Agents Overview

Agents are the heart of Solo. They're AI-powered teammates that understand context, communicate on your behalf, and handle routine work automatically.

What Agents Do

Agents can:

  • Read and understand emails, tasks, and conversations
  • Communicate across channels (email, Slack, SMS)
  • Make decisions based on context and your rules
  • Take action like sending emails, creating tasks, scheduling meetings
  • Collaborate with other agents and your team
  • Learn from your feedback and improve over time

Agent Capabilities

Context Understanding

Agents understand:

  • Email content: What the message is about
  • Sender relationships: Who is contacting you
  • Conversation history: Previous interactions
  • Task context: What needs to be done
  • Business rules: Your policies and preferences

Communication

Agents can:

  • Send emails on your behalf
  • Draft replies for your review
  • Create tasks from actionable items
  • Route messages to appropriate recipients
  • Coordinate with team members

Decision Making

Agents decide:

  • What to do: Reply, create task, escalate, delegate
  • How to respond: Tone, content, urgency
  • When to ask: Escalate to you for approval
  • Who to involve: Route to other agents or team

Action Taking

Agents can:

  • Send emails with proper tone and content
  • Create and manage tasks
  • Schedule meetings and manage calendar
  • Generate content like reports or summaries
  • Update records and track status

Agent Types

Solo includes several agent types:

Inbox Manager

Purpose: Manages your email inbox

Default Behavior:

  • Automatically created when you claim your Solo Identity
  • Active by default — handles all inbound email communications automatically
  • Can be disabled or deleted in the Team area if you don't want automatic inbox management

Capabilities:

  • Reads and categorizes emails
  • Drafts replies for your review
  • Creates tasks from actionable emails
  • Routes messages appropriately
  • Handles all inbound email communications actively (when enabled)

Assistant

Purpose: General help and task management

  • Handles routine questions
  • Manages your task list
  • Provides information and answers
  • Coordinates with other agents

Chief of Staff

Purpose: High-level coordination

  • Manages priorities and deadlines
  • Coordinates between agents
  • Handles strategic decisions
  • Provides executive support

Custom Agents

Create agents for specific purposes:

  • Billing Coordinator
  • Customer Success
  • Marketing Coordinator
  • Project Manager
  • And more...

See Agent Types for complete details.

How Agents Work

Verified Sender Recognition

Agents use verified sender technology (DKIM, SPF, and other email authentication methods) to know when you're interacting with them. This allows agents to recognize legitimate communications from you.

Decision Making

Agents are smart enough to:

  • Understand context: Analyze emails, tasks, and conversations
  • Assess alignment: Determine if actions align with your identity
  • Make decisions: Take action, escalate to HITL, or ignore inbound communications
  • Stay fault tolerant: Handle errors gracefully without impacting limits
  • Respect rate limits: Constrained to prevent adverse impact on token usage or execution limits

Action Taking

Agents decide when to act:

  • Take action when appropriate and aligned with your identity
  • Escalate to HITL when uncertain, risky, or misaligned
  • Ignore inbound when not relevant or appropriate

Important: Agents never take risky actions without explicit approval via the HITL process.

How Agents Work Together

Agents can collaborate:

  • Delegation: One agent delegates to another
  • Coordination: Agents coordinate on complex tasks
  • Specialists: Agents invoke specialists for specific tasks
  • Teamwork: Multiple agents handle different aspects

Human-in-the-Loop

Agents always keep you in control:

  • Never take risky actions without explicit approval
  • Escalate when uncertain, when confidence is low, or when actions don't align with your identity
  • Request approval for important actions
  • Hold drafts for your review before sending
  • Notify you of significant events or decisions
  • Alert you when actions may not be appropriate

Agents use verified sender technology (DKIM, etc.) to know when you're interacting with them, but they always require explicit approval for risky actions. You configure when and how agents involve you. See Human-in-the-Loop for details.

Visibility & Control

You have complete visibility and control:

  • All inbound and outbound exchanges are visible via your SoloMail address
  • Configure agents to act differently based on your preferences
  • Set rules for how agents handle specific inbound emails or requests
  • Monitor activity to ensure agents are working as expected

If you don't want something handled by agents:

  • Use a different email address for that communication
  • Configure agents to ignore or handle specific inbound emails differently
  • Set up rules in agent configuration to control behavior

Agent Configuration

Each agent can be configured in 10 areas:

  1. Basics: Name, kind, status, avatar
  2. Persona & Tone: Tone, traits, signature, style
  3. Working Patterns: Timezone, hours, SLAs
  4. Human-in-the-Loop: Confidence, triggers, approval mode
  5. Context & Knowledge: Datasets, retrieval settings
  6. Specialists: Intent-aware helpers
  7. Policies & Guardrails: Rules agents must follow
  8. Tools & Integrations: Email, calendar, storage, HTTP
  9. Model & Execution: AI model, parameters, budget
  10. Ops & Telemetry: Logging, alerts, shadow mode

See Configuring Agents for complete details.

Agent Lifecycle

Creation

  1. Choose agent type
  2. Set basic information
  3. Configure settings
  4. Activate agent

Operation

  1. Agent receives context
  2. Agent analyzes and decides
  3. Agent takes action or escalates
  4. You review and provide feedback

Improvement

  1. Review agent actions
  2. Provide feedback
  3. Adjust configuration
  4. Agent learns and improves

Agent Limits

Agents are subject to plan limits:

  • Token Usage: AI tokens consumed per month
  • Executions: Number of agent runs per month
  • Storage: File attachments and data storage
  • Agents: Number of active agents (plan-dependent)

View your usage in Settings → Workflow.

Best Practices

Start Simple

  • Begin with default settings
  • Let agents learn from interactions
  • Adjust configuration gradually

Set Clear Boundaries

  • Use HITL settings to control autonomy
  • Define escalation rules
  • Set approval requirements

Monitor and Refine

  • Review agent actions regularly
  • Provide feedback
  • Refine configuration based on results

Use Multiple Agents

  • Different agents for different purposes
  • Specialized agents for specific tasks
  • Agents that work together as a team

Next Steps

Version: 1.0
Last Updated: November 2025