!v1.0.12 · New Workbench Canvas →

Hand AI what you want done.
It finishes and tells you.

Say what you want done and AI gets to work — fixing code and chasing bugs, or sorting files and drafting reports. Pick “Until done” and it breaks the job into steps and keeps going; when something needs your call, its card lights up and waits for your sign-off.

Desktop app for Windows · macOS · LinuxWorks with your Claude Code, Codex or any model API keyFree plan available

SpectrAI · Workbench Canvas

Downloaded 9,074+ times · Works with 31+ model services — send each job to the model that suits it

Claude CodeCodex CLIGPTGeminiDeepSeekQwenGLMOllamalocalOneAPI · NewAPIrelay

Stop watching AI work. It gets things done. You just sign off.

AI can do more and more.
Keeping track is the hard part.

Once you have several sessions, goals and scheduled jobs running at once, the problem is no longer starting them — it is seeing what they are doing. That is what the Workbench is for.

BeforeWith the Workbench
Too many sessions to followA long sidebar list — no idea which is running, stuck or long finished.
Sessions, goals, scheduled jobs and teams become cards, grouped by project, status at a glance.
AI is waiting and you never noticedIt has been waiting for your reply or sign-off for hours.
Cards that need you light up and get stamped; “Awaiting you” lists them all, failures included.
Gone quiet mid-runIs it stuck or still thinking? You cannot tell.
Anything running with no activity for 10 minutes gets an amber hint and moves to the front.
A busy day, but what got done?Reviewing means opening everything one by one.
Today’s timeline replays every scheduled run; group summaries pull out decisions and next steps, straight into your queue.

Say it in one line. Pick how it runs.

Type what you want at the bottom of the Workbench, then pick how it should run. Here are lines you can copy as-is — one set for code, one for everyday work.

Just do it

Ask like you would in chat

AI starts right away and reports back when done.

Look at recent changes in this project, find the one issue most worth fixing, fix it, then run the testsRename last month’s invoice PDFs in Downloads by date, move them into one folder, and make a table of the totals
Until done

Turn it into a goal

AI breaks it into steps and keeps pushing, round after round, until it is truly done.

Fill in the unit tests: list uncovered modules, add tests one by one, until everything passesGo through every meeting note in this folder, pull out action items and owners into one table, and tell me when all are done
Team upPro

Send in an AI squad

They split the work and review each other; anything below the bar goes back for a redo.

Refactor the login module into its own service without changing the API, then cross-reviewResearch three popular note-taking apps: split up pricing, features and reviews, cross-check, then write one comparison report
SchedulePro

Run on a schedule

Runs daily or weekly and brings the results to you.

Every day at 9am, check the project builds and dependencies have no security alerts; summarize any problems for meEvery morning at 8, check the industry sites I follow and send me the 5 most important new items

Not ready yet? Press Alt + Enter to save it as a note — nothing runs until you dispatch it.

From start to sign-off,
every step is checked.

Experts review it — and send it back if it falls short

Bring in an architect, a security officer or a QA expert from the Expert Store — or seat the whole council. Every result is scored on five dimensions; one veto sends it back.

  • Completeness, robustness, security, code smell, architecture contract
  • Below the bar goes back to the lead agent until it passes
Teams & experts: Pro and up

Review AI changes before they touch your main branch

Each task works in its own isolated copy, away from your main branch. Like the diff? Merge in one click. Don’t? Throw it away.

  • File-by-file diffs, every line accounted for
  • A silent pre-check flags conflicts before you merge
  • Parallel tasks each get their own copy

Turn routine work into a pipeline

Draw the process once: AI picks the branch, failures retry with the error attached, and nothing moves on until tests pass.

  • Branches, retry loops, fan-out and merge
  • Build and tests are gates — fail and it goes back
Workflows: Ultra
Split view · drag to put several sessions side by side Built-in browser · open web pages in the app Project library · no more re-explaining context Command center · token spend and risks on one page

Away from your desk?
Still your call.

AI keeps running on your computer; decisions come to your phone. Tap to reply, sign off or pick an option, and it carries on.

Mobile appUltraTelegramPro+FeishuUltraWeComUltra

Start free. Upgrade when you need to.

The free plan works out of the box. Upgrade for teams, schedules and remote sign-off. Activate in the app with a code.

Free
Hand AI what you want done — it works it through until done. Ready out of the box.
  • Workbench canvas, “Awaiting you” queue, Xiaoguang assistant
  • Just do it and Until done (single AI)
  • Split view (basic)
  • Prompt optimizer (basic)
  • No teams, expert review or schedules
  • No pipelines (workflows)
  • No remote sign-off from phone or chat apps
Download free
Best for automation
Ultra
Unattended: pipelines run themselves, sign off from anywhere.
  • Pipelines: draw a fixed process and let it run (workflows); prototype design mode
  • Remote sign-off via mobile app, Feishu and WeCom
  • More scheduled jobs, with custom triggers
  • Catches the AI drifting off the goal and sends it back
  • Tracks how each model performs so you can pick the best
  • Priority technical support & dedicated channel
Get a code
01Buy a code

Choose a plan on the store page and you will get a code after payment.

02Activate in the app

Update to the latest version, then Settings → Account/Plan → Redeem code.

03Questions?

Buying and renewing: FAQ; refunds: refund policy, or ask in the group.

Do I need my own model account?

With built-in quota you can start right after signing in. You can also use command-line tools you already have, like Claude Code or Codex (install and sign in locally — no key needed in SpectrAI), or add any model’s endpoint and API key, such as DeepSeek or Qwen.

How is this different from using Claude Code or Codex directly?

They do the work; SpectrAI keeps the work in hand: many jobs at once with clear progress, every decision in one “Awaiting you” queue, and changes you review before merging. From Pro, AI teams review each other and jobs run on a schedule.

Are my code and chats uploaded?

Sessions and project settings are stored in a local database on your computer by default, not uploaded as cloud chat history; only the requests you start are sent to the model service you choose. Privacy policy

Can I use it without coding?

Yes. Sorting files, summarizing material, writing reports, collecting news on a schedule — just say what you want in plain words. The “Everyday work” examples above show how. More questions →


Hand it one thing today.

Windows, macOS and Linux. Install and go.

v1.0.12 · Windows 10/11 · macOS 12+ · Linux x64
SpectrAI WeChat group QR code
Join the WeChat groupTips, feedback and new releases — first in the group