Team Settings
This guide covers the behavior settings available when configuring AI teams in MeetLoyd. Every setting can be changed from the dashboard, through Loyd, or via the API.
Collaboration Mode
Determines how agents in a team work together on tasks.
| Mode | How It Works | Best For |
|---|---|---|
| Sequential | Agents work one after another in a defined order. Each completes before passing to the next. | Workflows with clear stages (lead qualification, then demo scheduling, then follow-up). Quality control checkpoints between stages. |
| Parallel | All agents work simultaneously on different aspects of a task, results are combined at the end. | Tasks that can be split into independent subtasks. Research from multiple sources. Speed-critical work. |
| Hybrid | Some agents work in parallel, then hand off to sequential stages. | Complex workflows with both independent and dependent work. Parallel research followed by sequential approval. |
Execution Mode
Controls how much autonomy the team has in executing tasks.
| Mode | Description | Human Involvement |
|---|---|---|
| Manual | Every action requires human approval | Maximum control, slowest |
| Plan First | Team creates a plan, waits for approval, then executes | Balance of control and speed |
| Supervised | Team executes but flags important decisions | Light oversight, faster |
| Automatic | Team executes autonomously, humans notified of outcomes | Minimal involvement, fastest |
When to Use Each Mode
| Mode | Good For |
|---|---|
| Manual | Testing new agents or workflows. High-stakes tasks. Regulatory human-in-the-loop requirements. |
| Plan First | Complex tasks where you want to review strategy. Building trust with a new team. Understanding agent reasoning before execution. |
| Supervised | Teams that have proven reliable. Tasks with occasional edge cases. You want to be informed without blocking execution. |
| Automatic | Teams with high success rate. Routine, well-defined tasks. Speed-critical operations. |
Agent Autonomy Level
Defines how proactively agents can act within the team.
| Level | Behavior | Trust Required | Speed |
|---|---|---|---|
| Reactive | Agents only act when given explicit tasks. They wait for instructions. | Low | Slow |
| Proactive | Agents suggest actions and identify opportunities, but ask before acting. | Medium | Medium |
| Autonomous | Agents identify and execute tasks on their own within their defined scope. | High | Fast |
A2A Visibility
Controls how much of agent-to-agent communication users can see.
| Level | What Users See | Use When |
|---|---|---|
| Hidden | Only final outcomes | Routine and trusted tasks. Simplicity matters more than transparency. |
| Summary | Brief summaries of agent conversations | You want oversight without information overload. |
| Full | Complete transcripts of all agent messages | Building trust. Debugging. Regulatory full-audit requirements. Training agents. |
Play/Pause (Safety Control)
A safety mechanism for controlling team activity.
| State | Description |
|---|---|
| Running | Team is active, processing tasks, agents communicating |
| Paused | All activity frozen, tasks queued but not processed |
| Stopped | Team is completely inactive |
When to pause:
- Stop runaway costs if agents are in an unexpected loop
- Prevent unwanted actions before agents take irreversible steps
- Freeze state to investigate issues without ongoing changes
- Scheduled maintenance windows
When paused, no data is lost. New tasks are queued (not dropped). When resumed, queued tasks process in order.
Trigger Configuration
When deploying a team, you can configure automation triggers:
Event Triggers
Enable events from connected integrations to automatically trigger agent actions:
| Source | Example Events |
|---|---|
| CRM | New leads, deal stage changes, tickets |
| Communication | Slack mentions, messages |
| Development | Pull requests, issues, deployments |
Only events from connected integrations can be enabled.
Scheduled Tasks
Configure recurring tasks that run automatically:
| Schedule | Example |
|---|---|
| Morning Pipeline Review | Weekdays at 9:00 AM |
| Weekly Forecast | Mondays at 10:00 AM |
| SLA Compliance Check | Every 2 hours |
| Daily CSAT Review | Weekdays at 9:00 AM |
Bootstrap Tasks
One-time setup tasks that run when the team is first deployed. Examples: import pipeline data, set up qualification framework, create meeting prep templates, import knowledge base, configure escalation rules. Each has a priority level (high, medium, low) and suggested due time.
Recommended Configurations
Conservative (High Control)
| Setting | Value |
|---|---|
| Collaboration | Sequential |
| Execution | Plan First |
| Autonomy | Reactive |
| A2A Visibility | Full |
Best for new deployments, sensitive data, regulated industries.
Balanced
| Setting | Value |
|---|---|
| Collaboration | Hybrid |
| Execution | Supervised |
| Autonomy | Proactive |
| A2A Visibility | Summary |
Best for established teams, moderate-risk tasks.
High Autonomy
| Setting | Value |
|---|---|
| Collaboration | Parallel |
| Execution | Automatic |
| Autonomy | Autonomous |
| A2A Visibility | Hidden |
Best for proven teams, routine tasks, high-volume operations.
How to Change Settings
Dashboard
- Go to Teams
- Click Edit on your team
- Navigate to the Team Behavior tab
- Adjust settings and save
Via Loyd
Just ask:
- "Change my sales team to automatic execution mode"
- "Make my support team more autonomous"
- "Show full A2A visibility for the DevOps team"
Changing settings while a team is running applies to new tasks only. Existing tasks continue with their original settings.