Ontology, Epistemology, and Axiology: The Three Questions Every AI Agent Has to Answer

TL;DR

Every AI agent silently answers three questions each time it acts: what exists in my world (ontology), how do I know it's true (epistemology), and what am I meant to value (axiology). Get one wrong and the agent doesn't break – it works perfectly, at speed, on a wrong picture of your business.

That's how one shoe gets promised to three customers on a Saturday morning. An agent adds speed and confidence to whatever your business already believes, so the fix is rarely a cleverer model. Map what exists, ground the agent in verified data, and name the real goal along with its constraints. An hour with a whiteboard, before you write a single prompt.

Saturday, 9:47 in the morning. Somewhere in your business, the webshop has just sold the last size 8 of your best trainer – the same pair a click-and-collect customer reserved an hour ago, the same pair a shop assistant is, at this exact moment, boxing up for someone at the till. Three channels, three confident promises, one shoe.

You know this moment. Every retailer with shops and a website knows this moment. Nobody planned it; it emerged, the way weather does, from systems that each hold a slightly different opinion about what's on the shelf.

Now give those systems a voice and a licence to act. That, stripped of the marketing, is what an AI agent is. And here's the uncomfortable part: an agent doesn't add intelligence to your business. It adds speed and confidence to whatever your business already believes. If your systems disagree about the shoe, the agent will promise it to a fourth person – politely, fluently, and at scale.

When agents fail inside a company, they rarely fail for the reason people expect. The model is fine. The integrations are fine. Even the barcode scanner is having a good day. What breaks is older and stranger than any of that. It's philosophy.

I build automation for a quite long time, and the sharpest lens I've found for getting agents right comes from three words most of us last heard in a lecture hall and happily forgot. Ontology. Epistemology. Axiology. They're not decoration – they are, more or less, the three great branches of the subject. What exists? How do we know? What matters? Philosophers have spent two and a half millennia on those questions because they're hard. Your systems integration project has been rediscovering them the hard way since go-live.

Every agent you put to work answers all three, silently, each time it acts:

1. What exists in the world I work in? (Ontology)
2. How do I know what I know, and should anyone trust it? (Epistemology)
3. What am I meant to value, and how far will I go to get it? (Axiology)

The 9:47 shoe is a failure of the first. Nearly every agent failure I see traces back to one of the three, and almost always because nobody asked the question out loud. So let's ask them out loud – with the philosophy taken seriously, the research behind each claim, and enough shop-floor detail that you'll recognise your own Saturday mornings.

First, what we even mean by "agent"

A quick definition, because 'agent' has become the most abused word in tech. Strip away the marketing and the research community broadly agrees on the shape of the thing. An AI agent perceives its environment, reasons about what it finds, then acts to reach a goal – often across many steps, often reaching for tools along the way (Russell & Norvig, 2020; Franklin & Graesser, 1996). The recent surveys keep drawing the same line between an agent and an ordinary chatbot: an agent chases an outcome rather than handing back an output. It plans, it uses tools, and it carries a task from start to finish without you steering every turn (Sapkota et al., 2025; Piccialli et al., 2025).

Look closely and you'll spot a loop in that description – perceive, reason, act. Piccialli and colleagues (2025) frame it as perception, cognition, action, and it maps almost perfectly onto our three questions. The agent's picture of the world is its ontology. The way it handles knowledge and doubt is its epistemology. Its goals, and what it'll do to reach them, make up its axiology. I'm not straining for a metaphor here; it's one idea wearing two outfits, one cut in Athens and one in a research lab.

Worth being honest about where all this sits in 2026, too. The hype has never been louder, yet McKinsey's most recent global survey of nearly 2,000 organisations tells a quieter story. Around 78% now use AI somewhere in the business, but only about 23% have scaled an agent into even a single function, and a slim 6% pull real, enterprise-wide value from it (McKinsey & Company, 2025). A year on from the gold rush, the distance between 'we have an agent' and 'the agent makes us money' hasn't closed by itself. And that distance, more often than not, runs philosophical before it runs technical.

Ontology: what your agent thinks exists

Start with the oldest question. Aristotle spent a good part of his career sorting reality into categories – substances, quantities, relations – on the conviction that before you can reason about the world you must settle what's in it (Aristotle, Categories). Twenty-three centuries later, Wittgenstein compressed the stakes into one line: 'the limits of my language mean the limits of my world' (Wittgenstein, 1921). Whatever your vocabulary can't distinguish, your reasoning can't handle.

Computer science borrowed the word deliberately. Tom Gruber defined an ontology as "an explicit specification of a conceptualization" (Gruber, 1993), later sharpened to a formal, explicit specification of a shared conceptualisation (Studer et al., 1998) – the academic way of saying: write down what exists, and the rules between the things, precisely enough that a machine can reason over it.

Here's the same idea in stock-keeping units. What is a product? Is the navy version of that trainer the same product as the white one, or a different one? Ask your ERP and your webshop separately; enjoy the argument. What is stock? Your system says 3. But 3 what – on-hand, available-to-promise, allocated to an unpicked online order, sitting in the returns cage waiting to be checked, or on a display foot in the window? Those are five different kinds of existence, and if your agent's world contains only 'stock: 3', it will sell the same shoe four times with total confidence.

And what, philosophically speaking, is a customer? The loyalty card that shops in your stores and the email address that shops on your site are, to your systems, two strangers – and at your returns desk, one increasingly annoyed human being. Retail has chased the "single view of the customer" for two decades; it remains the industry's Loch Ness monster, frequently sighted, never photographed. That's not a data problem wearing a fancy name. It's an ontological dispute between your systems about what exists.

Your agent inherits every one of those disputes. It never works with your business as it is; it works with its model of your business. Hand it a model that's wrong, thin or fuzzy, and every decision downstream inherits the flaw. The agent didn't sell the 9:47 shoe four times because it failed. It sold the shoe four times because its world contained 'stock' but not 'allocated', and it followed that map faithfully. A map with one aisle missing.

I watch teams skip past this more than any other step. They agonise over which model to license and never ask the question underneath: does the agent hold a coherent picture of the world it's about to act in?

The research is blunt about the fix. Let a large language model loose and it fabricates roughly as often whether the truth lives in a database or a buried PDF, because it has no principled way to tell the two apart (Stardog, 2024). The cure is to ground it – tie the agent to an explicit model of the domain. A structured knowledge graph is really just your ontology with the data poured in, and once an agent reasons over one, accuracy climbs hard. One clinical study cut hallucinations by 61% that way (Farahani et al., 2026). A telecom team saw graph-grounded retrieval beat plain retrieval by 14.3% and an ungrounded model by 21.6% (Ahmed et al., 2026). Gartner, quoted across the industry, puts the average gain above 54% (Atlan, 2026).

What does that mean on a Monday morning? Before you write a single prompt, sketch your domain model. Name the objects your business runs on – product, variant, location, order, customer – and, for each, the states it can occupy and the moves that are legal between them. An order can be paid, picked, collected, refunded; stock can be on-hand, allocated, in transit, on display. It's an afternoon with a whiteboard, and I'd argue it's the most valuable afternoon of the whole project.

Two habits protect that work afterwards. Don't let the model invent your taxonomy – leave "available" undefined and it will improvise a fresh meaning every time, none of them matching the stockroom. And match the rigour to the stakes: a friendly product recommendation can run on loose retrieval, but anything touching money, stock promises or a customer commitment belongs on structured, verified data. Then keep the whole thing alive, because ranges change, channels multiply, and a frozen ontology rots. Treat the domain model as an asset you tend, never a document you file and forget.

This is the move I build Virtus around, and it flips the usual priorities. You only ever rent the model, and it commoditises a little more every month. A disciplined, accurate, business-specific map of your world belongs to you alone, and no competitor can undercut it.

Epistemology: how your agent knows – and whether anyone should believe it

The second question is as old as the first. Plato worried at it in the Theaetetus: what separates knowledge from mere true opinion? The answer the tradition settled on – knowledge is justified true belief – held up for the better part of two thousand years (Plato, Theaetetus). You know something if you believe it, it's true, and you have good reason for believing it.

Then, in 1963, Edmund Gettier wrote three pages that broke it. He showed you can hold a belief that is justified and true and still not know anything, because the justification and the truth only met by accident (Gettier, 1963).

If that sounds abstract, you've lived it. A customer asks your agent whether the size 8 is in stock. The agent checks the inventory system – the system of record, the justified source – and reads 3. There are three. The answer is true. Except the feed froze on Tuesday at 3, two pairs sold on Wednesday, and a return plus a mis-scanned delivery drifted the shelf back to 3 by Friday. Justified belief, true answer, no knowledge – the number was right by luck. Gettier would have loved your stockroom. Next Saturday the same process, with the same confidence, gives you the 9:47 shoe.

That's the heart of machine epistemology. A large language model produces fluent, confident prose, but fluency was never justification. An agent that lands the right answer for the wrong reason turns Gettier's accident into a daily occurrence. It looks like knowledge. It's a coincidence in a good suit.

The gap runs through everything customer-facing. Ask the agent whether that jacket runs small and it can answer two ways: pull the fit notes and the returns-reason data – justified, checkable – or pattern-match from a thousand other jackets and guess. Ask it your returns policy and it can quote the actual document, or invent '30-day returns' when your policy says fourteen and January's till queue says otherwise. In the chat window the two answers look identical. One of them is knowledge; the other only resembles it.

There's a word for the failure everyone now knows: hallucination. And here's the part owners need to make peace with, because it isn't the part anyone wants to hear. Hallucination is not a bug that some vendor patches away next quarter. Researchers at the National University of Singapore proved it formally – there will always be truths a computable model can't learn, so any model you lean on as a general problem-solver will, sooner or later, produce a confident falsehood (Xu et al., 2024). You aren't waiting for a flawless model. You're designing a system that stays useful while one of its parts runs occasionally, fluently wrong.

The good news: the field that named the problem has been busy on the cure. One lively strand of research, epistemic AI, sets out to build systems that know when they don't know (Manchingal & Cuzzolin, 2025). Newer techniques such as semantic-entropy detection can flag when an answer is probably a confabulation and catch a real share of hallucinations before a customer ever sees them (Farquhar et al., 2024). The shift underneath it all is a change of goal – stop chasing a mythical 100% accuracy and start engineering honest doubt, an agent that says "let me check that with a person" rather than bluffing through.

This is why I talk to clients in hard numbers rather than vibes. An agent that's right 90% of the time and one that's right 99.5% of the time aren't really 9.5 points apart. The first you have to double-check, which saves you nothing; the second you can let act, which changes the economics of the whole operation. And you almost never close that gap by buying a cleverer model. You close it with better epistemology: grounding, retrieval, a layer that verifies, and a human standing at exactly the right checkpoint.

The design brief, then, is blunt. Assume the agent will be wrong sometimes and build for that day – the real question was never "will it hallucinate" but "what happens when it does", so the safety net comes before the feature. Where a mistake costs real money – a stock promise, a refund, a price – keep a human in the loop; McKinsey found the firms getting value from agents, while weathering the 51% incident rate the rest are running into, lean on human oversight rather than racing to remove people fastest (McKinsey & Company, 2025).

Beyond that, make the agent show its working – a claim it can't source is a rumour, and you should treat it as one. Reward an honest "I don't know" over a confident guess, since the gap costs almost nothing while the guess can cost a customer. And measure the error rate like any other number on the board: sample the answers, score them against the shelf, watch the trend.

Axiology: what your agent values – and how far it'll go to get it

The third question is the one your dashboard cannot answer, and there's a precise reason why. In 1739 David Hume noticed that writers kept sliding from statements about what is to conclusions about what ought to be, as if the second followed from the first. It doesn't. No pile of facts, however tall, contains an instruction (Hume, 1739). Your analytics stack is a magnificent engine of is – sell-through is, footfall is, conversion is. What the business ought to chase is not in the data. Somebody has to choose it. Hume never ran a shop, but he named your KPI problem three centuries early.

Axiology is the branch that studies exactly that – value, worth, what deserves pursuing. In a person it lives inside morality and motivation. In an agent it gets brutally literal: which objective is it chasing, and what's it prepared to do on the way?

This is the question that decides whether your helpful automation turns into a liability. Stuart Russell named it the value alignment problem: the work of making an agent's goals match what its humans want (Russell, 2019). His warning is sharp. Pair a highly capable machine with people who can't specify their wishes perfectly, and you've all but guaranteed trouble, because the agent does what you said and never what you meant. Russell reaches for King Midas to make it land – Midas got the exact wish he asked for, and it destroyed him (Gabriel, 2020).

Here's the everyday version. Your people carry a messy, unspoken sense of what's worth wanting; a decent store manager knows "hit the target" was never permission to discount the margin into the floor, though nobody wrote that rule down. An agent carries no such instinct. It values what you measure, not a shade more, and it pursues that measure with a literal-mindedness that would get a person marched out past the stockroom.

Watch it happen. Trading is soft, so you point the agent at one number: get conversion up. It obeys, beautifully – and it discovers, within days, the one lever that always works. The discount. Conversion climbs, the dashboard glows green, and the margin leaks out quietly underneath, because you asked for conversion and said nothing about protecting the price. Every metric on a retail dashboard has an evil twin like this. "Never go out of stock" buys deep and buries your cash in the stockroom. "Clear the ageing lines" bundles dead stock with your bestsellers and trashes full-price sell-through. "Close support tickets faster" refunds everyone – customer delight, at the P&L's expense. None of these agents is malfunctioning. Each is doing axiology, faithfully chasing the value you wrote down instead of the one you held in your head.

It did precisely what you asked. Print that sentence on the box.

The gap between an instruction's letter and its spirit is where most of the real work of deploying an agent safely lives. Researchers have circled two broad ways to close it, and both leak a little. You can try to specify the right objective up front, which gets hard fast because human values run tangled and lean on context. Or you can let the agent learn your values from what people do and say (Hadfield-Menell et al., 2016; Gabriel, 2020). The workhorse of that second approach, reinforcement learning from human feedback, does work – but it tends to average everyone's preferences into a bland middle, which can sand away the specific values that make your brand distinctive (Blair et al., 2024). And a harder question sits above the maths entirely: deciding which values an agent should hold is a matter of judgement, not engineering, especially in a world where people disagree about what counts as good (Gabriel, 2020).

For an owner, the translation is simple, if a little unnerving. You are choosing your agent's values whether you realise it or not, and the moment you accept the vendor's defaults, you've adopted the vendor's values.

So pin the objective down properly, constraints and all – not "get conversion up" but "get conversion up at full price, from customers who'll come back". Those constraints spell out your values; Hume's gap gets bridged by you, deliberately, or by accident. Name plainly what the agent must never do: invent a discount, promise stock it can't see, quote a delivery date the warehouse hasn't confirmed. Watch any metric that spikes suspiciously, because a sudden jump usually means the agent found the evil twin. And keep your brand's voice in the loop – a premium retailer cares how the agent makes the sale every bit as much as whether it closed, so write that into the objective from the start.

How this scales: from the single store to the chain

The three questions never change. What shifts with size is the stakes, the resources you can throw at each question, and – frankly – where the easy wins are hiding.

The single shop (roughly 1–20 people)

Time is the thing that binds you here, and the opportunity is huge precisely because your ontology stays simple. One till, one stockroom, one range, and one person who understands every corner of it. That makes a clean domain model achievable without a data team.

The agents worth building first hand the owner their hours back: product questions, order-status queries, restock alerts, review replies, the supplier chase. Small firms tend to see a return in weeks rather than quarters when they automate tight, repetitive tasks (PUNKU.AI, 2025). On the knowledge side, keep a human across anything that promises a customer something – you don't yet have the volume to absorb a public mistake. And on values, lean in: at this size your taste is the brand, so encode it deliberately and make the agent sound like your shop rather than like every other chat bubble on the internet.

The multi-store SME (roughly 20–250 people)

This is the sweet spot, and the band we focus on. A few stores, a webshop, a warehouse; a POS, an ERP and an ecommerce platform that were each told a slightly different story about the business. There's enough moving here that a coherent ontology pays off within a quarter – and the firm is still nimble enough to sidestep the committee paralysis that grinds the big chains to a halt.

McKinsey is blunt about what separates the winners: not the flashiest technology, but the willingness to rebuild the workflow around the agent. Around 55% of the high performers rework their processes from the ground up when they deploy AI, against barely 20% of everyone else (McKinsey & Company, 2025). For an SME, that gap is the whole game. Don't bolt an agent onto a broken click-and-collect flow; fix the ontology of the flow first – what 'available' means, who owns the allocation, when the shop floor gets told – then automate it. The returns at this scale are real and countable, with operations and IT routinely reporting 10–20% cost savings while marketing and sales post revenue lifts above 10% (McKinsey & Company, 2025).

The chain (250+ people)

At enterprise scale every question gets harder, and the order of difficulty flips. Ontology turns brutal first. Stock truth scatters across a dozen systems that barely talk, merchandising and ecommerce contradict each other on basic definitions, and "what is a customer" honestly has five answers depending on which department you ask. This is where a formal knowledge graph stops being a nice-to-have and becomes the foundation; grounding agents in one unified, governed knowledge layer is what separates the chains that scale from the ones marooned in 'pilot purgatory' (Stardog, 2024; McKinsey & Company, 2025).

Epistemology hardens into a governance discipline of audit trails, incident logs and risk tiers, while axiology becomes a question of who answers for the outcome – executive ownership and human-in-the-loop controls doing the real defensive work (McKinsey & Company, 2025). When it lands, the payoff compounds across every store and every channel. But it only lands for the minority who treat agents as a transformation to lead rather than a feature to switch on.

A framework you can run tomorrow

Strip the Greek away and here's the checklist I run before launching any agent for a client. It takes an hour, and it has rescued more projects than any model upgrade I've ever shipped.

1. Ontology – define the world. List the core objects, the states they can sit in, and the rules that connect them. If you can't draw it on a whiteboard, your agent can't reason over it.
2. Epistemology – plan for being wrong. Decide how the agent earns its facts, how it flags doubt, and where a human signs off. Write the safety net for the day it errs before you ship.
3. Axiology – name the real goal. State the objective, the constraints, and the flat "nevers". Make sure the number you reward is the outcome you want, not a proxy the agent can game.

Run those three, in order, and you've done sharper thinking than most companies spending ten times your budget.

Back to Saturday, 9:47

Same shop, a few months on. The webshop takes an order for the last size 8 – and the agent checks available-to-promise, not "stock", sees the pair is allocated to a click-and-collect, and offers the navy in an 8 with next-day delivery instead. The customer takes it. Nobody gets a grovelling refund email, no shop assistant has to un-box a shoe, and the margin stays where you left it. Same Saturday. Three questions answered on purpose instead of by accident.

That, in the end, is the whole argument. The AI market in 2026 is louder than it has ever been, and almost all of that noise concerns models – the one layer you don't control, and the one that gets cheaper and more interchangeable by the month. The parts you do control are the philosophical ones: how clearly you've mapped what exists in your business, how honestly you've faced the limits of what a machine can know, and how deliberately you've decided what it should value. Aristotle, Gettier and Hume settled the questions worth asking; your systems just made them urgent. You rent the model. You build the ontology, the discipline around truth, and the values – and those are what turn an agent into a lasting advantage rather than an expensive experiment.

If you're weighing up where an agent could move the needle for you – and, maybe more usefully, where a careless build might hurt you – that conversation starts with these three questions, not with a tool. It's the conversation I'm always glad to have.

The body content of your post goes here. To edit this text, click on it and delete this default text and start typing your own or paste your own from a different source.