Documentation
Working together

Workers, forks and switching agents

Your agent can hand work to workers that report back to it, and you can fork a conversation to try two directions from the same point.

5 min read
Turn it on in Agent features

One conversation is often not the right size for the work. Your agent may want a second agent to review its change, three workers to audit three modules at once, or a fresh look from Codex. You may want to try two approaches from the same starting point and keep the one that works. Codecast gives you both: workers your agent starts and manages, and forks you start yourself.

The difference is who looks after the result. A worker reports to the session that started it, so your inbox shows one thread and its answer. A fork is a conversation of its own, in your inbox, for you to steer.

A session that delegated two workers, linked them by name, and wrote one combined answer when both finished
A session that split a job between two workers and combined their results.

Turn it on

Open Settings, pick Agent Features under Machines, choose the computer your agents run on, and switch on Forks & Sessions under Working together. Your agents can then start workers on any agent you have installed (Claude Code, Codex, Cursor and others), fork when you ask, and hand work to a fresh session.

Ask for workers

  • "Have one worker review the diff and another write the missing tests, then tell me what they found."
  • "Get Codex to review this change before I merge."
  • "Audit each of the three payment modules in parallel and summarize the risks."
  • "Reproduce the bug in the other repo while you keep working on the fix here."

The agent writes each worker a brief, starts it, and waits. A worker starts fresh and knows only its brief, so the agent gives it what it needs. While it waits, the parent is dormant. It wakes when its workers finish, get stuck, or need a permission, and workers that finish together reach it as one message. Then it reads their results and gives you one answer.

Workers in the inbox

The Acme inbox with a session and two worker rows nested under it, each showing its agent and state
Workers nested under the session that started them.
  • Workers nest under their parent. The parent shows its first two; +N more sub-sessions expands the rest and collapse folds them away.
  • Every worker is a full session. Click one to read what it did, or write to it like any conversation.
  • States say who acts next. working means the agent is producing, dormant means it waits on something that will wake it, needs you means a person has to act, and done means it delivered.

Your agent creates separate inbox threads only when you ask for them. Asking for something to run in parallel gets you workers, not a stack of new cards.

Fork a conversation

A fork copies the conversation up to a point into a new session, which then goes its own way. Use it when the thread genuinely splits: two designs worth building, two theories about a bug, a risky refactor worth trying twice.

A message's menu open with Fork from here highlighted
Forking from a message.
  • Hover a message and click the fork icon (Fork from this message), or pick Fork from here from its menu, or press Alt F.
  • Write your next message and press Cmd Shift Enter (Ctrl Shift Enter off a Mac) to fork and send it in one step.

Or ask your agent: "Fork this two ways: try the queue, and try per endpoint limits." This thread continues on the first direction, and each other direction appears in your inbox as its own branch. A branch doesn't know it is a fork and reports to nobody; you steer it like any conversation.

Each branch carries the conversation so far. The request to fork stays out, so no branch inherits it.

Press T or Ctrl B for the Branch map: every branch of the conversation, which one you are in, and fork here from any point.

The branch map open over a conversation, showing the original thread and two branches with the current one highlighted
The branch map for a conversation with two forks.

Opening a teammate's session works the same way. Its message box reads Reply to fork this session..., and replying gives you your own copy, leaving theirs untouched.

Change the agent or the model

The model chip in a session's message box opens a menu whose Move this session part offers three ways to move a conversation:

The model chip menu: the model, effort, where the session runs, and Switch agent, Fork as and Hand off to under Move this session
Moving a session to another agent from the model chip.
ChoiceWhat it does
Switch agentSame session, another agent. The conversation continues under Codex (or another agent) with a divider marking the change
Fork asA copy of this session on another agent, alongside the original
Hand off toA fresh session, seeded with a brief of where the work stands

Change model & effort in the command palette changes the model without changing the agent. To start something new yourself, click New session in the sidebar or press Ctrl N.

On your phone

In the iPhone app, press and hold a message and pick Fork from here. The session's menu has Fork as… for another agent and Fork tree to see the branches.

When something is off

What you noticeWhat to do
Workers show up as separate cards in your inboxAsk the agent to start them as workers under its own session next time
The parent looks stuck while its workers runIt is dormant, waiting for them. It wakes when they finish
A worker is marked needs youOpen it. It may be asking a question or waiting on a permission prompt
You can't find a workerExpand +N more sub-sessions under its parent
More guides
Agent features: what your agents know how to do
Switch features on for each computer, and every new session there learns to remember, delegate, track work, show results and use your machine.
Memory: agents that look up past work
Your agents search every session you can see, across your machines, agents and team, and answer with the session they found it in.
Search your history across every machine
Every computer you connect sends its sessions to one history, searchable from the web, the Mac app and your iPhone.
See which agent session wrote a line
Set Blame to Sessions on any file to see the session behind each line, and open the conversation where it was decided.
Messaging between sessions
Your sessions hand each other results and answers directly, so you stop relaying text between them.
Stable context: sessions that know what's been happening
New sessions start with a short list of what you and your team worked on recently, so they pick up threads instead of starting cold.
See your whole team's agent sessions in one place
Every session your team runs, on every machine and agent, in one live Activity page and inbox, shared per folder.
Use Codecast with T3 Code
Threads you start in T3 Code appear in Codecast with no setup, beside every session you run anywhere else, ready to search, steer and share. What you get on top, and what stays in T3 Code.
Use Codecast with OpenCode
Sessions you run in the OpenCode TUI appear in Codecast within seconds, with no plugin. Reply to them from the app, start new OpenCode sessions there, and search them beside every other agent you use.
Share a session with your team
Choose what the team sees of a session, share it by link or a few messages at a time, and how that compares to other tools.
Pinned thread state
The agent keeps one short note on each session saying where it stands, above the composer and on its inbox card.
Decisions: asking without interrupting
Agents put the calls only you can make on one Decisions page you clear when you choose to, and each answer goes back to the session that asked.
Team chat with your agents in the room
Channels, threads and DMs where you can hand a session or a role something by mentioning it, while agents stay quiet unless they're needed.
Huddles, transcripts and walkie
Every huddle is transcribed under each speaker's name and leaves a summary, so your agents can quote what was said, and a session can join the call.
Tasks and plans
Agents file the work they take on, post progress and close it with what they verified, and you follow it on the Tasks and Plans pages.
Triggers
Agents schedule their own follow-ups, once, on a schedule or on a GitHub or Linear event, and you can set one yourself from the Triggers page.
Workflows
A fixed sequence of agent steps, checks and approval gates that runs the same way every time and waits for you where you want a say.
Orchestration
Hand an agent a whole plan and it runs a team: implementers working in parallel, a reviewer on every task and critics on the result.
Pull requests and issues
Every pull request gets a page with its checks and threads, the session that opened it fixes what reviewers and CI flag, and Linear or GitHub issues become tasks.
The org: roles that look after your work
Give lasting work to a role with an area, a charter and a standing session, and approve the changes your agents propose to the org.
Let agents use your Chrome
Agents check pages in the Chrome you already use, logins included, from their own background tabs. Screenshots and errors come back to the conversation.
Vault: keys, logins and sign-ins for your agents
Fill a credential once and every agent on every machine can use it, without the value ever entering a conversation.
Computer use: agents in your Mac apps
Agents work in Preview, Slack, System Settings or your own desktop build, in the background, with an orange pointer that shows where they act.
Typecheck: one shared check for every agent
With Typecheck on, agents on a computer share one typecheck per project, so checks answer in seconds and a busy machine stays usable.
Skills: slash commands for the jobs you repeat
Type / in a Claude Code session to pick up work, hand it over, get a second opinion or ship a pull request, the same careful way every time.
Run sessions on other machines and in the cloud
Start a session on another computer or a cloud machine in your AWS account, move it there and back, and watch it from anywhere.
Codex Cloud tasks in codecast
Bring your Codex Cloud tasks into your inbox, start new ones with several attempts, and turn the result into a pull request or local changes.
Usage limits are a pause
When a Claude plan runs out, sessions wait for the reset or continue on another account you've saved, instead of stopping for good.
The visual canvas
Agents answer with charts, comparisons and diagrams drawn right in the conversation when a picture says it better than text.
Published pages
Agents turn reports and mockups into pages with their own link that you can share, gate, and get comments on.
Why codecast feels instant, even offline
Everything you see comes from a copy on your device that the server keeps current, so screens open at once, your edits show immediately, and nothing is lost offline.
Taking longer than usualOffline · reloads when back