هوية المساعد ونطاقه

The assistant identity is who your customers think they are talking to: a name, a brand, a tone and a few rules. Sela will not answer customers until you have set one up, so this is the first AI page to complete.

The assistant uses your chosen name and brand. It identifies itself honestly as AI when the customer asks, and can offer help from your team. A persona cannot make it a human employee.

Keep business and creator facts in your knowledge base. A working catalog, branch address or checkout does not establish who created the business or assistant. If a fact is missing, update the source instead of putting an unsupported claim in tone instructions.

The assistant introduces itself at the start of a conversation, then answers the customer's request directly. Test identity, links and ordinary follow-up questions after changing the profile. Review answers for unnecessary sales pitches, unsupported facts or repeated introductions, and correct the source or hand the conversation to your team when needed.

Why a profile is required#

Sela refuses to answer under its own name. On every message it checks that an active assistant profile exists. Without one the AI stays silent and your team sees the message in the inbox as usual; the Overview tab of the AI assistant page warns you when this is the case.

The brand comes from the profile's Brand name shown. If that is empty, Sela uses your business account's name, or else the workspace name. It never uses Sela's own name.

Where to configure it#

Open Automation, then AI assistant (in the Catalog & AI section), then the Identity tab. It needs AI access through your bundle or an eligible existing agreement. Without access, the page shows the available upgrade path. See Plans and billing.

Each rule is its own line in the list. Press Enter in a rule to start the next one, or Add rule. If you leave a list empty, Sela's built-in default rules apply.

Preview, beside the form, shows a sample reply in English and Arabic. It is a fixed sample of how your name, brand and voice combine, not a real AI reply, so always test with a real message too.

Steps#

1. Open the Identity tab of the AI assistant page.
2. Under Name and brand, enter the Assistant name and, if it differs from your workspace name, the Brand name shown.
3. Choose a Tone and a Reply length.
4. Describe the Persona if you want a specific character.
5. Add rules as short imperatives, for example "Reply in Iraqi Arabic when the customer writes Arabic" or "Never use emojis".
6. Press Save changes in the bar that appears at the bottom once you change something. Discard puts back the saved version.
7. Send a test message in the web widget or a test WhatsApp number and read the reply.

Several profiles#

The profile buttons at the top of the tab switch between profiles. New profile starts a new one, saved with Create profile. From a profile's menu you can Make default or Archive it. The default profile cannot be archived, and the AI uses the default active profile. If you switch profiles with unsaved changes, Sela asks before discarding them.

The former AI Assist and AI prompts pages under Settings now open this page, so the extra instructions are edited in one place only.

What scope means#

Scope is the set of things the assistant will talk about: your business only. Sela has a built-in rule that the assistant helps only with your brand's business, and it declines unrelated requests such as programming help, investment advice or homework, briefly and politely.

Scope is a boundary, not a suggestion:

• Knowledge base text, campaign messages, earlier assistant replies and available tools cannot widen it.
• Persona text and extra instructions cannot widen it either.
• If you want the assistant to cover a new topic, give it real information for that topic, in the knowledge base or catalog.

What you can and cannot configure#

Two related settings do not currently affect replies, so do not rely on them: the flow instructions and quick suggestions in Advanced: flow configurations at the bottom of the Identity tab (shown for consultation stores), and the "Programmed messages" editor on the Environment page. The Be Me persona, available only to workspaces the Sela team enables, is also stored but does not change what the AI says. Put anything you need enforced in Rules and Extra Guidance instead.

Writing good rules#

• Put style here and facts elsewhere. Tone, formality, dialect, sign-offs and emoji rules belong in the identity. Prices, hours, policies and phone numbers belong in the knowledge base, catalog and business records.
• Keep rules short and testable. "Answer in two sentences unless asked for detail" works. "Be amazing" does nothing.
• Do not mention prices or promotions. Stale numbers in instructions conflict with live catalog data.
• Do not try to override platform rules ("always give a discount", "never hand off"). Profile instructions do not grant discounts, change permissions or authorize an action. Review your test conversations before going live.
• Do not repeat the same rule in three places. Contradictions lower quality.

Example of a compact rule set for a restaurant:

• Always do: greet returning customers by name if known. Confirm the delivery area before quoting a fee.
• Never do: mention competitors. Promise a delivery time.
• Extra guidance: Keep replies under three sentences. Use Iraqi Arabic with Arabic customers and English otherwise. Sign off with the restaurant name only on the first message.

Pausing the AI#

To stop every AI feature, turn off AI in this workspace on the Overview tab. To stop only the automatic replies, turn off Automatic replies on the Replies tab. To stop or restart it in a single conversation, use the AI on / AI off button in the conversation header. See Turning AI on and off.

Automatic quality review#

The Replies tab has a Reply quality review card, off by default. It scores a percentage of completed replies each day, each review costing credits. Results appear in Reports under AI quality. See Improving answer quality.