Skip to main content

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.

ModeHow It WorksBest For
SequentialAgents 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.
ParallelAll 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.
HybridSome 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.

ModeDescriptionHuman Involvement
ManualEvery action requires human approvalMaximum control, slowest
Plan FirstTeam creates a plan, waits for approval, then executesBalance of control and speed
SupervisedTeam executes but flags important decisionsLight oversight, faster
AutomaticTeam executes autonomously, humans notified of outcomesMinimal involvement, fastest

When to Use Each Mode

ModeGood For
ManualTesting new agents or workflows. High-stakes tasks. Regulatory human-in-the-loop requirements.
Plan FirstComplex tasks where you want to review strategy. Building trust with a new team. Understanding agent reasoning before execution.
SupervisedTeams that have proven reliable. Tasks with occasional edge cases. You want to be informed without blocking execution.
AutomaticTeams with high success rate. Routine, well-defined tasks. Speed-critical operations.

Agent Autonomy Level

Defines how proactively agents can act within the team.

LevelBehaviorTrust RequiredSpeed
ReactiveAgents only act when given explicit tasks. They wait for instructions.LowSlow
ProactiveAgents suggest actions and identify opportunities, but ask before acting.MediumMedium
AutonomousAgents identify and execute tasks on their own within their defined scope.HighFast

A2A Visibility

Controls how much of agent-to-agent communication users can see.

LevelWhat Users SeeUse When
HiddenOnly final outcomesRoutine and trusted tasks. Simplicity matters more than transparency.
SummaryBrief summaries of agent conversationsYou want oversight without information overload.
FullComplete transcripts of all agent messagesBuilding trust. Debugging. Regulatory full-audit requirements. Training agents.

Play/Pause (Safety Control)

A safety mechanism for controlling team activity.

StateDescription
RunningTeam is active, processing tasks, agents communicating
PausedAll activity frozen, tasks queued but not processed
StoppedTeam 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
info

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:

SourceExample Events
CRMNew leads, deal stage changes, tickets
CommunicationSlack mentions, messages
DevelopmentPull requests, issues, deployments

Only events from connected integrations can be enabled.

Scheduled Tasks

Configure recurring tasks that run automatically:

ScheduleExample
Morning Pipeline ReviewWeekdays at 9:00 AM
Weekly ForecastMondays at 10:00 AM
SLA Compliance CheckEvery 2 hours
Daily CSAT ReviewWeekdays 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.

Conservative (High Control)

SettingValue
CollaborationSequential
ExecutionPlan First
AutonomyReactive
A2A VisibilityFull

Best for new deployments, sensitive data, regulated industries.

Balanced

SettingValue
CollaborationHybrid
ExecutionSupervised
AutonomyProactive
A2A VisibilitySummary

Best for established teams, moderate-risk tasks.

High Autonomy

SettingValue
CollaborationParallel
ExecutionAutomatic
AutonomyAutonomous
A2A VisibilityHidden

Best for proven teams, routine tasks, high-volume operations.

How to Change Settings

Dashboard

  1. Go to Teams
  2. Click Edit on your team
  3. Navigate to the Team Behavior tab
  4. 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"
info

Changing settings while a team is running applies to new tasks only. Existing tasks continue with their original settings.


Agent-to-Agent Communication
How agents collaborate within and across teams
Composing Teams
Design effective multi-agent teams
Process Orchestration
Enterprise deployment workflows