AI agents are pre-configured to help you with your sales process. You can configure every aspect of them to fit your needs. Here is a quick guide on what you can configure.
Agent Settings
The Agent Settings tab contains the core configuration for your AI agent:
Agent Name
The display name for your agent that appears throughout the interface. Choose a descriptive name that reflects the agent's purpose, such as "Account AI agent" or "Deal AI agent".
Description
A brief description of what this agent does. This helps team members understand the agent's role and capabilities. For example: "Helps CSMs, AMs, AEs manage account health, growth potential and unlock strategic opportunities".
System Prompt
The system prompt is the most critical configuration - it defines your agent's behavior, personality, and capabilities. This is where you specify:
- Role and Introduction: Define what the agent is and its primary purpose
- Core Responsibilities: List the specific tasks the agent should handle
- Communication Style: Set the tone and approach for interactions
- Guidelines: Establish rules and best practices for the agent to follow
Example system prompt structure:
<introduction>
You are an Account AI Agent, a specialized sales assistant focused on account-level strategy and relationship management.
</introduction><core_responsibilities>
- Analyze account health, growth potential, and strategic opportunities
- Provide insights on account expansion, renewal, and upselling strategies
- Identify key stakeholders and decision-makers within the account
</core_responsibilities><communication_style>
- Be strategic and business-focused in your recommendations
- Provide data-driven insights with clear rationale
- Use professional language appropriate for C-level discussions
</communication_style>
Knowledge
The Knowledge tab allows you to provide your agent with context-specific information to enhance its responses. You can add four types of knowledge:
Products
Add product information to help your agent understand your offerings. This enables the agent to:
- Recommend relevant products during conversations
- Provide accurate product details and specifications
- Suggest cross-sell and upsell opportunities
ICPs (Ideal Customer Profiles)
Include your ideal customer profiles so the agent can:
- Better qualify leads and prospects
- Tailor messaging to specific customer segments
- Identify expansion opportunities within existing accounts
Case Studies
Add customer success stories and case studies to help the agent:
- Reference relevant examples during sales conversations
- Build credibility with prospects
- Address common objections with proven results
Playbooks
Include sales playbooks and processes so the agent can:
- Follow your established sales methodology
- Provide consistent guidance across team members
- Suggest next steps based on your proven processes
Tools
Tools extend your agent's capabilities by allowing it to perform specific actions and access data. The Tools tab shows you which tools are available and lets you add or remove them.
Individual Tools
These are standalone tools that provide specific functionality, such as:
- listAccountOpportunities: Retrieve opportunities associated with an account
- listAccountContacts: Get contact information for account stakeholders
- draftEmailToSend: Create email drafts for outreach
- researchCompanyByDomain: Research company information using their domain
Tool Groups
Some tools are organized into groups that provide related functionality. When you add a tool group, all tools in that group are added to your agent. This is useful for:
- Quickly adding comprehensive functionality
- Ensuring related tools work together
- Maintaining consistency across similar agents
Integration Tools
Tools can also be provided by integrations (like HubSpot, Salesforce, etc.), allowing your agent to interact with external systems and data sources.
MCPs (Model Context Protocol)
MCPs provide advanced capabilities and integrations for your agents. The MCP tab allows you to add specialized protocols that extend your agent's functionality beyond basic tools.
Examples of MCP capabilities include:
- Browser MCP: Allows agents to browse websites and extract information
- Database MCPs: Enable direct database queries and data manipulation
- API MCPs: Provide access to external APIs and services
MCPs are more powerful than regular tools as they can maintain state and provide complex, multi-step functionality.
Background vs Foreground Agents
Bigmind supports two modes of agent operation, and you can configure both for the same agent using the toggle switch:
Foreground Agents
These are the agents users directly interact with in chat conversations. They:
- Respond to user questions and requests
- Provide recommendations and insights
- Help with day-to-day sales activities
- Use the main system prompt, tools, and knowledge you configure
Background Agents
These agents work automatically behind the scenes to:
- Monitor activities and events (like meeting completions)
- Suggest CRM updates based on new information
- Track warnings and risks
- Update deal summaries and frameworks
Background agents have their own separate configuration (internal system prompt, internal tools, internal MCPs, and internal knowledge) that's optimized for automated processing rather than conversation.
Example Background Agent Workflow
When a meeting ends, a background agent might:
- Analyze the meeting summary
- Identify key information that should update the CRM
- Suggest field updates to keep data current
- Flag any risks or opportunities discovered
Testing Your Agent
The right side of the configuration interface provides a testing environment where you can:
- Select a specific CRM object (Account, Contact, Deal, Lead) to test against
- Have conversations with your agent using real data
- Verify that tools and knowledge are working correctly
- Refine the system prompt based on actual performance
This testing capability ensures your agent works as expected before deploying it to your team.