Documentation
Tracking and automation

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.

4 min read
Turn it on in Agent features

A workflow is a process you want run the same way every time: build the change, run the checks, loop back if they fail, then stop and wait for you to approve before anything ships. Each step is an agent, a command, or a point where a person decides. A prompt describes what you want and hopes the agent follows it; a workflow fixes the order, the checks and the sign-off.

Workflows only run when someone starts one. Agents never start one on their own.

A workflow run paused at its approval gate
A run waiting at its Approve step. Pick a choice or answer in your own words.

Turn it on

Open Agent features (under More in the sidebar), pick the computer your agents run on, and switch on Workflows under Tracking & automation.

The Workflows card in Agent features
Click How it works on the card for what it adds and a request to try.

Make one by asking

Describe the process and the agent writes the workflow and checks that it is valid. It lives in your project as a small file, so it can be reviewed and changed like code.

  • "Write a workflow that implements a task, typechecks, and waits for my approval before merging."
  • "Add a step to the release workflow that runs the end to end tests before the approval."
  • "Make the review loop give up after three failed attempts."

A workflow can hold these kinds of steps:

  • An agent step: a session with its own instructions, on Claude, Codex or another agent.
  • A command: tests, a typecheck, a build. Whether it passes decides where the run goes next.
  • An approval gate: the run stops until a person picks one of its choices.
  • A branch: route on the result of the step before, or run several steps side by side and wait for them all.

Start a run

Click Workflows in the sidebar, under Automation. Routines lists your workflows and Runs lists the runs so far. Pick a workflow and click Run, give it the Project path and, if you like, a Goal override, then click Run. A review shows the steps and agents it will start; confirm it there.

Starting a workflow run
The run dialog: the project, an optional goal, and Run.

A plan with a workflow attached has a Run workflow button on its page. You can also ask in a conversation: "Run the review workflow on the webhook retries task." A run is tied to a task or plan, which is where it gets its goal and context.

One run: the first typecheck fails and loops back to the agent, the second passes, and the run waits at the gate until someone approves.

The run page

Each run has a page. The top line says where the run stands, and links under it open the session that ran it, its task and the decision it is waiting on. Below, every step is listed by phase with how far each phase got and how long each step took. Each agent step is a real conversation you can open and read. Show the graph draws the whole workflow with the current step highlighted.

The workflow's graph and its steps
The graph: the check passed, the run sits at Approve, and Revise would send it back.

Answer a gate

When a run reaches a gate, it waits. The question appears on the run page, in Decisions, and as a notification on your phone and desktop. Pick a choice, or write a reply in your own words: your words travel to the next step as its instructions, so "Revise: keep the old retry limit as the default" sends the work back with that note. Dismiss ends the run there.

While a run is waiting, its task shows In Review on the task and plan pages.

Workflows, orchestration or triggers

Use a workflow when you know the steps and they must run the same way every time: a release checklist, a verify loop, anything with a required sign-off. Use orchestration when the shape of the work isn't known up front and a lead agent should work it out across many agents. Use a trigger for a single follow-up later or on an event, with no graph at all.

When something is off

What you noticeWhat to do
A run failed right after a gateIt was dismissed, or the answer matched none of the gate's ways out. Start it again and pick one of the listed choices
A run keeps loopingAsk the agent to give the loop a limit, so it stops after a few failed attempts
Nothing listed under RoutinesNo workflow has been written in this workspace yet. Ask an agent to write one
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.
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.
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