IMITATION/AI
Intelligence Engineered
Our Approach
Where does AI become differentiating intelligence?
You can give AI access to documented processes, policies, playbooks and case studies. But information alone does not make an AI intelligent.
Real intelligence sits in how experts think.
It is found in the judgement they apply when the answer is not obvious. In the patterns they recognise before anyone else. In the exceptions they know how to handle. In the language they use, the questions they ask, the trade-offs they make, and the instincts they have developed through years of experience.
Much of this knowledge is tacit. It sits beneath the surface in experience, intuition, behaviour and context. It may never have been written down. It may not even be fully conscious to the person using it.
Imitation AI exists to capture that intelligence and make it usable by AI.
We combine expertise capture, linguistic engineering and AI evaluation to extract how experts think, structure it into usable intelligence, and test whether an AI can consistently act within the right boundaries.
This means going beyond prompts and process automation. We engineer the language, reasoning patterns, behavioural rules and decision heuristics that allow AI to carry forward a way of thinking.
The result is AI that does more than follow instructions.
It can reflect the judgement, nuance and expertise that make an organisation, team or individual genuinely differentiated.
Imitation AI.
Intelligence Engineered.
Microsona™
Microsona™ is designed for individual experts and single operators.
It helps professionals such as personal trainers, tutors, counsellors, coaches and consultants capture the way they think, advise and support their clients.
The goal is not to replace the expert. It is to extend their presence, make their expertise more accessible, and create AI experiences that reflect their real style, judgement and approach.
Microsona™ turns individual expertise into a usable AI persona that can support clients, answer questions, guide decisions and carry the expert’s method into more interactions.
What we offer
Macrosona™
Macrosona™ is built for enterprises that need to capture and preserve the intelligence of their workforce.
Every organisation depends on people who know how things really work. The experienced colleague who understands the customer. The technical specialist who knows where the risks are. The sales leader who knows how to position the offer. The operator who knows the shortcuts that never made it into the process document.
Marcosona™ helps organisations capture this hidden intelligence before it is lost, scattered or trapped in isolated teams.
It is designed to learn from experts, conversations, decisions, documents and working patterns, then distil that knowledge into AI-usable intelligence. This creates organisational memory that can be reused, tested, improved and applied across the business.
Intelligence Capture Consulting
Our consulting work helps businesses design and implement intelligence capture strategies.
We support organisations that want to move beyond generic AI adoption and build systems that reflect their own expertise, culture, operating model and competitive advantage.
This includes identifying where intelligence sits in the business, deciding what should be captured, designing the right AI architecture, creating evaluation approaches, and helping teams move from experimentation to practical deployment.
We work with organisations to make AI useful, grounded and specific to how they actually create value.
AI Strategy Consulting
We help organisations turn what they know into intelligence they can use, scale and sell.
By uncovering the expertise, heuristics, judgement and tacit knowledge behind high-performing people and processes, we identify where intelligence can be engineered into new products, services and organisational capabilities. From AI strategy, use-case prioritisation and operating-model design through to prototyping, proposition development, sales strategy and go-to-market execution, we provide the practical direction needed to move from an intelligent idea to real adoption and commercial value.
Book Preview: Embracing the Curiosity Economy - How human judgment, experience, and curiosity become your greatest assets in the age of AI.
What happens when the delta between idea and execution disappears?
For most of our working lives, value has been tied to what we know how to do. The software we can operate. The processes we understand. The qualifications we have earned. The experience we have accumulated.
AI changes that.
As technology becomes capable of translating intention into action, the advantage shifts. Knowing which buttons to press matters less when you can simply describe the outcome you want. Expertise doesn't disappear, but our relationship with it changes.
Suddenly, work becomes the question.
Embracing the Curiosity Economy explores what happens when curiosity moves from being a personality trait to becoming one of the most important skills in work.
How do we become more curious people? How do leaders create organisations where curiosity is encouraged rather than engineered out? And what should education, careers and opportunity look like when knowing how to use today's tools is no longer enough preparation for tomorrow?
This isn't a book about becoming better at AI.
It's about what AI gives us permission to become better at.
In a world where execution is increasingly abundant, expertise accessible and technology democratised, what remains scarce is our ability to imagine what might be possible, recognise what doesn't make sense, ask a better question and remain curious enough to follow where it leads.
The organisation is no longer limited by technology. It's limited by the questions it asks.
Welcome to the Curiosity Economy.
Latest Paper: Cognitive bias as a prompt-level behavioural setting for LLMs
Building from Philosophical hyperparameters, I supervised the research of Vladyslav Fridmo, in his MSc dissertation, Cognitive bias as a prompt-level behavioural setting for LLMs looks at how explicitly injecting biased instructions into the prompt can enact and control certain behavioural characteristics
The project investigates a new approach to steering Large Language Model (LLM) behaviour by using cognitive bias as an explicit prompt-level behavioural setting. The aim is to determine whether deliberately induced cognitive biases can reliably influence LLM responses. A central challenge lies in isolating and quantifying these effects, as model randomness and prompt sensitivity can obscure or mimic the intended steering.
The project was carried out as an experimental study using models from two major commercial LLM providers. Ten cognitive biases were organised into opposing pairs to test whether behaviour could be steered both with and against existing model tendencies. Repeated sampling and controlled test variation were used to reduce the influence of unrelated variability. The analysis examined the direction, strength and consistency of the resulting behavioural shifts across the tested conditions.
Latest Paper: Philosophical Hyperparameters, Grounding LLMs via Configurable Ethical and Philosophical Frameworks
Today’s AI systems behave—but they don’t believe.
Their alignment is reactive, shaped by post-hoc constraints and surface-level safety tuning rather than stable, principled grounding.
Philosophical Hyperparameters introduces a new approach to AI alignment, treating ethical and philosophical frameworks not as abstract guidance, but as configurable control parameters for behaviour. Instead of training models toward a single, risk-averse norm, the paper demonstrates how large language models can be grounded in explicit ethical worldviews that act as a moral operating system.
The paper presents a proof-of-concept system in which LLMs are configured with 55 distinct philosophical frameworks, spanning classical ethics, religious traditions, and modern meta-ethical positions. Each configuration is evaluated across 20 complex dilemmas and quantitatively measured along 11 behavioural axes, including harm avoidance, risk appetite, autonomy, rule adherence, and collective good orientation. This produces a multidimensional behavioural signature for each framework, allowing alignment to be measured, compared, and audited rather than assumed.
The results show that LLMs can exhibit deep, coherent, and repeatable behavioural alignment when grounded in explicit philosophical convictions. These behaviours cluster into a small number of emergent moral regimes—such as harm-minimisation absolutism, risk-on activation, and rule-bound legalism—revealing a new design space for controllable, interpretable AI behaviour. The work reframes alignment as configuration rather than constraint, offering a path toward AI systems whose decisions are transparent, intentional, and anchored in known ethical postures rather than opaque optimisation pressures.
Cognitive Geometry for Agentic Memory Systems: Bridging Neural Correlation and Symbolic Reasoning
Today’s AI systems remember—but they don’t think.
Their memories function as static repositories, not dynamic structures of understanding.
Cognitive Geometry in Memory Systems introduces a new way to design memory for AI—one that transforms information into reasoning. The paper presents a four-layer cognitive memory model that maps different types of knowledge to unique geometries:
Facts → Knowledge Webs: semantic graphs that enable deep associative recall.
Experiences → Semantic Temporal Knowledge Webs: time-indexed graphs that preserve sequence, context, and meaning.
Procedures → Causal Trees: hierarchical chains of cause, effect, and subgoal.
Personalisation → Forests of Knowledge Trees: adaptive, individualised reasoning spaces.
This geometry creates a bridge between neural memory (pattern-based learning) and symbolic memory (logic-based reasoning)—allowing systems to store, transform, and reason over knowledge dynamically.
The result is a neuro-symbolic substrate that tackles long-standing LLM challenges: catastrophic forgetting, weak interpretability, and the inability to learn continuously. It reframes memory as the cognitive engine of agentic AI.
How can we help you scale intelligence?
Whether you have a question, an idea, or just want to say hello, feel free to reach out—we’re here to help.