Save the agent on the [General](/workspace/ai-agents/tabs/general) tab first, then reopen it. ## Related docs * [External Capabilities](/workspace/ai-agents/tabs/external-capabilities) * [Custom Fields](/workspace/contacts/custom-fields) * [Ask Questions](/workspace/automation/steps/ask-questions) * [Sequences](/workspace/automation/steps/sequences) * [Automation Overview](/workspace/automation/overview)