Documentation
Showing the work

The visual canvas

Agents answer with charts, comparisons and diagrams drawn right in the conversation when a picture says it better than text.

3 min read
Turn it on in Agent features

Some answers are easier to see than to read: a comparison, a before and after, a breakdown, a flow. With Visual Canvas on, an agent can answer with a small designed panel right in the conversation, with charts, cards, tables and diagrams, instead of a wall of text or ASCII art. Plain text stays the default. The agent draws a canvas only when the shape of the answer carries the meaning.

A conversation where the agent answered with a canvas: a bar chart of webhook retry failures by hour and three cards comparing backoff options
Asked to compare three backoff strategies. The answer is one canvas and a sentence of recommendation under it.

Turn it on

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

Agents started from then on know how to draw one. Click How it works on the card to see what it adds and a request to try.

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

Ask for it in plain words

Say what you want to see. Mentioning a visual helps, but agents also choose one on their own when it fits:

  • "Compare the three backoff options as a visual."
  • "Show me webhook failures by hour, before and after the fix."
  • "Draw the flow of a webhook from the provider to our database."
  • "Lay out the open pull requests by status."

What a canvas looks like

Real canvases, drawn by the same component the app uses. Pick an example or a theme: a canvas follows whichever theme you use.
  • It matches the app. A canvas uses the app's fonts and colors, and follows you when you switch between light and dark.
  • Small interactions work. Tabs, tables you sort by clicking a header, tooltips on hover, and charts with hover labels.
  • Pictures show in the message. When an agent wants to show you a screenshot or a chart it rendered, it uploads the image, so you see the picture rather than a path on its machine that your browser can't open.

The canvas header

The header shows the canvas's title and three buttons: Show source to see the HTML behind it, Copy HTML, and Fullscreen. Press Esc to leave fullscreen. A tall canvas folds behind a Show all button so it never swallows the conversation.

Where canvases show up

A canvas is part of the message. It stays in the transcript, appears for teammates reading the session, and shows in shared links and in decisions, where an agent can lay options side by side.

On the iPhone a canvas shows as a card with its title. Tap it to open it full screen, where you can also view its source or copy it.

A canvas card in a phone conversation, and the same canvas open full screen
On the phone, tap the card to open the canvas full screen.

What it will and won't do

Conversations sync across your team, so a canvas is something other people see without having written it. It is built to be safe to look at:

  • No code runs. Scripts, forms, embedded frames and anything that reacts to clicks are removed before the canvas appears. Tabs, sorting and charts are codecast's own, not the agent's.
  • Nothing phones home. Images from other websites are dropped, so a canvas can't track who opened it. Images an agent uploaded to codecast, and images drawn inside the canvas, show normally.
  • It stays in its box. A canvas can't restyle the app around it, and links in it open in a new tab (links to codecast's own sessions and tasks open in the app).

Canvas or page?

A canvas lives inside the conversation. When the result is something you will send to other people by link, a report for a stakeholder or a dashboard that runs its own code, ask for a published page instead.

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.
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