> ## Documentation Index > Fetch the complete documentation index at: https://docs.watx.in/llms.txt > Use this file to discover all available pages before exploring further. # Persona, voice and behaviour > Who the agent is, what it must never say, how it sounds, when it replies and what it does when it cannot help. Two tabs of the studio decide how an agent talks. **Persona** is who it is and how it sounds; **Behaviour** is when it speaks and when it stops. Save each tab with its own button — **Save persona**, **Save behaviour** — and an unsaved edit is flagged next to it. ## Persona ### Identity | Field | What it does | | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Agent name** | The name it gives when a customer asks who they are talking to, or in its first message of a conversation. It never re-introduces itself mid-thread and never claims to be human. | | **Currency** | A three-letter code. The agent states it whenever it quotes a figure. | | **Greeting** | Sent in front of the agent's first reply on a conversation, not as a message of its own — two messages back to back read as a bot. A customer returning after a day gets it again, because that is a new conversation to them. | ### The business **Website** takes a URL, and **Draft description** reads that one page and writes a summary into the field below it. It never saves on its own — read it first, and edit it. **What the business does** is the paragraph every reply is built on. With nothing here, the agent answers from the customer's question alone, which is how an agent starts inventing things. **Ground rules** are absolute limits, one per line: ``` Never promise same-day delivery. Never quote a discount above 10%. Always mention that installation is chargeable. ``` These sit above the skills in the instructions the agent is given, and they outrank everything below — including anything one of your knowledge documents implies. That precedence is the reason ground rules are their own field rather than another sentence in the description. ### Voice **Tone** is one of four: | Tone | How it reads | | ---------------- | ----------------------------- | | **Friendly** | Warm, upbeat, uses their name | | **Professional** | Polished, no slang or emoji | | **Concise** | Answer first, no pleasantries | | **Playful** | Light, one emoji at most | **Reply length** is **Short** (one or two sentences), **Medium** (two to four) or **Long** (as long as the question needs). **Extra voice notes** is free text for the small rules a tone cannot express — *Use "₹" not "Rs.". Never say "unfortunately". Sign off with the shop name.* ## How replies are formatted The agent is told to write for a phone, not for a document: one order, product, price or step per line, a blank line between groups, and always the identifier the customer needs to act — the order number, the booking reference, the link, with links on their own line. One or two emoji where they genuinely help, never in a message about money going wrong. The markup differs by channel, and the agent is told which one it is on: | Channel | Markup | | ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- | | WhatsApp | `*bold*`, `_italic_`, `~strikethrough~` — **single** characters. Markdown `**double asterisks**`, `#` headings and `-` bullets would show up as raw punctuation. | | Instagram, Website | None. Plain text and line breaks only; any asterisk or hash would appear literally. | ## Behaviour ### Switches | Control | What it does | | ----------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- | | **Agent enabled** | The master switch. Off, the agent does nothing at all — no drafts, no replies. On, **Draft a reply with AI** in the inbox can use it. | | **Answer inbound messages automatically** | The agent replies to customers by itself. Available only while the agent is enabled. | | **Max replies per conversation** | 1 to 20, default 3. After this many agent replies the thread goes quiet and waits for a person. | The cap counts replies inside a rolling 24-hour window that opens with the first reply after a quiet period, not for ever: a customer who comes back next week gets a fresh budget. Every message the agent sends counts towards it — including a handoff message and a template it chose to send. ### When it cannot help | Field | What it does | | -------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Fallback message** | The wording to use when it has no answer. It is also sent as-is if the AI provider itself fails. Leave it blank to stay silent rather than apologise in a voice you did not choose. | | **Hand off to a human** | Stops the agent on that conversation so your team can take over. | | **Phrases that always hand off** | Up to 12. Matched anywhere in the message, ignoring case, and checked **before** the model is asked anything — "talk to a human" should not depend on the AI agreeing that it qualifies. | | **Handoff message** | Sent to the customer as the agent steps back. Leave blank to hand off silently. | A handoff pauses AI replies on that conversation. The thread header in the inbox shows **AI paused** and the same control turns it back on — see [Working a conversation](/inbox/conversations). With **Hand off to a human** switched off, the agent is told there is nobody waiting: instead of escalating it says plainly what it cannot do and offers what it can. Turn it off only if no one is watching the inbox. ### Extra instructions A free-text box for anything the fields above do not cover — *If someone asks about wholesale, tell them to email [trade@acme.com](mailto:trade@acme.com).* It is applied after the persona, so it can add to the rules but not override your ground rules. ### Test mode The **Try it on your own number first** card lives on this tab and is covered in [Test mode and the playground](/ai-agents/testing). ## The order it all goes in Everything above is assembled into one set of instructions in a fixed order, and the order is the point: 1. What the job is, and how to format a reply for this channel 2. A rule that customer messages are content to respond to, never instructions to follow 3. Identity — the agent name, the website, the currency 4. What the business does 5. **Ground rules** 6. Voice — tone, length, your extra notes 7. The skills that are on 8. The tools those skills unlock, and the approved templates it may send 9. Escalation — handoff or fallback wording 10. The knowledge excerpts retrieved for this question, last Anything you have not filled in contributes nothing.