Plain answers about MS Duplex and MS Reflex.
The questions teams ask before they deploy.

With a pilot on your own work. Tell us where your team works and what MS Duplex should learn first. We agree the measures before it begins, and set MS Duplex up with you in the placement you choose.

On decisions and seats. A decision is one request MS Duplex takes part in, whether MS Duplex answers it or brings in your AI. Every quote comes in writing before you commit.

No. You bring your own model access and pay your provider for it, and MatterSpace adds no markup to tokens. A decision MS Duplex has learned needs no model call at all.

It stays in the placement you choose. In MatterSpace Cloud, MatterSpace runs MS Duplex for you and each customer stays separate. In your cloud, it stays under your controls. The one thing that leaves is a request to an outside model you connect, and that provider sees only that request.

MS Duplex is the Agent Operating System powered by Runtime Intelligence: the layer every agent runs on, whichever model it uses. MS Duplex is your AI model and an ACI model, working as one: runtime intelligence for your AI and your agents. Together they learn, plan, simulate, decide and act while the work happens, from one person to the whole enterprise. What it learns is yours. Built on ACI, Adaptive Continual Intelligence.

Today’s AI is fragmented: the model, retrieval and application code each hold a piece of the intelligence, and none learns from the work. MS Duplex is the infrastructure layer that binds them into one system that learns, plans, simulates, decides and acts. The centre of gravity moves to the whole system: the model can change, and MS Duplex carries the rest forward.

MS Duplex is the Agent Operating System powered by Runtime Intelligence: the layer every agent runs on, whichever model it uses. Agents now work for hours or days, across sessions, apps and models, but each one still builds its own memory, rules and tool connections, and loses them when the model or the app changes. MS Duplex gives them one layer for all of it, so every agent keeps its context, rules and tools whichever model or app it uses.

It coordinates everything a goal needs: the plan, the options, the decision, your approvals, the work in your tools and the check on the result. It carries each agent’s context, keeps long work going through pauses and change, keeps one history of every step and learns from what was verified. Your stack becomes one toolset for every agent, what each person, team and organisation learns stays in its own layer, and the model can change while what your agents learned stays.

The layer your agents run on is runtime intelligence at work: your AI model and an ACI model, working as one, learn from every result, plan, simulate, decide and act while the work happens. That is why it gets better with use, and why what it learns stays yours when you change models.

Anyone whose work runs on AI, from one person to the whole enterprise. A person starts in their own assistant, a team shares what it learns, a small business uses MatterSpace Cloud, and a larger company brings it into its own agents and cloud through MCP + hooks.

A harness gives your AI tools, prompts and steps, and does what it was set up to do. MS Duplex pairs your AI with an ACI model that learns from every confirmed result, plans, simulates, decides and acts within your rules, and carries your work across tools and models. It works inside Claude, Codex, Cursor and Hermes, and inside your own agents through MCP + hooks.

114 capabilities in 17 groups: Context and observation · Rules and behavioural control · Tool execution · Learning and personalisation · Long Horizon: long-running work · Planning and decision support · Skill Fabric: reusable skills · Persistent threads and sharing · Forgetting and data control · Status and explanations · Persistent intelligence · Personalisation · Multimodal intelligence · Confidence and autonomy · Runtime safety and oversight · Operational intelligence · Integration and portability.

Everything a goal needs: the context, the plan, the options played forward, the decision, your rules and approvals, the work in your tools, the check on the result, long-running work, recovery when something changes, and learning from what was verified. They work as one system around your goal, not as separate tools to wire together.

Long Horizon is how MS Duplex carries long work to its goal. Work that runs for days or weeks stays one job, with its goal, plan, rules and progress. Each step checks what it depends on before it runs, the plan is revised when the facts change, exceptions go to the people you choose, only verified steps count as progress, and the work is taken up where it stopped after a pause or a hand-off.

Skill Fabric is how MS Duplex turns what works into skills your whole organisation can rely on. A skill is made from work that was verified, can be opened and inspected, is shared with other teams once it is approved, is watched in use and retired when it stops delivering, and stays yours when you change models.

No. Those store what happened and find what looks like it. MS Duplex learns from experience at runtime: it understands the pattern behind each result, compresses it into what generalises, predicts what comes next and acts on it, within your rules. So it tells look-alikes apart, follows a changed rule from the next request and gets faster with use. They become its tools.

On its own at runtime, your AI model is rented by the call, starts every task from nothing, can’t learn from what your team confirms, loses context between sessions, and nothing checks what your agents do before they act. MS Duplex pairs it with an ACI model that learns, plans, simulates, decides and acts within your rules. The work gets faster and cheaper with use, and what MS Duplex learns is yours.

Your AI stays in place, and MS Duplex pairs it with an ACI model beside it. MS Duplex acts on what it has learned in milliseconds, and brings in your AI for new or uncertain work, with that learning attached. Each confirmed result teaches MS Duplex for next time.

Two intelligences doing different jobs together, the way the brain does: a slow one for general knowledge and a fast one for each new experience. Your AI is the slow one, learned before deployment. An ACI model is the fast one: it learns from live work, then plans, simulates, decides and acts on it. Together they are MS Duplex.

Partly: MS Duplex is your AI model and an ACI model, working as one. The ACI model is a second intelligence of its own, and it never replaces your AI. A confirmed decision can run in milliseconds without a model call. New or uncertain work goes to your AI with MS Duplex’s learning attached, and the confirmed result teaches MS Duplex for the next request.

Runtime intelligence: your AI model and an ACI model, working as one, learning, planning, simulating, deciding and acting while the work happens, within your rules. What it learns is yours. Two intelligences, one system: the combination is the product.

Anywhere your AI does real work: coding and desktop assistants, support and operations agents, enterprise workflows, high-volume AI products, teams adapting a model and regulated work. It is most useful where results can be confirmed, because MS Duplex applies each confirmed correction, decision or outcome to the next request it fits.

They become MS Duplex’s tools. MS Duplex calls each one when a step needs it, learns which one fits which situation and checks that what they return is current, sourced and dated.

ACI, Adaptive Continual Intelligence, is a new category of intelligence, created by MatterSpace. It keeps learning, planning, simulating, deciding and acting while your work happens, in tandem with the AI models you already use. MS Duplex pairs it with your AI model, MS Reflex with your autonomy stack.

AI models learn before they are released, and then stay as they are. ACI learns, plans, simulates, decides and acts after: at runtime, from your work, for as long as it runs. It learns your work rather than the world, builds on everything it learned before, and what it learns is yours: a category of its own.

In tandem. The model brings general intelligence: knowledge, language and reasoning. ACI brings what it learns from your work. It handles what it already knows, and brings in the model, briefed, for what is new. The model stays as it is, and you can switch models without losing what ACI learned.

For your AI: it learns on the spot from one confirmed result, follows a new rule from the next request, handles cases it has never seen, acquires skills and gets faster and cheaper with use. For your machines: it learns from one example, plans, simulates and decides on the device, and holds every command to your rules, connected or not. Either way, what it learns is yours.

Until now, only the labs that train models could make AI learn. With ACI, every person and every company has AI that learns from their own work, and owns what it learns. It compounds with every result and stays where you choose, in the cloud or on the machine, whichever model or stack you run.

Both are built on ACI, and ACI is the intelligence in each. Paired with your AI model, it is MS Duplex, inside your team’s assistants and the agents your company builds. Paired with your autonomy stack, it is MS Reflex, on any machine that decides and acts on its own.

ACI is the result of years of research into neural nets and their trilemma: plasticity, stability and editability. Plasticity is learning the new, fast. Stability is keeping what it knows. Editability is changing what it learned. A neural net gets two at best: learn fast and it forgets, hold it steady and it stops learning, and what it learned is spread through all of it. ACI holds all three.

Faruk Guney built ACI, MS Duplex and MS Reflex on his own, after years of research into the trilemma of neural nets and more than fifteen years growing Norck into a global on-demand manufacturing and engineering company.

From results that show the work was right: a passed test, an approved review, an observed change or a later business outcome. It can also be pretrained on reviewed examples, past decisions, documents, rules and tool routes.

Yes. Pretrain MS Duplex on your reviewed examples, past decisions, documents, rules, tool routes and libraries of proven methods. It learns them before it goes live, so it is useful from the first request, and it keeps learning in production.

Your team sets the standard for each kind of work. Code may need tests and review, while a regulated action may need a person’s approval.

A correction belongs to the work area where it was made, and it helps later work that fits. Authorised users can review, correct or remove anything MS Duplex has learned.

Yes. MS Duplex learns the pattern, so it handles new wording and new details, and it spots a look-alike that needs a different answer. On misleading look-alikes it was wrong 7.5% of the time, against 45.3% for a cache.*

The new rule applies from the next request. MS Duplex replaces the outdated decision and leaves unrelated work in place. After a policy change it served 0% stale answers, against 72% for cache and retrieval.*

Continual learning, at runtime. MS Duplex learns from each result as it is confirmed, so the next request already benefits, with no training run and no GPU. Through a change, 100% of its earlier work stays intact.*

Ordinary use is the training: MS Duplex learns from every confirmed result and applies it from the next request. Pretraining gives it a head start, and your AI’s weights stay as they are.

For work that is new, broad or creative, and anything that needs fresh writing or reasoning. MS Duplex prepares exactly what your AI is given, with what it has learned attached. A decision MS Duplex has learned needs no model call.

If MS Duplex was pretrained on that kind of work, it answers from the start. Otherwise your AI takes it with MS Duplex’s knowledge attached, and once the result is confirmed, MS Duplex handles it next time.

Your AI, whenever the work needs new writing or open-ended reasoning, with what MS Duplex has learned attached. When MS Duplex has learned the work, it answers on its own.

Everything MS Duplex has learned lives beside your AI, so it moves with you to the new model. In the adaptation test, what MS Duplex learned moved to another model family with no retraining at all.

No, it does the opposite. What your organisation learns lives in MS Duplex, not inside one vendor’s weights, one chat transcript or one app’s memory. Change the model, the agent client or the provider, and the processes, rules, history and skills stay.

Yes. Your placement and settings decide which model is available and where each request goes.

Ordinary cloud servers, on CPU. MS Duplex needs no GPU of its own: a decision it has learned takes ≈97 ms, against ≈2,231 ms for a model call. Only your AI needs accelerators, and MS Duplex brings it in for new work.*

The goal, settled decisions, constraints and unfinished work continue within the same customer and work area. Unrelated work and credentials stay behind.

What you need to continue: goals, decisions and unfinished work. The full transcript stays where it was, and your team’s access rules still apply.

Yes, when the connections belong to the same customer and allowed work area. Identity, work-area and customer boundaries stay in place.

Yes, when both people are authorised for the shared work area. Personal or restricted work stays separate, under your access settings.

Context helps you continue unfinished work, and it can be temporary. What MS Duplex learns comes from confirmed results, and it helps every time it fits.

It applies confirmed corrections, updates decisions when a rule changes, carries active work forward, plans multi-step processes, uses your tools and cuts model calls on work it has learned.

Yes. MS Duplex learns how your processes respond, plans the shortest route and carries constraints and confirmed methods across steps and sessions. Your AI brings fresh reasoning to every unexpected turn.

Yes. It learns what actions change in your systems, predicts the effect of a step before it runs and proposes the shortest route to a goal. On a public enterprise benchmark, it beat three frontier models at predicting system changes. Every real step still runs through your controls.

Yes, once your team switches it on: give it a goal, the actions it may take and a way to check success. It explores safely, tests the skill before using it and removes it on request. It completed every task with the model switched off.

Yes. MS Duplex makes your model answer as if it had been trained on your work, and the model’s weights stay as they are. It beat fine-tuned adapters in 6 / 6 tests, with no training run, and the adaptation moved to another model family with no retraining.*

Yes. For well-defined tasks, MS Duplex writes a small program or reuses one that has already worked, tests it against known cases and runs it once it passes. Your team can pause or retire it at any time.

Yes. Documents, knowledge graphs and databases become MS Duplex’s knowledge sources, each with its owner, source and date. MS Duplex knows when a fact changes, and brings the right facts into each decision.

Yes. MS Duplex can share approved learning and context with every agent in the chosen work area. For anything it learned, you can see which agent it came from, with which model, and when. Each customer’s learning stays with that customer.

Your team decides what MS Duplex learns from, reviews what it learned and can correct or remove any of it. Your rules, approvals and controls apply to every action.

The four plugins are Claude, Codex, Cursor and Hermes. Teams that build their own agents connect them through MCP + hooks.

Four plugins are available today. If your team builds and runs the agent, MCP + hooks may fit; for any other assistant, tell us which one you use.

For the agents your company builds. They connect to MS Duplex through MCP, and the hooks bring MS Duplex in at every step: before each request, before each tool call and after each result. Each action is checked against your rules before it runs, with approvals where you want them and one history you can export.

A plugin brings MS Duplex into a supported assistant through MCP, and builds your personal intelligence. MCP + hooks brings it into every step of the agents your company builds, and builds your company intelligence. It is the same MS Duplex in both.

Before each request, before each model call, before each tool call, after each result, at each hand-off and at each approval. MS Duplex applies your rules first, then what it has learned, and each action is checked before it runs.

A plugin, when people work inside a supported assistant. MCP + hooks, when your company builds its own agents and MS Duplex should join every step.

Yes. Connected to the same work area, they share the same approved learning and context. Access stays limited to the people and agents you authorise.

A plugin or MCP + hooks, who shares what MS Duplex learns, and, if you like, the examples, decisions and documents to pretrain it on. Then the placement and the access rules that fit the work.

With a supported plugin, people keep working inside the assistant they already use. The team confirms good outcomes and corrects bad ones, and approval steps depend on the product and work area.

From the first request, when you pretrain it. A confirmed correction helps from the next matching case, and every confirmed result makes MS Duplex faster, cheaper and more accurate.

Yes, that is pretraining. Reviewed examples, past decisions, documents and rules make a strong start. Your team places each one in the right work area and can correct or remove it later.

Yes. In the console, authorised users can review, correct or remove anything MS Duplex learned, and see the history behind it. The exact controls depend on the product and deployment.

No. You set what matters: the goals, the rules and the actions that need your OK. MS Duplex handles the routine inside those rules and holds every agent to them. It checks each model call and tool action before it runs, and carries what your team approved into every session.

Yes. You can set up narrower work areas, and identity and access settings decide who shares each one. All of that learning stays within your organisation.

MS Duplex has two placements: MatterSpace Cloud, which MatterSpace runs for you, and your cloud, a cloud account you own. Your cloud is an enterprise solution. Every integration is available in both, subject to the deployment terms.

As an enterprise solution. Contact us at hello@matterspace.ai with the environment, where data must stay and your security requirements, and we plan the deployment with you.

Yes. There is a supported path between placements, and what MS Duplex learned moves with no retraining. Operating responsibilities and migration work are agreed for each deployment.

Yes. A deployment can use your own model access. Model-provider charges, credentials and the boundary they create are handled separately and set out in the quote and agreement.

Yes. Your inputs, reference material, history and everything MS Duplex learns from them serve your organisation alone. Work areas can add narrower boundaries for teams, products, regions or data classes.

Yes. Across six families of paraphrased attacks, it blocked every one, with 0.7% false refusals, the lowest of any approach that blocked them all.*

You choose who is authorised, in every placement. MatterSpace operates the hosted service, and has access to a deployment in your cloud only when you delegate it for an agreed purpose.

Your team signs in to the console through your own identity provider, traffic is encrypted in transit, and what MS Duplex learns and the history are encrypted at rest. Options to hold your own keys depend on the placement.

Yes. Authorised users can remove anything MS Duplex learned, restore an earlier version, and export what it learned with its history. The deletion and backup process for your deployment is covered in the security review and agreement.

Yes. Remove a result or an observation, and what MS Duplex learned from it is withdrawn with it, so nothing built on it lingers. The history shows the change.

Only what you allow. Personal data can be redacted before MS Duplex learns from it, sends it to a model or adds it to the history, and MS Duplex can apply what it learned without the original text.

It is append-only and tamper-evident: every change is added as a new entry, so an altered entry would show. Authorised users can export it.

Authorised users can remove its influence, and unrelated learning stays as it was. After deliberate poisoning, MS Duplex removed all 40 poisoned samples, and its legitimate learning stayed intact.

Retention is set per deployment. It depends on the data, placement, your configuration, backup design and the agreement that applies.

MS Duplex is in private pilots, and independent certification is planned. Until then, the security brief sets out the controls in place today for the placement you are reviewing.

The providers used for your deployment, and any subprocessor terms, are set out in your customer documents. In your cloud, you choose them.

11 results across cost, accuracy, continual learning, generalisation, planning, agents, security, new skills and adaptation, including three public benchmarks.

A cache replays an earlier answer when a request looks similar. MS Duplex learns the pattern behind confirmed results, follows rule changes from the next request and spots look-alikes, and it can still call your cache as a tool. After a rule change, MS Duplex held 92.5% accuracy where a cache fell to 42.6%.*

Keep it: retrieval becomes one of MS Duplex’s tools. MS Duplex calls it when a step needs a passage, learns which sources answer which questions and knows when a fact has changed.

It becomes a knowledge source for MS Duplex. MS Duplex reads linked facts when a decision needs them, knows when they change and learns which relationships matter for your work.

Yes. Fine-tuned and specialist models become tools MS Duplex routes work to, and MS Duplex can hand your training team confirmed examples when you want to train. Everything MS Duplex learns keeps working beside the new weights.

They become part of how MS Duplex acts. MS Duplex runs every model and tool call under your rules, and your guardrails and firewalls keep enforcing theirs.

An AI gateway routes calls and reports usage. MS Duplex is an intelligence: it learns from every confirmed result, plans, simulates, decides and acts on it, and through MCP + hooks it joins every step of the agents your company builds, with shared learning, continuity, approvals and one history.

Alongside them. Observability shows what your agents did and evals test it; MS Duplex learns from what your team confirms, so a correction applies from the next matching request. Your traces and eval suites keep working as they are.

MS Reflex is the runtime for any machine that decides and acts on its own, from edge devices to robots. It pairs your autonomy stack with an ACI model, on the device: every command passes the gate, and it learns, plans, simulates, decides and acts inside your rules, with or without a connection.

Five invariants, on every machine, whatever runs it. Every command that acts passes the gate. Safety rules loosen only through an authorised, logged act. Every change is attributable and reversible. Learning stays on the device, bounded, with no network. “Unknown” means defer, not guess.

Whatever runs your machine today: a VLA, an MPC, an autopilot, a PLC program or an AI agent. It stays exactly as it is. Your autonomy stack and an ACI model, working as one: that is MS Reflex. The combination is the product.

Both. Edge devices and robots: two shapes, one runtime. Edge devices are the controllers, gateways and smart cameras in plants, on sites and out in the field. Robots are the arms, mobile robots, drones, vehicles and vessels on land, in the air, at sea and under water, and the spacecraft in orbit.

It decides in the moment, on the device: what to do, which skill to run and when to defer. It decides whether each command may pass the gate, and whether it knows enough to act.

Yes. It simulates each move on the device before it makes it, and sees what a command will do before your machine carries it out. A move that would go wrong is changed on the device, before anything moves, and the move it makes still passes the gate.

Every command that acts passes the gate. Before anything moves, switches, opens or sends, MS Reflex checks it against your rules, and what fails does not run. It holds for every command, whatever runs the machine, and every decision at the gate is on record.

“Unknown” means defer, not guess. When it meets something it does not know, it hands the call to your stack or your operator. It never guesses. Every deferral teaches it: what your stack or your operator did next becomes something it knows, for the next time.

It learns fast and on the spot, on the device: one example or one deferral is enough, and the lesson carries to cases like it. It is focused learning, not general learning, inside the bounds you set, with no network and no training run. Your stack stays as it is, and every lesson is on record.

No. Learning never loosens a rule, and neither does time. Loosening one takes an authorised act, and that act is logged. Adding or tightening a rule takes effect from the next command, even while the machine runs.

Yes. Every change to a rule, a limit or what it has learned shows who or what made it, and when. A lesson can be taken back on its own, or a machine returned to a point you saved, and that goes on record too. If a lesson ever cannot be taken back exactly, MS Reflex says so, rather than pretend.

No. It runs on the processors your machines already carry, on CPU, with no GPU and no cloud. It learns, plans, simulates, decides and acts with or without a connection: it works offline and air-gapped, never phones home, and its licence works offline too.

Yes. Each machine runs MS Reflex on the device and decides for itself, with or without a link. Across a fleet, each machine keeps its own rules, and skills move between them only when you choose. A skill learned on one machine can then go to others like it.

No. MS Reflex decides what the machine does next and holds every command to your rules at the gate. It sits above your certified safety controllers, interlocks and emergency stops, never in their place: they stay independent of it and keep the last word, and your team keeps each machine’s safety case, as it does today.

Both, alike, with the same five invariants on every machine. It works with no connection, nothing has to leave the machine, and every decision is on record. In defence, that holds on kinetic and non-kinetic missions alike: every command passes the gate, within your rules of engagement.

MS Reflex is in beta. What it has shown so far comes from simulation and benchmarks, and we prove it with you, on your machines, in a pilot. Each pilot is planned with you, behind your own safety systems.

They are separate products, both built on ACI, Adaptive Continual Intelligence. MS Duplex pairs an ACI model with your AI model, for your AI and your agents. MS Reflex pairs one with your autonomy stack, for any machine that decides and acts on its own.

The product, expected use, team size, placement and any dedicated capacity. Prices come in writing, with the assumptions behind them.

MS Duplex and MS Reflex are products of Vareon, Inc., the company behind matterspace.ai.

Use the contact page and mention the product, placement and kind of work you have in mind. The team will answer the question or point you to the page with the detail.