Friday Work
Product
Solutions
Resources
Pricing
Try for free
Guides
Guides
Plain explainers and how-tos for teams working with AI agents.
Start here
What is an AI workspace?
An AI workspace is a shared place where a team works with AI. The main types, what to look for, and how a multiplayer AI workspace for coding agents differs.
What is multiplayer AI?
Multiplayer AI means people and AI agents working in one shared session with the same context. What it is, how it differs from single-player AI, and what it needs.
Multiplayer AI vs multi-agent AI
Multi-agent AI is agents working together. Multiplayer AI is people and agents working together. How they differ and why a team needs both.
Work with coding agents
How to share a Claude Code session with your team
Claude Code share links are read-only. Here are the ways to share a session with your team, and how to make it live so teammates can join and steer.
Use Claude Code, Codex and Cursor together
Each coding agent suits different work. How to run Claude Code, Codex and Cursor on one task in one shared session without them colliding.
AI pair programming with agents and teammates
AI pair programming no longer has to be one person and one assistant. How to pair with an agent, and a teammate, in the same live session.
How to run multiple coding agents on one repo
Several coding agents on one repository can overwrite each other. Simple rules to keep them apart, and how to see who is changing what.
Review and trust
How to review AI-generated pull requests
Agents open pull requests faster than teams can review them. A practical order of checks for AI-generated code, and how to catch problems earlier.
Human in the loop for coding agents
Human in the loop means a person can see, steer and stop an agent. The controls to look for, and how to set limits for a coding team.
What is an audit trail for AI agents?
An audit trail records what an AI agent did, who asked, and what happened. What to log, what makes it useful, and how to keep a record that helps.
Shared control of AI agents: the driver model
In a shared session each agent has one driver at a time. What that means, how control changes hands, and why it keeps teams from stepping on each other.
Agents and tools
AI agent handoff: how to pass work between agents
A handoff passes a task and its context from one agent to another, or to a person. What to pass along, what to leave out, and how to keep it visible.
MCP for teams: connect AI agents to your tools
MCP is the open standard for giving AI agents access to tools. How teams use it, how to keep access safe, and what to connect first.