Skip to main content

AI Config

AI Config is where you set the agent’s name, workspace, model, tone, and creativity for automated replies. Use it after you create an agent or whenever you want to change how the AI behaves without rebuilding the whole setup.

The page title is AI Config, with the subtitle Choose your AI model and configure core parameters.

Open AI Config​

  1. Sign in to ChatMaven and open Agents from the top navigation (Profile, Agents, Workspaces, Accounts).
  2. Pick the agent from the agent dropdown at the top of the left sidebar (for example dan health).
  3. Under General, click AI Config.

The left sidebar also lists Knowledge Base, Integrations, and channel shortcuts under SPOTLIGHT (such as Web Chat and WhatsApp). Lower in the sidebar you’ll find Preferences, Live Chats, and Templates for compliance, handoff, and messaging templates.

AI Config page showing identity, model, tone, and creativity

Enable AI Response​

At the top right of the main panel, Enable AI Response turns automated AI replies on or off for this agent.

  • On: The agent can generate answers according to your model and guidelines (subject to your plan and channel rules).
  • Off: Turn this off if you want the agent to stop sending AI-generated messages—for example during maintenance or when you rely on human-only handling.

Always click Save after changing the toggle if your screen shows save actions at the bottom.

AI Config page showing identity, model, tone, and creativity

Identity​

These fields control how the agent is labeled and which workspace owns it.

FieldPurpose
Select WorkspaceDropdown: choose the workspace this agent belongs to.
Agent NameThe name shown in ChatMaven lists and dropdowns (for example your brand or channel-specific name).
Role TitleHow the agent describes its role to users (placeholder example: Customer Support Agent). Helps set expectations in conversations.

AI model​

Select AI Model is a dropdown of available models (for example GPT-3 Mini or other options your workspace provides). Pick the balance of quality, speed, and cost that fits your use case; your admin or plan may limit which models appear.

Style & tone​

Tone​

Tone uses pill buttons so only one style is active at a time. Typical options:

  • Professional
  • Friendly
  • Casual
  • Formal

The selected pill is highlighted (for example in purple). This steers how formal or relaxed the agent’s wording feels.

Creativity​

Creativity is a slider from Precise (left) to Imaginative (right), often shown as a percentage (for example 75%).

  • Lower / Precise: Stricter, more consistent phrasing—good for policies, FAQs, and compliance-sensitive replies.
  • Higher / Imaginative: More varied and flexible wording—use with clear guidelines so answers stay accurate.

AI Config page showing identity, model, tone, and creativity

Chat guidelines (if shown)​

In some flows—especially during the creating an agent wizard—you may also see Chat guidelines: rules for scope, safety, and what the agent must avoid. If your AI Config screen includes that section, use it the same way as described in Step 2: AI Config on the creating an agent page.

Save your changes​

Use Save at the bottom right to apply updates. Cancel discards unsaved edits on that screen (exact behavior matches the product).

AI Config page showing identity, model, tone, and creativity

FAQ and troubleshooting​

The agent is too verbose or too terse.​

Adjust temperature and style presets if available, and tighten the system or instructions text with examples of ideal reply length.

It ignores my knowledge base.​

Confirm sources are indexed, not expired, and that the agent has retrieval enabled. Conflicting instructions (“make things up”) override grounding—rewrite for “use only the knowledge base when possible.”

Wrong language or tone.​

Set an explicit language and tone line in instructions, and test with native prompts. Some models drift if the user writes in another language—add a rule to match the user’s language.