Configure
Personas & tone
A persona is a self-contained configuration that controls tone, goals, tool access, and routing for a specific part of your site. Most customers run one general-purpose persona; teams with complex funnels often run three or four.
What a persona owns
- Name and color for identifying it in the dashboard.
- Role description — a short paragraph that sets the agent's identity (e.g. “Enterprise SDR for B2B SaaS”).
- Tone — friendly, formal, playful, concise, detailed, etc.
- Primary goal — book a meeting, qualify, deflect support, answer pricing, etc.
- Welcome message and proactive greeting overrides.
- BANT profile — what counts as qualified for this persona (see BANT).
- Allowed tools — which integrations this persona can use.
- URL patterns — which pages this persona answers on.
- Social channels — on the Channels tab, claim a connected Facebook Page, Instagram account, or WhatsApp number so this persona answers that channel's DMs and comments (see Assign a persona to each channel).
Create a persona
- Open Personas in the dashboard sidebar.
- Click + New Persona.
- Pick a template: Sales SDR, Support, Pricing Specialist, E-commerce Concierge, Demo Booker, or Blank.
- Fill in the name, description, tone, and goal. A live preview on the right shows the agent's first reply.
- Click Save.
URL routing
Each persona can own one or more URL patterns. When the widget loads, it picks the persona whose pattern matches the current page. If none match, the default persona answers.
| Pattern | Matches |
|---|---|
/pricing | Any URL path containing /pricing. |
/docs/* | Any path starting with /docs/. |
example.com/blog | The blog on a specific subdomain. |
/product/{handle} | Shopify product pages with dynamic handles. |
You can also hard-pin a persona from the embed snippet (see Shopify install or the deploy page).
Tone & role tips
The agent is highly responsive to how you describe its role. Specific beats generic.
| Less effective | More effective |
|---|---|
| You are a helpful assistant. | You are a senior SDR at Acme. You speak like a confident peer, not a salesperson. Your job is to qualify for budget, timeline, and team size, then book a 20-minute demo. |
| Be friendly. | Warm, low-pressure, and never use buzzwords like “synergy” or “leverage.” Mirror the prospect's formality. |
Workflows
A persona's System prompt defines who it is. Its Workflows define how it handles specific situations — the step-by-step process you'd give a new rep, written in plain English. Each workflow is tied to a trigger (an event), so it only runs when—and where—it should.
Open the Workflows section on a persona and click Add a trigger. For each workflow you pick the event that fires it and write the steps:
| Trigger | Runs on |
|---|---|
| New chat conversation | Web chat |
| New lead captured | Web chat, once a lead’s details are known |
| New social comment | Facebook / Instagram comment replies |
| New direct message | WhatsApp, Messenger, Instagram DMs |
| New email received | Inbound email auto-replies |
| Follow-up email after a chat | The recap email sent when a chat ends |
| Any / always | Every channel |
| Custom… | A trigger you describe in plain English, on a channel you pick |
A workflow only enters the prompt for its trigger's channel — so a social-comment workflow never clutters a web-chat reply. Write the steps as a numbered list and reference your connected tools by name. For example, on New lead captured:
1. Look the company up on Apollo and note their HQ.
2. If they look like a strong fit, offer to book a meeting.
3. Use the rep for that region — send their Calendly link or check
Google/Outlook availability and book it.
4. Update the CRM with everything you learned.
Each persona has a tool palette listing exactly which tools it can use (from your connected integrations). A workflow step that names a tool you haven't connected simply won't run, so the palette is the quickest way to see what's available — and to restrict a persona to a specific subset.
Few workflows? The section stays collapsed and just shows how many are active. Expand it to add, edit, enable, or remove them.
Workflows are guidance the AI follows, not a rigid script: they steer the agent reliably but a multi-step chain depends on the named tools being connected. Identity and tone still belong in the System prompt; situational process belongs here.
Review & refine
Not sure your workflow is clear enough? Click Review & refine under the Workflows box. The AI checks it for clarity, missing steps, and vague conditions, suggests improvements, and — because it knows which tools this persona has connected — flags any step that names a tool you haven't set up (and suggests one you have). It also flags steps whose tool isn't available on the channel — for example a “send an email” step won't run on a voice call (use Post-conversation actions for that). It proposes a cleaned-up version you can accept with Use this or ignore; nothing is changed unless you choose to apply it.
Post-conversation actions
When a conversation ends — a chat that goes idle, or a phone call that hangs up — Quincer can send a summary to your team. Set this per persona under Channels → Post-conversation actions. No workflow needed; it works out of the box.
The summary can go to any combination of:
- Slack — posted to your Slack history channel. On by default once Slack is connected.
- Teams — posted to the persona's Teams channel. On by default once Teams is connected.
- Email — sent to the recipient address(es) you enter (comma-separated). Leave the field blank to send to your team members instead. The email goes out from your connected Gmail/Microsoft mailbox if you have one, otherwise from Quincer, and includes a View conversation button.
Each summary includes the visitor/lead details, message count, topics, and a link to the full conversation. It also adds, when available:
- Caller ID and date/time for phone calls.
- Sentiment — when conversation sentiment is enabled for the widget.
- CSAT — the post-chat survey rating, when surveys are enabled and the visitor responded.
This is the right way to “email me the call details.” A persona workflow step that says “send an email” will not run on a phone call — email tools aren't available during voice calls — so use Post-conversation actions for end-of-call summaries.
Guardrails
Every persona has a Boundaries field where you can list things the agent must never do. Typical entries: don't promise pricing, don't make roadmap commitments, always escalate HIPAA or legal questions.
Boundaries are always enforced in the system prompt, even when a tool output suggests otherwise. If a visitor asks about something on the boundary list, the agent defers to a human via live chat.
Plan limits
| Plan | Personas |
|---|---|
| Free | 1 |
| Starter | 3 |
| Growth | 10 |
| Scale | Unlimited |