Getting Started with TeamDay

This guide walks you through signing up, creating your first AI agent, and having your first conversation. You'll be up and running in a few minutes.

Visit teamday.ai and click Sign Up
Authenticate with Google, GitHub, or Email
An organization is created for you automatically

Once signed in, you land on the org home page where you can create agents, browse your files, and start chatting. To add team members, invite them from your organization settings — you can include an optional personal note with the invite email.

Core Concepts

Before building, here's how TeamDay is organized:

Concept	What It Is
Agent	An AI employee — a specialized team member with a name, role, system prompt, model, and equipment (skills, MCPs, subagents).
Folder	An ordinary folder in your organization's file tree. Every chat, job, and mission works from a folder you choose when you create it.
Skill	A reusable capability that teaches agents how to do specific tasks (e.g., generate images, write reports).
MCP Server	A tool integration that connects agents to external services (Google Analytics, Ahrefs, Slack, etc.).
Mission	A scheduled task — run an agent on a cron schedule, once at a future time, or continuously.

Onboarding Flow

When you first sign in, Teamday will ask for your company's website to personalize your setup — this is optional but recommended. Teamday researches your site and uses it to generate AI employee suggestions, starter projects, and mission ideas tailored to your business.

The recommended path to get started:

Sign up and create your organization
Enter your company website — Teamday learns about your company and personalizes your setup
Review AI employee and project recommendations — accept the ones that fit
Start chatting — everything is ready; provider and runner checks are supporting steps, not blockers

Create Your First Agent

In the Web App

From the org home page, click + Create Agent
Set the basics:
- Name: "My Assistant"
- Role: "General Assistant"
- System Prompt: "You are a helpful assistant. Be concise and friendly."
Start chatting immediately

Via CLI

teamday agents create \
  --name "My Assistant" \
  --role "General Assistant" \
  --system-prompt "You are a helpful assistant. Be concise and friendly."

Via API

curl -X POST "https://cc.teamday.ai/api/v1/agents" \
  -H "Authorization: Bearer $TEAMDAY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "My Assistant",
    "role": "General Assistant",
    "systemPrompt": "You are a helpful assistant. Be concise and friendly."
  }'

Chat With Your Agent

Every chat has two ingredients: the agent and the folder it works from.

Pick the Agent

Start a chat from the org home page or an agent's profile. The agent always brings its own equipment — instructions, skills, MCP connections, and subagents — into every chat.

Pick the Folder

When you start the chat, choose the folder the agent should work in (for example /projects/my-first-project). This is the chat's working directory: files the agent reads and writes by default live there, and it stays fixed for the life of the chat even if you browse other folders later. If you do not need files, the agent's default folder is fine.

Built-in Tools

Agents in TeamDay are powered by Claude and have access to a full set of tools:

Read, Write, Edit — work with files in the chat's folder
Bash — run shell commands
WebSearch, WebFetch — search the web and fetch pages
Glob, Grep — find and search files

These tools let agents do real work — not just answer questions.

Via CLI

Interactive multi-turn chat:

teamday agents chat <agent-id>

Single message execution:

teamday agents exec <agent-id> "Summarize the README in this project"

Start a chat in a specific folder so the agent works with those files:

teamday chats new --agent-id=<agent-id> --cwd=/projects/my-first-project

Create a Folder

Files live in ordinary folders in your organization's file tree. Nest them however you like; nothing is special about a top-level folder.

Open Files in the sidebar
Create a folder (e.g., /projects/my-first-project)
Upload any files the agent should work with, or connect a Git repository (see Git Integration)

Start a chat with that folder as its working directory and the agent can read and write files there, run commands, and use its tools.

Via CLI:

teamday files mkdir /projects/my-first-project

Equip Your Agent

Agents have four types of equipment, managed via the agent's detail panel:

Equipment	What It Does
Tools	Built-in Claude tools (Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch) — available by default
Skills	Reusable capabilities (e.g., research, data analysis, image generation)
MCPs	External integrations (Google Analytics, Ahrefs, databases, etc.)
Subagents	Other agents this agent can delegate work to

Attach Skills

teamday agents add-skill <agent-id> core:research-assistant core:data-analyst

Or attach them through the agent's detail panel in the web app.

Connect MCP Servers

MCP (Model Context Protocol) servers connect agents to external tools and services:

teamday agents add-mcp <agent-id> google-search

Popular integrations include Google Analytics, Ahrefs, Slack, and GitHub. See MCP Servers for the full list.

Store Secrets

If your MCPs or skills need API keys, store them as encrypted organization secrets. They are shared by every agent, whichever folder it works in:

teamday secrets put OPENAI_API_KEY "$OPENAI_API_KEY"

Visibility vs Attachment

These are two separate concepts:

Visibility controls who can see and discover an item: private, organization, public, or unlisted.
Attachment controls where an item is active: skills and MCP servers are attached to a specific agent and travel with it into every folder.

Setting an agent's visibility to organization means all org members can see it — but it does not mean every skill or MCP server is automatically available to it. Items must be explicitly attached to the agent to be used.

Set Up Authentication

For API and CLI access, you need credentials.

teamday auth login

Opens your browser for secure authentication. Tokens are managed automatically.

Option 2: Personal Access Token (API / CI)

Go to Settings in the web app
Create a new Personal Access Token
Copy and save it immediately (shown only once)

# Use with CLI
teamday auth set-key "td_your_token_here"

# Or as environment variable
export TEAMDAY_API_TOKEN="td_your_token_here"

See API Keys & Authentication for the full guide.

Claude API Credentials

TeamDay agents are powered by Claude. By default, the platform provides Claude API access. You can also bring your own credentials for direct billing:

# Check what's configured
teamday keys status

# Set your Claude OAuth token (from claude.ai subscription)
teamday keys set oauth sk-ant-oat01-your-token

# Or set an Anthropic API key
teamday keys set api-key sk-ant-api03-your-key

TeamDay uses a priority system: your personal credentials are used first, then organization credentials, then the platform default.

Next Steps

Guide	What You'll Learn
Create Your First Agent	In-depth agent creation with equipment, models, and system prompts
Folders and Files	Organize folders, files, and Git repos
Skills	Build and install reusable agent capabilities
MCP Servers	Connect to external tools and services
Missions	Schedule agents to run tasks automatically
CLI Tool	Full command-line reference

Get Help

Support: support at teamday.ai
Community: Discord
API Reference: /docs/api

Getting Started with TeamDay

Sign Up

Core Concepts

Onboarding Flow

Create Your First Agent

In the Web App

Via CLI

Via API

Chat With Your Agent

Pick the Agent

Pick the Folder

Built-in Tools

Via CLI

Create a Folder

Equip Your Agent

Attach Skills

Connect MCP Servers

Store Secrets

Visibility vs Attachment

Set Up Authentication

Option 1: OAuth Login (CLI)

Option 2: Personal Access Token (API / CI)

Claude API Credentials

Next Steps

Get Help