✨What's New

A running job could show a tool’s name, replace one step with the next, or go quiet with no sign of progress, and the chat’s summary could disagree with the job’s card. Now each step gets its own line in plain words, quiet stretches are counted, and every job ends with one clear status and a list of the files it made.

• See the brief your agent sent

  Each job now starts with the brief your agent sent it, so you can check what was asked. A long brief opens in full with one tap.

• Every step in plain words, line by line

  Steps say what’s happening in plain words, each on its own line. After 10 quiet seconds, the last line counts the seconds since the last update, so a quiet job never looks frozen.

• One clear ending, with your files listed

  Each job ends with one status, such as Delivered or Partly delivered, and the files it made, each with an Open button. Your agent’s summary works from that same list.

• Know when a job never got going

  A job that never got going now reads “Couldn’t start” and says nothing ran, so you know to try again, instead of looking like work that failed partway.

• Your agent picks the skill

  The skill buttons in the chat are gone. Describe what you need, and your agent picks the right skill for the job.

Once a job had started, you couldn’t stop it, and if it broke partway through, its card could say “Working” for hours. Now a Stop button ends a running job, jobs start on a fresh machine of their own, and your agent takes one job at a time. Cards say what really happened, and the chat opens at your newest message.

• Stop a running job with one tap

  Tap Stop on a running job’s card and the work ends, shown calmly as Stopped, not as a failure. If Slate can’t confirm the job has stopped, it says so, and you can try again.

• A fresh machine, one job at a time

  Jobs used to share a machine, so one could cut another short. Now jobs start on a fresh machine of their own, and your agent takes one at a time, saying when it’s busy.

• An honest result when a job breaks

  If a job stops unexpectedly partway through, its card says so within 10 minutes, not hours later, and the files it saved are kept. A job that fails to start now shows as failed.

• Jobs without steps get a name and status

  A quick job without steps used to sit empty in your Jobs list and never reach the Board. Now it shows one line with its name and status: working, done, failed, or stopped.

• Chat opens at your newest message

  Opening a chat could leave it blank or stuck partway up the conversation. Now it opens at your newest message and holds there while job cards and pictures load, until you scroll up yourself.

A finished job used to end on one thin line in the chat naming one file; the rest sat in a separate gallery. Now the chat hands the work over as a stack of previews you can flip through and open, and each job keeps its files beneath its steps. While a job runs, you get more detail on the current step and each step’s status at a glance.

• Flip through finished work in the chat

  Delivered files arrive as a stack of previews: most pictures as themselves, videos by their first frame. Flip through with a swipe, the arrows, or your keyboard, and tap the front card to open it.

• A job’s files, right beneath its steps

  In your agent’s Jobs list, each job’s files sit beneath its steps as tiles you can tap to open. This replaces the Documents gallery; files not tied to a job gather under “Other files.”

• Every step’s status at a glance

  In the Jobs list, each step shows a small icon for done, running, next, or failed. On the Board, each job’s label shows its result and how long it took.

• A clearer view of the work in progress

  While your agent works, a quiet line under the timeline says what it’s doing right now. It can also say how it’s getting around a snag, and explain its choices when it finishes.

• A smoother start to each request

  Every agent, even one with no skills yet, now runs its jobs in the Studio you chose. Ask for several things in one message and it starts one job, not several at once.

A working agent used to give you a scrolling machine log and little sense of where things stood — and the moment you left the chat, you lost sight of it entirely. Now the work reads like a calm journal: the current step shimmers as it happens, your document glows for exactly as long as a job is running, and each job’s tasks are laid out as a List or a Board. Leave the chat and the job rides along in a small status pill you can tap to check on. And every file it makes is tagged with the job that made it.

• See every step as it happens

  While your agent works, the chat shows a live, unhurried timeline of what it is doing, with the current step gently shimmering. No more reading a wall of machine output to work out where things stand.

• Your work glows while a job runs

  The panel around your document blooms a soft light for exactly as long as a job is running, and goes quiet the moment it finishes. You can tell something is happening without watching the chat.

• Tasks as a List or a Board

  Each job’s steps appear as a clean list — newest on top, the live one marked, the done ones checked off — and a finished job folds to a single line you can reopen, with a jump straight back to that moment in the chat. Prefer columns? A Board is one tap away, and your choice is remembered.

• A status that follows you

  Leave the chat and a running job rides along in a small pill in the header bar: the current step, the time elapsed, and a tap to open the full plan. Start a second job and it splits off into its own dot — tap it to switch which job you are watching.

• Files know which job made them

  Every file your agent produces now carries a tag for the job that made it, pictures show a real thumbnail, and you can filter down to a single job’s output. Finding the thing you just made no longer means guessing.

• Honest titles, verdicts, and timings

  Every job shows its real name, whether it delivered, and how long it took — one number, the same everywhere you see it. Where a per-step time could not be measured truthfully, it is left off rather than faked.

• Agents now run on Claude Sonnet 5

  Every agent moves up from Claude Sonnet 4.6 to Claude Sonnet 5, in chats and jobs alike. There’s nothing to switch on: the agents you’ve already hired move up too.

A long job used to depend on your open page, and it stopped after about half an hour. Now jobs run on their own for up to six hours, keep going if you close the tab, and save their result to the chat when they finish. Come back partway through and the job card catches up.

• Jobs keep going for hours

  A job can now run for up to six hours, so bigger pieces of work no longer stop at the half-hour mark.

• Close the tab, and the work carries on

  Closing the tab, losing your connection, or an update to Slate no longer cuts a job short. It keeps working and saves its result to the chat when it’s done.

• Come back to a job in progress

  Reload the page or return later, and the job card catches up with what the job is doing, then keeps updating as the work continues.

Choosing a skill used to mean a row of small buttons, and your choice wasn’t passed on to your agent. Now a bar at the bottom of each agent’s page lets you search for a skill and pick it, and your agent uses that skill. A bell tells you when a job finishes, and portfolios now show real pictures and videos.

• Find any skill in seconds

  A bar at the bottom of each agent’s page sorts its skills into Featured, All, and Recent. Search by name, or press ⌘K (Ctrl+K on Windows) to open it.

• Your agent uses the skill you pick

  Choose a skill and your agent now uses it for your request instead of picking its own. The chosen skill stays in the bar until you change or clear it.

• Know when the work is done

  A bell with an unread dot and an inbox list the jobs your agents finished, even after a reload.

• Portfolios with real pictures and videos

  An agent’s portfolio now shows its pictures and plays its videos, on larger cards that let the work fill the frame.

• Make your agent’s page your own

  Tap the emoji on your agent’s page to change it; before, it was fixed once created. An agent you hired links back to the one you hired it from.

Replies could pause for a slow check before starting, a finished job could take up to 22 seconds to report back, and long videos could time out. Now every agent runs on Claude Sonnet 4.6, replies and results come sooner, and long videos run to the end. When something goes wrong, the error stays on screen with a way to fix it.

• Every agent runs on Claude Sonnet 4.6

  Chats and jobs alike now run on Claude Sonnet 4.6, up from earlier Sonnet models, with nothing for you to change.

• Faster replies, faster results

  A check that added up to three seconds before each reply is gone, and a finished job now reports back in under a second, not up to 22.

• Errors stay on screen, with a fix

  If a message can’t go through, a clear alert stays in the chat with a button for the next step, such as trying again or signing in.

• Long videos run to the end

  Videos that take longer than about five minutes to make used to be cut off partway. Now they keep going until the video is ready.

• FixTasks stuck after a job ends

  When a job ends early, its unfinished tasks are now marked failed, instead of staying in To Do or Active forever.

Until now, a job had no ready-made know-how to draw on. Now you can add skills as you write it, set each one’s options in a short form, and the job runs with them in place. Some starting points come with skills built in, and each piece of work opens with a clearer view of its progress.

• Add a skill to a job

  As you write a job, add a skill for spreadsheets, slide decks, documents, or brand guidelines, and it’s in place when the job runs.

• Type /skill to find one fast

  Type /skill while you write, narrow the list by name, and drop the skill right where you want it.

• A short form for each skill’s options

  Each skill appears as a card that says what it does, with a short form for any options it needs.

• Starting points with skills built in

  Some ready-made starting points now come with the right skill already added, so you can run them as they are.

• See progress at a glance

  Each piece of work opens with a header showing how much is done, how many files it has, and a preview stack of your documents.

Following a busy project meant switching between jobs to see where each one stood. Now one board shows every task, grouped by job. A badge tells you when work is running, switching projects shows the right progress straight away, and more kinds of documents open right in Slate.

• Tasks grouped by job

  Your project’s tasks sit in To-Do, In Progress, and Completed columns, grouped by the job they belong to, so you no longer switch between jobs to see where things stand.

• See at a glance when work is running

  While a job runs, an In Progress badge pulses beside the project’s name and goes away when the work is done.

• The right progress when you switch projects

  Switch projects from the sidebar and the overview and task list update straight away, without showing another project’s tasks.

• Open more documents right in Slate

  More kinds of finished documents, like reports ready to print or share, now open in the viewer beside your chat, with a button to save a copy.

• Every kind of file, easy to spot

  Each kind of file now has its own icon and color, the same wherever it appears, so a spreadsheet never looks like a video.

Starting something new meant a blank page or a trip to the gallery, and you couldn’t see how much your work used. Now seven starters sit on the home page, and a blank Slate runs exactly what you wrote. Work is counted in simple credits, with your balance in the sidebar, plans to upgrade to, and a warning before you run out.

• Seven starters for common jobs

  Pick Research, Spreadsheet, Data Visualization, Product Photoshoot, Image Ad, Video Ad, or a blank Slate, check the brief, and run it. Slate sets up the project for you.

• A blank Slate runs what you wrote

  Write your brief in a new blank Slate and run it, and the job starts with exactly what you typed.

• Credits you can see

  Your work is now counted in simple credits. Your balance sits in the sidebar, and a new page lets you choose a plan to upgrade to.

• A warning before your credits run out

  The sidebar warns you when your balance runs low, so a job doesn’t stop without a reason.

• To-dos and files that update live

  A project’s page now shows its to-do list and files as they change, with ticks and times, without refreshing. Links to a file in another project open on the first click.

A job’s progress could read “No steps recorded,” and finished work had few ways to open. Now a step-by-step view shows what Slate is doing and links each file as it’s made. Three new kinds of files open in place, every viewer works the same way, and each project opens on an overview of its files.

• Canvases, live web pages, and video edits

  Jobs can now hand back designs on a zoomable canvas, web pages that show as a live preview instead of code, and simple video edits you can preview and adjust in place.

• Follow each step, open files as they appear

  A step-by-step view shows what Slate is reading, writing, and running, and ends with a plain summary like “All steps finished in 1m 52s.” Click a file in the list to open it.

• An overview for every project

  Each project opens on an overview with all its files in a grid, and you rename it by clicking its name. Your recent Slates wait on the home page.

• One familiar viewer for every kind of file

  Every viewer now shares the same toolbars and buttons, text and code open in a richer editor, and the video settings panel is easier to use.

• Faster jobs, fewer missing files

  In one test, a job that took two and a half minutes finished in under a minute and a half. A final check now recovers files the live view missed.

Slate began as an AI office suite. You keep work in projects with rich pages, describe a job in the chat or write it as a page, and Slate does the work on its own machine. Its to-do list ticks off as it goes, and the files it makes appear beside the conversation. A gallery of ready-made examples helps you begin.

• Describe a job, get files back

  Ask in the chat and Slate plans the work, runs it, and hands back documents, spreadsheets, code, and images. Each file opens in a viewer right next to the conversation.

• Turn a page into a job

  Plan a job on a rich page in your project, then run it from the page. Slate works from the whole page, not just a short chat message.

• Your files, current and in one place

  Projects and their files sit in one sidebar that updates as files arrive. A revised file replaces the old one instead of piling up copies.

• Start from a ready-made example

  Browse a gallery of ready-made projects by category, read a short guide for each, and start your own copy with Use This Slate.

• A new home page and sign-in

  A redesigned home page introduces Slate as an AI office suite, and signing up or signing in now happens on a new split-screen page.