Hands on the machine
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.
5 min read
Turn it on in Agent features An agent that changes a web app should look at the result, and the pages worth looking at usually sit behind a login. With the Browser feature on, your agents work in the Chrome you already use, so your logins come along: staging, an admin panel, a dashboard behind single sign-on. Each agent gets its own tab in the background. Your tabs, windows and keyboard stay yours.
What the agent sees comes back to the conversation. Screenshots appear inline, and when a page misbehaves the agent reports the errors the page logged and the requests that failed, so you can read the cause without opening the page yourself.
Turn it on
You need desktop Chrome and codecast running on the same computer as your agents (Getting started covers connecting a computer).
- Open Agent features from your account menu and pick the computer your agents run on.
- Switch on Browser, under Hands on the machine.
- The card asks for the two steps that remain. Click Install extension to add Codecast from the Chrome Web Store, in the Chrome profile you want agents to use. Then click Pair: Chrome opens the extension, and you click Pair there.
- The card turns green and reads Chrome extension connected.
Repeat this on each computer you use. If an agent reaches for the browser before setup is done, the same steps appear as a card under its step in the conversation, with a Tell the agent to continue button once Chrome is connected. You never have to leave the conversation to finish setup.
Click How it works on the card to see what the feature adds and a request to try.
Ask for it in plain words
There is nothing to learn. Mention a page, or ask for something only a page can show:
- "Open the settings page, change the theme, and show me a screenshot."
- "Reproduce the checkout bug on staging and tell me what the console says."
- "Check that the new pricing table renders on the marketing site."
- "Read last week's invoices in the billing dashboard and total them."
Agents that change a web app also check their own work this way without being asked: open the page, look, fix, look again.
What you see in Chrome
- One tab per session, in the background. Agent tabs open inside a red tab group called Cast. They never take focus, and a tab you open yourself is moved out of the group so agents never touch it.
- You can tell when a tab is being driven. The page wears a thin frame, a pointer follows the agent's clicks, and Chrome shows its own notice that Codecast is debugging the browser. The frame and pointer are hidden from the agent's screenshots.
- Agents only touch their own tabs. A session cannot read, close or navigate your tabs or another session's.
- Tabs are cleaned up. An agent closes its tab when it is done, and a tab left behind by a finished session is closed for it.
What you see in codecast
Every browser step lands in the conversation as a small row above the agent's reply:
| On the row | What it does |
|---|---|
| Screenshot thumbnails | Click one to see it full size |
| open tab | Brings the agent's tab to the front in your Chrome |
| watch live | Opens the agent's tab in a pane beside the conversation, so you can watch it work |
| tab gone · reopen? | The tab was closed. Click to bring the page back |
An agent can also offer you a page: a chip appears next to the session title, and clicking it opens the page in a pane beside the conversation. It never opens on its own, because an agent should not move what you are looking at. In the Mac app this pane loads any site, including ones that refuse to be embedded in a web page.
What it will and won't do
- It uses your Chrome, never a copy. No profiles or cookies are copied or synced anywhere. If the extension is missing or asleep, the agent waits for it and tells you what to fix. It never quietly starts a different browser.
- Sign-ins stay with you. When a page asks for a login, the agent opens it in your Chrome and asks you to sign in there, then carries on in the same tab.
- Some pages are off limits. Chrome does not let any extension drive its own pages (
chrome://settings, the Chrome Web Store). The agent hands you the link and the exact steps, and carries on with the rest. - Leaving a mark waits for you. Agents read, click through and check pages freely. Submitting a form, sending a message, buying something or changing account settings happens only when you asked for it.
- A project can fence it in. A team can limit which sites agents may visit for a project, and every site an agent lands on is recorded.
When something is off
| What you notice | What to do |
|---|---|
| The card says Chrome is not connected | Click Pair again on the Browser card. If Chrome is closed, pairing opens it |
| The agent says the extension is asleep | Reload Codecast at chrome://extensions, then tell the agent to continue |
| Agents open tabs in the wrong Chrome profile | Pair from the profile you want. Keep Codecast enabled in only one profile |
| A session on another computer can't reach your Chrome | Chrome must run on the same computer as the session. Turn Browser on for that computer too |
For anything inside a native Mac app rather than a web page, such as a file picker, System Settings or Slack, see Computer use.
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.
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.
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.