Adaptive Continual Intelligence.
A new category of intelligence.
ACI learns from your work as it happens, plans, simulates, decides and acts within your rules, and what it learns is yours. Paired with your AI model, it is Duplex. Paired with your autonomy stack, it is Reflex.
What ACI is.
ACI is intelligence that keeps learning, planning, simulating, deciding and acting while your work happens. It carries everything it learned and decided forward, and works in tandem with the AI models you already use.
Step 1 of 6: What ACI is
Three words, three behaviours.
Adaptive Continual Intelligence: each word names something ACI does for your work.
- Adaptive
- It fits itself to your work, and to every change in it.
- Continual
- It keeps learning for as long as it runs, and builds on what came before.
- Intelligence
- It generalises, plans, simulates, decides, acts and acquires skills, within your rules.
Step 1 of 3: Adaptive
Adaptive: ACI starts from what your team knows, and a correction changes the next answer.
The trilemma of neural nets.
ACI is the result of years of research into neural nets and their trilemma: plasticity, stability and editability. Learn fast, keep what it knows, or let you change what it learned: a neural net gets two at best. ACI holds all three.
Plasticity: a neural net that learns fast overwrites what it knew. Researchers call it catastrophic forgetting.
Step 1 of 5: Plasticity
Plasticity
Learn the new, fast.
- In a neural net
- A network that learns fast overwrites what it knew. Researchers call it catastrophic forgetting.
- With ACI
- ACI learns from a single confirmed result, and the very next request has it.
Stability
Keep what it knows.
- In a neural net
- Hold a network steady and it keeps what it knows, but it stops learning.
- With ACI
- ACI goes on learning, and everything it learned before stays exactly as it was, for as long as it runs.
Editability
Change what it learned.
- In a neural net
- What a network learned is spread through all of it, so one thing can’t be corrected or removed without retraining.
- With ACI
- Anything ACI learned can be reviewed, corrected or removed on its own, and the rest stays as it was.
Holding all three is what lets ACI learn, plan, simulate, decide and act at runtime, from your work, for as long as it runs. It is what makes ACI a new category of intelligence.
Intelligence, not retrieval.
RAG, vector databases, knowledge graphs, caches and memory store what happened and find what looks like it. Duplex learns: it understands the pattern behind each result, compresses it into what generalises, predicts what comes next, and acts on it.
When a request only looks familiar, retrieval returns the nearest match. Duplex understands the pattern, and sees the difference.
Step 1 of 5: A look-alike
- 01
It understands
The pattern behind a result: why it worked, and where it applies.
- 02
It compresses
What it learned into what generalises, so it gets faster and leaner with use.
- 03
It predicts
What comes next, from everything your work has taught it.
- 04
It acts
On what it learned, at runtime, within your rules.
A new category of intelligence.
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.
Step 1 of 4: When it learns
A model learns before it is released. ACI learns every day it runs.
In tandem with AI models.
Your AI model brings general intelligence, learned from the world. ACI brings Adaptive Continual Intelligence, learned from your work. Together they do what neither does alone.
Step 1 of 4: Learned from
Your model learned from the world. ACI learns from your work.
What ACI unlocks.
With ACI, your AI learns on the spot, plans, simulates, decides and acts on what it learned, keeps up with every change, gets faster and cheaper with use, and what it learns is yours.
Learning on the spot
Confirm a result once, and the very next answer reflects it, with no training run and no new version to wait for.
0%*Stale answers after a policy change
Current with every change
Change a rule, and ACI follows it from the next request, while everything else it learned stays as it was.
92.5%*Right on the decisions a rule change affected
Faster and cheaper with use
Work it has learned is answered in milliseconds with no model call, so the more it learns, the less each request costs.
−84.8%*Cost, with accuracy up
It knows what it knows
It answers what it has learned, and brings in your model, briefed, when a case is new.
Cases it has never seen
It learns the pattern behind a result, so it handles a new case and tells a look-alike apart.
Skills of its own
It acquires new skills from your work, tests each one before use, and removes it on request.
Intelligence you own
Everything it learns belongs to you, and you can see where it came from: review it, correct it or remove it.
Carried to any model
Move to another model, agent or app, and what ACI learned comes with you.
0*Retraining to move to another model family
Why ACI matters.
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.
Step 1 of 4: Who could
Until now, only the labs that train models could make AI learn. With ACI, every person and company can.
Duplex is built on ACI.
Duplex pairs an ACI model with your AI model, and the combination is the product: everything Duplex learns, plans, simulates, decides and does at runtime is ACI at work. Duplex brings it into the assistants your team uses, and into the agents your company builds through MCP + hooks.
ACI is the intelligence that adapts. Duplex is the product that pairs it with your AI: the decisions, the governance, the ways in, and the life of everything it learns.
Duplex
The product you useDuplex works inside the assistants your team uses and inside the agents your company builds. It starts informed, decides the route, acts within your rules and carries its decisions, its learning and your context forward.
- Inside your assistants
- Inside your own agents
- Within your rules
- In the placement you choose
ACI
The intelligence in DuplexIt learns, plans, simulates, decides and acts while the work happens, leaves your model’s weights alone, and everything it learns belongs to you.
- Learns from every result
- Acts within your rules
- Keeps up with every change
- Yours, wherever you work
Three essays on ACI.
What makes it new, what it makes possible, and why it matters.
Where training ends, ACI begins.
For you if your AI is as good today as the day it was released, whatever your team has taught it since.
Read the essay →5 min readWhat becomes possible when your AI keeps learning.
For you if you want to know what ACI changes in a working week, request by request.
Read the essay →4 min readAI that learns, for everyone.
For you if you want to know why ACI matters beyond the next request, for your company and for AI.
Read the essay →4 min read
One language, defined once.
The words for ACI and Duplex, each in one sentence.
Step 1 of 5: Owned
Your AI is rented intelligence, paid by the call; what Duplex learns from your work is owned intelligence.
Owned intelligence
What Duplex learns from your work: decisions, corrections, routes and context. It stays in your boundary and goes wherever you work.
Rented intelligence
An AI you pay for by the call. Brilliant and general, and unchanged by anything your team confirms.
Complementary learning system
Your AI and an ACI model together, two intelligences in one system, and that system is Duplex: general intelligence, learned slowly, and runtime intelligence that learns fast, plans, simulates, decides and acts, like the neocortex and the hippocampus.
General intelligence
What your AI brings: knowledge, language and reasoning, learned slowly before you arrived.
Runtime intelligence
What the ACI model in Duplex brings: a second intelligence beside your model that learns, plans, simulates, decides and acts while the work happens. It starts informed, chooses the route, plans the steps, simulates each one, acts within your rules, acquires skills, learns from every result and carries its decisions, its learning and your context forward.
Confirmed result
What Duplex learns from: a test passed, a review approved, a correction accepted, an outcome observed.
Provenance
Where each thing Duplex learned came from: which agent, with which model, and when.
ACI
Adaptive Continual Intelligence: a new category of intelligence that learns, plans, simulates, decides and acts at runtime, in tandem with AI models, and the result of years of research into the trilemma of neural nets. Duplex is built on it.
The trilemma of neural nets
Plasticity, stability and editability: learn fast, keep what it knows, and let you change what it learned. A neural net gets two at best. ACI holds all three.
Learning
What Duplex does with every result: it understands the pattern, compresses it into what generalises and predicts what comes next. Retrieval only finds what looks similar.
In tandem
How ACI works with AI models: the model brings general intelligence, ACI brings what your work has taught it, and each takes the work it does best.
Duplex
The product: the runtime intelligence for your AI and your agents, built on ACI. It works inside the assistants you use and inside the agents your company builds.
Plugins
Duplex inside Claude, Codex, Cursor and Hermes, through MCP. The assistant brings Duplex in at each step. It builds your personal intelligence.
MCP + hooks
Duplex inside the agents your company builds. They connect through MCP, and the hooks bring Duplex in at every step, before each action runs. It builds your company intelligence.
Placement
Where Duplex runs: Vareon Cloud or your cloud. The product is the same in both.
Questions about ACI.
Give your AI an intelligence that learns, plans, simulates, decides and acts.
Duplex is built on ACI, Adaptive Continual Intelligence: a new category of intelligence that learns, plans, simulates, decides and acts at runtime, in tandem with AI models.