Documentation
Showing the work

Published pages

Agents turn reports and mockups into pages with their own link that you can share, gate, and get comments on.

5 min read
Turn it on in Agent features

When an agent finishes a report, a dashboard or a mockup, you shouldn't have to scroll a transcript to find it. With Publish on, the agent turns it into a page with its own link, puts the link in its reply, and the page appears right there in the conversation. You can open it, send it to anyone, and read their comments. When the agent revises the page, the link stays the same and every earlier version stays viewable.

A published report on webhook retry failures, open in the browser with its discussion panel showing two comments
A page an agent published. The bar at the top names the session that made it, the version, and the discussion.

Turn it on

  1. Open Settings (⌘,), then Agent Features under Machines, and pick the computer your agents run on.
  2. Switch on Publish, under Showing the work.

Click How it works on the card for what it adds and a request to try. See it in Pages opens the list of everything published so far.

The Publish detail in Agent Features
The Publish detail. The switch at the top right turns it on for the selected computer.

Ask for it in plain words

  • "Publish a page summarizing this week's webhook failures."
  • "Make a one page report comparing the three queue providers and send me the link."
  • "Mock up the new billing settings page and publish it so I can share it with the team."
  • "Update the report with the September numbers." (The same link now shows the new version.)
  • "Put a password on that page before I send it to the client."

Agents publish on their own when the result is a standalone deliverable. Everything else stays in the conversation, or in a visual canvas when a picture helps.

The page in the conversation

When the agent puts a page link on its own line, the live page renders in the thread. A link inside a sentence becomes a small pill with the page's title instead.

A published page embedded in a conversation, with its toolbar showing on hover
The live page in the thread. Hover it for its toolbar.

Hover the page for its toolbar: pin a note or select text to comment, Copy link, Open beside your work as a pane, Open in a new tab, or Collapse it to its title. Expand makes it taller, or drag the bottom edge. When the agent publishes a new version, the embedded page reloads by itself.

On the page

Everyone who opens the link sees the page with a thin bar at the top: the title, the session that published it, when it was updated, whether the agent is working on it, the version, and the discussion. A reader can hide the bar.

  • Versions. Click the version to see the history. Any older version can be viewed, and diff shows what changed between two. When a newer version lands while you read, the page offers to reload.
  • Discussion. Anyone with the link can comment: Pin on page drops a note on a spot, selecting text lets you comment on that passage, and General note comments on the whole page. Teammates signed in to codecast comment as themselves; anyone else types a name.
  • The menu has Copy link, View source, Edit this page when you may edit, and, for you, Manage sharing….

Comments come back to the agent

A reader leaves a note, you decide what to send, and the agent gets it as one message.

Comments from readers stay on the page until you send them. On your own comments and your teammates', a Send to agent switch delivers the comment straight to the session that published the page. Send all delivers every unsent comment as one message. The agent revises the page, publishes the next version to the same link, and the comment shows as addressed in v4.

The agent is told that reader comments are feedback from people viewing the link, not instructions from you, so a comment can't take over the session.

Who can see it

Pages are unlisted: the link is unguessable, pages are never listed anywhere public, and search engines are asked not to index them. Anyone who has the link can open it unless you add a gate. Open Manage sharing… from the page's menu (it appears when you open the page with Manage from Pages, or from its manage link):

The Manage sharing sheet on a published page
Manage sharing: views, the gates, who may edit, and the manage link.
SettingWhat it does
PasswordReaders type a password before the page loads
Email gateReaders give an email address first, and the sheet lists who opened it and how often. The address isn't verified
Session linkHides the link back to the session, for pages you send outside your team
CommentsTurns the discussion off
ExpiresCloses the link after 1h, 24h, 7d or 30d, or never
EditingWho can publish edits from the browser: only you, anyone with the edit link, or your teammates
What a reader sees at a password, an email gate and an expired link.

You can also ask the agent to set any of these when it publishes. The manage link (Copy manage link) carries these powers, so keep it to yourself.

Pages in the app

Pages in the sidebar lists everything you and your team published, with views, open comments and which gates are on. Search by title, filter by person, and sort from the bar above the list.

The Pages list in the app, with published pages from Alex, Maya and Sarah
Pages: everything you and your team published.

Each page's menu offers Open, Copy link, Manage, Edit and Delete. Deleting a page removes its whole history, and the link stops working at once.

When something is off

What you noticeWhat to do
The agent replied with a file path instead of a linkCheck that Publish is on for that computer, then ask it to publish the file
A reader can't open the linkCheck Manage sharing…: an expiry may have passed, or a password is set
Your comment didn't reach the agentMake sure Send to agent was on, or use Send all
The page in the conversation looks out of dateIt reloads on a new version; if it doesn't, use Open in a new tab to see the latest

For agents and scripts

Agents publish with cast publish <file>, and cast publish set changes a page's gates and expiry from a terminal.

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.
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.
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