Behavior
This tutorial walks you through configuring the Behavior section for the Brew agent — a customer support assistant for Brew & Chat Cafe. The three fields you will set here (Mission, Personality, and Interaction) are injected directly into the AI's context and have the greatest influence on the quality and tone of every response.
Scenario Used in This Tutorial
| Field | Value |
|---|---|
| Agent | Brew (Brew & Chat Cafe customer support) |
| Mission | Streamline customer interactions — reservations, menu, and allergen info |
| Personality | Warm but efficient, empathetic, professional |
| Interaction | Balanced responses, proactive suggestions, clear error handling |
Two Ways to Fill In the Fields
Before you start writing, know that each field in the Behavior section can be filled in two ways:
- Type directly — Write your own text in the field. This gives you full control over wording and detail.
- Let AI help — Type a rough idea (or use the existing placeholder), then click the ✦ Modify button below the field. The AI rewrites the content to be clearer and better aligned with best practices.
Tip: A practical approach is to write a short rough draft first, then click Modify to have the AI refine it. Review the result and adjust further if needed.
Step 1 — Open Persona → Behavior
Click the hamburger menu (☰) in the top-left corner to open the sidebar. Expand the Persona section, then click Behavior.
The Agent Behavior page will load, showing three editable fields: Mission, Personality, and Interaction.
Step 2 — Write the Mission
The Mission field defines what the agent is here to do. It sets the goal and scope for every conversation.
- Click inside the Mission text area to edit it.
- Replace or update the existing text with a clear, specific purpose statement.
Scenario value for Brew:
Brew's primary purpose is to streamline customer interactions for Brew & Chat Cafe by managing reservations and waitlists and providing accurate, up-to-date menu and allergen information. It serves cafe patrons — walk-ins, regulars, and guests planning visits — as well as staff who need a reliable front-line assistant to reduce workload and improve throughput.
Tips for writing an effective mission:
- State the subject area or domain (cafe, hospital, software, etc.)
- Describe the type of help the agent provides (reservations, FAQ, troubleshooting)
- Mention constraints where relevant (e.g., "only use information from the company knowledge base")
Step 3 — Define the Personality
The Personality field specifies the agent's character traits. These traits guide tone, word choice, and level of formality in every response.
- Click inside the Personality text area.
- List the traits that match the intended audience and use case.
Scenario value for Brew:
Warm but efficient: friendly, approachable, and polite while remaining concise and businesslike when needed. Brew communicates with empathy (especially around allergies and special requests), patience with users who need more guidance, and quiet confidence that instills trust.
Common trait combinations to consider:
| Style | Example traits |
|---|---|
| Professional | Formal, concise, objective, jargon-aware |
| Friendly | Warm, approachable, conversational, uses light humour |
| Empathetic | Patient, supportive, validates feelings before answering |
| Expert | Authoritative, detailed, cites sources, no oversimplification |
Step 4 — Describe the Interaction Style
The Interaction field explains how the agent communicates — its approach and methods for helping users. This is different from personality: it describes behavior patterns, not character traits.
- Scroll down to the Interaction field.
- Describe how the agent structures responses, handles ambiguity, and manages edge cases.
Scenario value for Brew:
Responses should be balanced: concise for straightforward requests (e.g., confirming a reservation) and more comprehensive when customers ask for details (e.g., menu ingredients, allergy cross-contact information). Brew is primarily reactive but proactive where it helps the user: offering suggestions (alternative menu items, quieter seating times, waitlist opt-in), gentle reminders (upcoming reservations), and prompts to complete necessary details (party size, date/time, allergy specifics). When Brew does not know an answer or cannot guarantee allergen safety, it should state that transparently and propose contacting a human staff member.
Things to specify in Interaction:
- Whether the agent asks clarifying questions before answering
- How it structures long answers (numbered steps, headers, bullets)
- How it handles off-topic or sensitive questions
- Whether it proactively suggests next steps or waits to be asked
Step 5 — Save Changes
Once all three fields are filled, click the Save button at the bottom-right of the page. A confirmation will appear briefly to indicate the settings have been saved successfully.
What Happens After Saving
The updated Mission, Personality, and Interaction values are injected into the agent's system context the next time a conversation is started. Existing active conversations are not affected until they begin a new session.
To verify the changes, open the live preview panel on the right side of any config page and start a new conversation. Ask a question that would test the new personality or mission scope.
Related Pages
- Persona overview — all six Persona sub-sections
- Profile — agent name, logo, and avatars
- Introduction — welcome message and example questions
- Advanced — conversation memory and AI model selection