Agent Configuration

This guide covers the settings available when configuring Agents and Characters on TeamDay.

Configuration Overview

Agent Fields

Agents are lightweight. These are the configurable fields:

Field	Required	Description
`name`	Yes	Display name
`systemPrompt`	Yes	System prompt — the core instructions
`role`	No	Role description (default: "Assistant")
`model`	No	AI model ID (default: `claude-sonnet-4-6`)
`visibility`	No	`private`, `organization`, `public`, `unlisted` (default: `organization`)
`advanced_tools`	No	List of MCP tool IDs to enable
`tags`	No	Tags for organization and filtering

Character Fields

Characters include everything Agents have, plus:

Field	Required	Description
`category`	Yes	`marketing`, `finance`, `hr`, `engineering`, `operations`, `general`, `data`
`system_message`	Yes	System prompt (named differently from Agent's `systemPrompt`)
`skillIds`	No	Skills to install (e.g., `["core:research-assistant"]`)
`allowedTools`	No	Explicit tool allowlist (default: `Read, Write, Edit, Bash, Glob, Grep`)
`slug`	No	URL slug for public marketing page
`characterDescription`	No	Short description (up to 500 chars)
`initialGreeting`	No	First message when a user starts a chat
`image`	No	Avatar image URL
`longDescription`	No	Extended description for marketing page
`useCases`	No	List of use case descriptions
`faq`	No	FAQ items (`[{question, answer}]`)
`integrations`	No	List of integration names
`seo`	No	SEO metadata (`{title, description, keywords}`)

Models

Available Models

TeamDay supports models from multiple providers:

Claude (Anthropic):

Model ID	Name	Description	Pricing (per 1M tokens)
`claude-sonnet-4-6`	Claude Sonnet 4.6	Best value — fast, smart, great for coding	$3 in / $15 out
`claude-opus-4-6`	Claude Opus 4.6	Most capable — complex reasoning	$5 in / $25 out
`claude-haiku-4-5-20251001`	Claude Haiku 4.5	Fastest — simple tasks	$1 in / $5 out

Gemini (Google):

Model ID	Name	Pricing (per 1M tokens)
`gemini-3-pro-preview`	Gemini 3 Pro (Preview) (coming soon)	$2 in / $12 out
`gemini-3-flash-preview`	Gemini 3 Flash (Preview) (coming soon)	$0.50 in / $3 out
`gemini-2.5-pro`	Gemini 2.5 Pro	$1.25 in / $10 out
`gemini-2.5-flash`	Gemini 2.5 Flash	$0.30 in / $2.50 out

OpenAI:

Model ID	Name	Pricing (per 1M tokens)
`gpt-5.3-codex-2026-02-05`	GPT-5.3 Codex (coming soon)	$1.75 in / $14 out
`gpt-5.1-2025-11-13`	GPT-5.1 (coming soon)	$1.25 in / $10 out
`gpt-5-mini`	GPT-5 Mini (coming soon)	$0.25 in / $2 out

Setting the Model

CLI:

teamday agents create --name "Fast Bot" --model claude-haiku-4-5-20251001 --system-prompt "..."

API:

{
  "name": "Fast Bot",
  "model": "claude-haiku-4-5-20251001",
  "systemPrompt": "..."
}

Tools

Every agent has access to built-in Claude tools by default:

Tool	Description
`Read`	Read files from the workspace
`Write`	Write files to the workspace
`Edit`	Make targeted edits to existing files
`Bash`	Run shell commands
`Glob`	Find files by pattern
`Grep`	Search file contents
`WebSearch`	Search the web
`WebFetch`	Fetch and process web pages

Platform MCP Tools

TeamDay provides built-in MCP tools that agents can use:

Tool	Purpose
`mcp__teamday-media__MediaGeneration`	Generate images and videos
`mcp__teamday-admin__TeamdayAdmin`	Manage platform resources (spaces, agents, skills)
`mcp__teamday-ui__UICommand`	Control the chat interface (notifications, modals, handoffs)

See Platform Tools for detailed documentation.

External MCP Integrations

Connect agents to external services by installing MCP servers on a Space:

teamday spaces add-mcp <space-id> google-analytics ahrefs

See MCP Servers for available integrations.

Restricting Tools

Characters support an allowedTools field to restrict which tools the agent can use:

{
  "allowedTools": ["Read", "Write", "Glob", "Grep"]
}

This removes access to Bash, WebSearch, and other tools not in the list.

Visibility

Control who can see and use your agent:

Level	Description
`private`	Only the creator can see and use
`organization`	All members of your organization (default)
`public`	Listed on the TeamDay `/team` page — anyone can use
`unlisted`	Accessible via direct link, not listed publicly

Public Characters get a marketing page at teamday.ai/team/{slug} with their description, FAQ, use cases, and a "Add to Team" button.

System Prompt

The systemPrompt (Agents) or system_message (Characters) field is the core of your agent's behavior. See Prompts & Instructions for a complete guide.

Key tips:

Start with identity: "You are Name, a role"
Define behavior: what the agent should do and how
Set constraints: what the agent should not do
Be specific: vague prompts produce vague results

Skills

Skills are reusable capabilities. Assign them to Characters via skillIds:

{
  "skillIds": ["core:research-assistant", "core:data-analyst"]
}

Or add them to a Space where any agent can use them:

teamday spaces add-skill <space-id> core:research-assistant

See Skills for how to build custom skills.

Updating Configuration

All fields can be updated after creation:

CLI:

teamday agents update <id> --model claude-opus-4-6 --system-prompt "New instructions..."
teamday characters update <id> --skills "core:research-assistant,new-skill"

API:

curl -X PATCH "https://us.teamday.ai/api/v1/agents/<id>" \
  -H "Authorization: Bearer $TEAMDAY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-opus-4-6"}'

Only provided fields are updated. Omitted fields remain unchanged.

Next Steps

Prompts & Instructions — Write better system prompts
Tools — Deep dive into available tools
Skills — Build and install reusable capabilities
Spaces — Configure workspaces for your agents