Skip to content
MatterSpace

MS Duplex — The Agent Operating System powered by Runtime Intelligence. Rent the model. Own the intelligence.

New skills, learned on its own.

Routine work nobody scripted becomes a skill MS Duplex runs itself, where it is safe to try.

Skill Fabric: reusable skills. It runs On request, once your team switches it on. In the Agent Operating System, it is how every agent gains new skills, proven programs and the right tool for each job.

  • 100%*
    Of tasks completed with the model switched off, and every learned skill removable. See the result →

* Figures from MatterSpace’s internal benchmarks, not independently verified. Read the disclaimer

Set a goal and the limits. MS Duplex works out the skill, and proves it.

Your team gives MS Duplex a goal, such as setting up a new client’s workspace, with the actions it may take and a way to check success.

Step 1 of 5: The goal

A task MS Duplex has learned stops costing a model call.

Once the skill is proven, every new client after the first gets a workspace set up by MS Duplex itself, and your AI is free for work that is new.

Step 1 of 3: First client

The first new client’s workspace is worked out step by step, and the result is checked.

Every task completed with the model switched off.

MS Duplex was tested on four suites over ten runs, with no examples, labels or help. It completed 100% of tasks, refused every unsafe shortcut and could remove every skill it learned.*

Step 1 of 5: Model off

The model was switched off for the whole test: a single model call would have failed the run.*

It only tries what you allow.

MS Duplex learns new skills where it is safe to try and where success can be checked. An action outside the limits you set is refused before it runs, and the skill is still learned.

Step 1 of 4: Allowed

Creating the client’s project board is within its limits, so MS Duplex may try it.

See it on your own work.

From your own assistant to every agent your company runs, a pilot puts MS Duplex on your own work, with the measures agreed before it begins.