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
Downloaded 9,074+ times · Works with 31+ model services — send each job to the model that suits it
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.
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.
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
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
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
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.
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.
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.
Draw the process once: AI picks the branch, failures retry with the error attached, and nothing moves on until tests pass.
AI keeps running on your computer; decisions come to your phone. Tap to reply, sign off or pick an option, and it carries on.
The free plan works out of the box. Upgrade for teams, schedules and remote sign-off. Activate in the app with a code.
Choose a plan on the store page and you will get a code after payment.
Update to the latest version, then Settings → Account/Plan → Redeem code.
Buying and renewing: FAQ; refunds: refund policy, or ask in the group.
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.
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.
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
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 →
Windows, macOS and Linux. Install and go.
