Agent Settings

Configure agent identity, model, caching, context memory, and more.

Tip: Your agent can update its own settings. Ask it — "Change your name to DataBot", "Set your timeout to 30 minutes", or "What are your current settings?"

Overview

The Settings drawer (gear icon in the agent header) lets you configure your agent's identity, model preferences, caching behavior, and how much conversation history the AI remembers.

Agent Identity

Name

The agent's display name — shown in the sidebar, headers, email address, and everywhere the agent is referenced. Click the edit icon next to the name in the header to change it.

The name also determines the agent's email address:

agent-name@mailer.communa.io

Info: Changing the name updates the display everywhere but the email address is set at creation and doesn't change automatically.

Description

An optional description of what the agent does. Helps team members understand the agent's purpose at a glance.

Chat Settings

Open the Settings drawer to access model, cache, and context memory options.

Default Model

Override the system default AI model for this specific agent. Useful when different agents have different cost/performance needs — a quick-task agent can use a lighter model while a research agent uses the most capable one.

Select System Default to follow the platform-wide model setting.

Cache Strategy

Control prompt caching behavior to reduce costs on repeated interactions:

StrategyDescription
No CacheEvery request is processed fresh — highest cost, best for volatile prompts
5 MinutesRecommended — caches the system prompt for 5 minutes, good balance of freshness and savings
1 HourMaximum savings — caches for 1 hour, best for agents with stable system prompts

Context Memory

Controls how much conversation history the AI sees when generating responses. Choose from three presets:

PresetText MessagesTool CallsScreenshotsBest For
Minimal20103Short tasks, quick automations, lowest cost
Balanced50305Most agents — recommended default
Extended1508010Complex multi-step workflows, long conversations
  • Text Messages — User, assistant, and system messages loaded from conversation history
  • Tool Calls — Tool call/result pairs (computer actions, web searches, file reads, etc.)
  • Screenshots — Recent screenshots kept as full images; older ones are replaced with lightweight text descriptions to save tokens

Advanced Context Settings

For fine-grained control, expand Advanced Context Settings inside the Context Memory section to customize each value individually:

SettingRangeDefaultDescription
Text Messages10 – 20050Max user + assistant messages loaded from history
Tool Interactions5 – 10030Max tool call/result pairs kept in context
Screenshots Kept1 – 205Recent screenshots kept as images; older become text placeholders

Changing any slider automatically switches the preset to Custom. Pick a preset button to reset all three values.

Tip: Start with Balanced. Only increase if your agent loses track of earlier context in long sessions. Reduce to Minimal for simple, repetitive tasks to save on token costs.

Editing Settings

Settings can be changed two ways:

Through the UI

  • Name — Click the edit icon in the agent header
  • Chat settings — Open the Settings drawer (gear icon)

Through Conversation

The agent can update its own settings using the settings_manager tool. Just tell it:

  • "Change your name to ResearchBot"
  • "Update your description to 'Handles daily email triage and reporting'"

This chat-first approach means you rarely need to navigate to settings pages — your agent is its own settings panel.

Tips & Best Practices

  • Use descriptions — A clear description helps team members understand what each agent is for
  • Let the agent self-configure — During onboarding, the agent sets its own name, persona, and settings through conversation
  • Match context to the task — Simple agents (e.g., email triage) work well with Minimal context; research or multi-step agents benefit from Extended
  • Monitor token costs — If an agent's per-message cost is higher than expected, try reducing context memory

What's Next?