Slow travel down an aisle of server racks

MA Duplex / The adaptive runtime for AI agents

Rent the model. Own the intelligence.

MA Duplex sits in front of any frontier model, learns from every answer it gets and serves what it knows on its own. Your agents get more accurate, more governed and cheaper with every turn.

16 pts

Over fine-tuning

89%

Fewer model calls

0

Training runs

01 / Why a runtime

Why agents need a runtime.

An agent that calls a model for every decision pays for every decision, forever, and learns nothing your company keeps. An agent in operations also has to be bounded: every turn authorized, every action on record. MA Duplex gives agents both.

A data center campus at night, seen from the air

02 / Day one

What changes on day one.

An empty office at night, screens glowing over the city
  1. 01

    Point your agents at it.

    MA Duplex speaks the OpenAI and Anthropic APIs your code already uses. Change the address, not the code.

  2. 02

    It asks, then it learns.

    The first time it meets a task it asks the model and learns the answer.

  3. 03

    Every turn governed.

    From the first request, every turn is authorized and every action goes on record.

  4. 04

    Nothing to train.

    No dataset, no GPU hours, no checkpoint to ship.

03 / Cost inversion

The more it works, the less it costs.

The first time it meets a task it asks the model and learns the answer. From then on it serves that decision itself, in milliseconds.

On repeated work it cut model calls by 89% while getting more answers right than a fine-tuned model. Of the 303,176 answers it gave on its own, 99.9% were correct.

Fiber cables running into a lit server rack

11,207

Model calls in 100,000 requests

99.9%

Of its own answers correct

10 of 10

Runs ahead

04 / Learning without training

Accuracy above fine-tuning. Zero training runs.

Fine-tuning means datasets, GPU hours, checkpoints and a model that starts aging the day it ships. MA Duplex learns from live work, one example at a time. On a public benchmark it reached 91.9% with no training run, against 85.8% for a fine-tuned model and 71.3% for the model alone. On repeated work: 98.6%.

Fiber cables running into a lit server rack

91.9%

On a public benchmark, with no training run

85.8%

Fine-tuned model

98.6%

On repeated work

05 / Always current

Change a fact once. Every answer follows.

Across 20,160 answers through every kind of update, it gave zero stale answers. Standard retrieval gave stale ones 57% of the time.

0%

Stale answers, against 57% for standard retrieval

0 of 8,640

Changed facts answered the old way

100%

Of deleted facts kept out

06 / Governed turns

Every turn authorized. Every rule enforced.

Each turn passes one gate before anything reaches a model or a tool. Rules hold on what a request means, not only on how it is worded, and every action is written to a tamper-evident record your auditors can verify.

A restrained control-room settingA restrained control-room setting

07 / Reversible

Unlearn anything, exactly.

Any lesson can be removed on request, and MA Duplex returns precisely to the state it was in before it learned it. Nothing else is disturbed. Every change is on record.

08 / Your stack

Works with the stack you already run.

A data center campus from the air, fiber in a server rack, a server hall, a cooling plant and an office at night
  1. 01

    Any frontier model.

    Swap it tomorrow without losing what was learned.

  2. 02

    Drop-in endpoints.

    OpenAI and Anthropic compatible, and usable from LangChain.

  3. 03

    SDKs, a command line and an HTTP API.

    Python and TypeScript.

  4. 04

    Your memory, graph and tools.

    It works with the knowledge and tools your agents already use.

  5. 05

    Your cloud, your premises or managed for you.

    In your own cloud account, on your premises, or in a separate environment operated by Machine Autonomy.

  6. 06

    Offline development.

    It runs end to end offline, with no API keys. Many agents and multi-step workflows pass through the same gate.

Integrations

09 / For operators

What operators get.

An operations floor with screens, wide and quietAn operations floor with screens, wide and quiet
  1. 01

    A record auditors can verify.

    Every turn and every action, tamper-evident and retrievable by API.

  2. 02

    Rules that hold.

    Each turn passes one gate before anything reaches a model or a tool.

  3. 03

    Facts that stay current.

    Change a fact once and every answer follows. Delete one and it stays deleted.

  4. 04

    Keys, scopes and quotas.

    For every team, with usage, in one console.

10 / Where it runs

Its own environment. Or yours.

Each customer gets a separate MA Duplex environment, operated and managed by Machine Autonomy. Or run it in your own cloud account, on your premises or fully air-gapped. Your data and what it learns stay where you decide.

  • A separate environment for each customer, managed for you
  • Your cloud account
  • Your premises
  • Air-gapped
Pipes and pumps in a data center cooling plant

11 / What it costs to run

The bill falls as the volume grows.

Every answer MA Duplex has learned is served without a model call, in milliseconds. The savings grow with volume from day one, and nothing is spent on training.

89%

Fewer model calls on repeated work

59%

Of requests on a public benchmark answered with no model call

0

Training runs, datasets or GPU hours

12 / How a pilot runs

How a pilot runs.

A data center exterior at nightA data center exterior at night
  1. 01

    Your own traffic

    MA Duplex goes in front of the model you use today, on real requests.

  2. 02

    Your rules

    Policies and limits set before the first turn.

  3. 03

    Measure it

    Accuracy, model calls and every turn, on record.

  4. 04

    Roll it out

    For your agents, in our environment, your cloud or your premises.

Partners

13 / Where it pays off

Where it pays off.

  1. 01

    Customer support

    Accuracy that grows every day and a model bill that shrinks.

  2. 02

    Operations

    Tickets, orders and requests at volume, every decision governed and on record.

  3. 03

    Finance and compliance

    Decisions that follow the latest rule the moment it changes.

  4. 04

    Agents and copilots

    Tool choices and routing served in milliseconds.

Enterprise AI and data centers

14 / Proof

Ahead of fine-tuning, without fine-tuning.

Repeated work

98.6% accurate, 16 points above a fine-tuned model.

  • MA Duplex98.6%
  • Fine-tuned model82.6%
  • Model alone66.8%

Nine requests in ten repeating, across 2.4 million decisions. 89% fewer model calls.

Public benchmark

Beats fine-tuning on a public benchmark, with no training run.

  • MA Duplex91.9%
  • Fine-tuned model85.8%
  • Model alone71.3%

59% of requests answered with no model call, 99.6% of them correctly.

Knowledge updates

Lower is better

Zero stale answers through every kind of update.

  • MA Duplex0%
  • Standard RAG57%

Stale answers across 20,160 answers in 360 knowledge families.

Output rules

Fine-tuned accuracy on strict output rules, without fine-tuning.

  • MA Duplex98.1%
  • Fine-tuned model97.7%
  • Model alone96.2%

Answers that met every output rule. Zero training runs.

Every result

15 / Questions

Questions.

  • Does MA Duplex replace my model?

    No. It sits in front of it. Your model handles what is new, MA Duplex handles what it has learned.

  • What changes in our code?

    Very little. Point your agents at MA Duplex instead of the model. It speaks the OpenAI and Anthropic APIs.

  • Do I need training data?

    No. It learns from live work, one example at a time, and from the corrections your team makes.

  • What happens the first time it sees a task?

    It asks the model, returns the answer and learns it. The next time, it can answer on its own.

  • How quickly does it pay off?

    From the first repeat.

  • Can we change models later?

    Yes. Swap the model without losing what was learned.

  • Where does it run?

    In its own environment, operated and managed by Machine Autonomy, or in your cloud account, on your premises or air-gapped. Your data and what it learns stay where you decide.

  • Can developers work offline?

    Yes. It runs end to end offline for development, with no API keys.

  • Can it forget something?

    Yes, exactly, with the change on record.

  • How do we get it?

    Machine Autonomy offers MA Duplex to enterprises and to teams building agents.

    Partners
A data center exterior at nightA data center exterior at night

Own the intelligence your agents create.

Run MA Duplex on your own traffic and watch accuracy rise while the model bill falls.