Documentation
Tracking and automation

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.

6 min read

A session is one conversation: it does a piece of work and ends. Work that lasts, like keeping growth moving or looking after the billing code, needs someone who is still there next week. In codecast that is a role: a named seat with an area it looks after, someone it reports to, and a charter you write that says what it is for. Each role has one standing session that speaks for it, checks its area on a schedule and answers what you send it.

Because work goes to the role, not to whichever session happens to be running, you can assign a task to @growth, mention @growth in chat, or write on its page, and it reaches whoever holds the seat today. Restart the session or replace it, and the role keeps its area, its notes, its tasks and its place on the chart.

The Codecast org page before anyone was hired, offering to hire the Head of People
A new org starts with one offer: hire the Head of People, the team's standing agent at the top of the chart.

Turn it on

The org is a team feature. A team admin opens Settings, then Team, and switches on Organization under Features. It is marked In development. Your personal workspace can have an org of its own once any of your teams has it on.

Then open the Org page. It shows your team's goals, projects and people as one chart, with Everything, Goals and People views, a Health button, and Add a role.

Start with the Head of People

A new org offers one hire first: the Head of People, the team's standing agent at the top of the chart. Pick the project folder it lives in (or leave it blank) and click Hire Head of People. It reads how work actually flows in your team, proposes who should own what in a weekly review, looks after what no other role owns, and answers in chat and Slack until the team hires an Executive Assistant. You can rename it and give it a face on its page.

To get a first proposal right away, click Propose an org now: a fresh session reads your projects, sessions and commits and suggests the roles that would carry the work.

Add a role

Click Add a role on the Org page, or Add a lead on a project that has none.

The Add a role dialog with name, handle, face, area, reports to, charter and how long
Add a role. The charter is written from the area you pick, and you can edit it freely before you create the role.
  • Name and Handle: what people see, and the @handle to mention it by.
  • Area: the projects and plans it looks after. With none picked it has no area of its own; it runs its check and answers what it is asked.
  • Reports to: a person or another role. What it can't settle itself goes there, with its recommendation.
  • Runs on: whose computer and account run its session.
  • Charter: what the role is for. You write it; the role itself can't change it.
  • How long: Ongoing, or Until something ends.

Click Create and start. The role starts as soon as you create it. From a template sets up a role someone has already packaged, with its charter and routines.

Give it work

YouThe role
Assign a task to it (the Assignee picker lists roles next to people)Is told about the task, and answers for it
Mention @handle in team chatWakes and reads your line (Team chat)
Write to it on its pageGets your message in its standing conversation
WaitRuns its regular check, reads what changed in its area since last time, and acts on it

Things you might write to a role:

  • "The pricing page is live. Watch the signup funnel this week and tell me if it drops."
  • "Take over the open billing bugs and keep me posted on the ones that need a decision."
  • "What is stuck in your area right now?"

A role's page

Click a role on the chart to open its page. Its standing conversation fills the left side, so there is one place to talk to it. The tabs beside it:

TabWhat it shows
OverviewWhat it is for, where things stand, what it is doing, its notes, and what happened lately
WorkIts tasks, by status, its plans and pages
SessionsThe sessions working for it, grouped by who acts next
DecisionsQuestions it raised and how they were answered
TriggersIts regular check and any other schedules, with the next run. Change or pause them here
SettingsName, area, who it reports to, whether it starts work on its own, its limits, where it runs, which chat channels it reads, and its history

Two settings decide how much it does without you:

  • Starts work on its own. On, it starts work in its area and answers decisions there without asking. Off, it reads, answers questions and recommends, and you start the work. The Head of People always proposes and leaves the deciding to you.
  • Limits. The most it may do in one day: sessions started, turns, and tokens, with sensible defaults filled in. When it reaches one, it waits for tomorrow and says so in its notes.

Pause role in the page's menu stops its schedules and lets its sessions finish at a safe point; Resume role brings it back. Retire role ends it for good.

What you see in the inbox

A role gets one card in your inbox, with a sessions pill for the sessions working under it. Those sessions sit under the role (hover one: Reports to @handle, which decides what reaches you), not in your inbox one by one, so twenty sessions on growth don't become twenty cards.

A question travels up the line. A session asks its role; a role that can't answer asks whoever it reports to. When it reaches you, it arrives as one card from the lead that needs you, with the question pinned at the top of its conversation.

Proposals: agents suggest, people decide

Changes to the org itself (a new role, a move, a retirement, a wider area, a new routine) are always a person's call. The Head of People, or a session you asked to review the org, writes them as a proposal on the Org page. Each change shows its reason and evidence, with Approve, Reject and Reply. Approve all takes the rest in one go, and approved changes apply when you send your answers.

When something is off

What you noticeWhat to do
There is no Org pageAsk a team admin to switch on Organization in Team settings
A role isn't starting anythingCheck Starts work on its own in its Settings, and whether it is paused
A role went quiet partway through the dayIt reached one of its Limits. Raise it, or let it pick up tomorrow
Work in a project isn't reaching its roleCheck the role's Area includes that project. Health on the Org page flags roles that are overloaded, idle or bypassed
Too many sessions in your inboxGive the work a role: sessions in a role's area sit under its card
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 feed 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.
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 into one queue 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.
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.
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.
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