Skip to main content

Product: Workforce Ontology

software-eating-the-world

Intent Engineering: Software Was Never the Point

Written by Eric Macfarlane on .

software-eating-the-world

For thirty years, durable software was the only path to the outcomes organizations wanted — so we built it, maintained it, migrated it, and kept feeding it. Most enterprises now spend 60–80% of their IT budgets just sustaining systems that already exist, leaving twenty cents on the dollar for anything new. The machine developed an appetite — and a whole services ecosystem to keep it fed.

AI is being sold as a way to build software faster. That’s true, and it’s the least interesting part. The real shift: when AI can assemble software on demand to serve a specific outcome and dissolve it when the moment passes, software stops needing to be durable. It becomes temporal — built for the moment, gone when the moment ends. The question that’s haunted every technology budget for thirty years finally has an answer: it stops when the moment passes.

But temporal software needs a venue — a durable, governed foundation of organizational knowledge, ontology, and intelligent infrastructure that every temporary application inherits. Most organizations are deploying AI without one. They’re booking events without a venue. The engineers who matter most in this model aren’t building applications — they’re building the venue. We call them intent engineers.

Read the Full Article
Diagram contrasting AI agents rediscovering context on every run versus operating against structured, executable enterprise knowledge to reduce token consumption.

From Tokenmaxxing to Skills Intelligence: Why AI’s Real Cost Isn’t Compute — It’s Context

Written by Eric Macfarlane on .

Diagram contrasting AI agents rediscovering context on every run versus operating against structured, executable enterprise knowledge to reduce token consumption.

AI spend is climbing faster than anyone budgeted — and the industry is blaming usage. That’s the wrong target. AI gets expensive when it runs without understanding the work, forcing agents to rediscover context on every run. Liz Eversoll and Joe Shepherd break down why context is the new advantage, and how encoding knowledge in SIGN cut token consumption by half.

Read the Full Article
Diagram contrasting AI agents rediscovering context on every run versus operating against structured, executable enterprise knowledge to reduce token consumption.

From Tokenmaxxing to Skills Intelligence: Why AI’s Real Cost Isn’t Compute — It’s Context

Written by Liz Eversoll on . Posted in Explainable AI, Skills-Based Organization, Workforce Development.

By Liz Eversoll, CEO, and Joe Shepherd, CPO — Career Highways

Over the last month, two stories have surfaced in the AI market.  On the surface they look unrelated.  Read together, they expose the same problem.

The first is cost.  Reports from Microsoft, Uber, and other large adopters show AI usage costs climbing faster than anyone budgeted.  Uber’s CTO told The Information the company burned through its entire 2026 AI coding budget in four months.  The cost per token keeps falling, but total spend rises as usage scales — and Goldman Sachs projects agentic AI will drive a 24-fold increase in token consumption by 2030.  Cheaper to use, more expensive to operate.

The second is behavior.  Engineers at major technology companies have been encouraged — sometimes incentivized through internal leaderboards — to maximize token consumption as a proxy for AI adoption and productivity.  The practice has a name now: tokenmaxxing.  Cognizant CEO Ravi Kumar S. recently called it what it is: a vanity metric.

Both stories are being framed as an AI cost problem.  They are actually exposing something larger.  AI does not get expensive because you use too much of it.  It gets expensive when it runs without understanding the work — and without structured knowledge to operate against.

If you own the AI bill — and increasingly that is the CTO — this is the distinction that matters.  Cost is exploding and usage is exploding, and your CFO and CEO can see both.  What they want to know is whether it can be controlled.  It can.  But not by capping usage.  By fixing what the usage is spent on.

The Wrong Metric

For decades, companies measured labor utilization.  Now many are measuring AI utilization.  Neither tells you whether value is being created.

Token consumption is simply the latest case of Goodhart’s Law: when a measure becomes a target, it stops being a good measure.  More prompts, more agents, and more AI calls do not necessarily produce better decisions, better products, or better outcomes.

The real problem is not that organizations use too much AI.  It is that most cannot say what work should be done by people, what should be augmented by AI, and what should be automated outright.  Without that understanding, you optimize for activity — and activity, billed by the token, is expensive.

Context Is the New Advantage

Here is what the cost narrative misses.  AI is expanding access to problem-solving across the entire workforce.  People no longer need years of specialized training to analyze data, build a workflow, generate a solution, or ship working software.  The barrier to participation has dropped.

As access to answers goes up, something else becomes scarce and valuable: context.  Understanding the business problem.  Understanding how the work actually gets done.  Knowing what a good outcome looks like — and how to tell whether the AI produced one.  A model can generate an answer.  It cannot reliably tell you whether you are solving the right problem.

This is why a company like Cognizant is expanding hiring beyond traditional technical backgrounds.  Value is shifting toward people who understand the business, the customer, and the workflow — not only the technology.  AI widens who can participate; context determines who creates value.  The question is no longer who can perform the work.  It is who can frame the right problem, validate the solution, and put it into production.  Those are skills.

From Skills to Execution

Understanding the work, and the skills behind it, is the first step.  Most organizations still lack a systematic way to define that work, map the skills it requires, and apply that consistently across the enterprise.  That is the gap Career Highways closes — identifying the work that actually exists, defining the skills required to perform it, and connecting those skills to roles, workflows, and outcomes.  The result is a system of record for capability: what work needs to be done, and who can do it.

But a second constraint shows up the moment you try to operationalize it.  Even when the work and the skills are defined, AI still struggles to use that knowledge efficiently.

Why AI Keeps Rediscovering What You Already Know

Most enterprise knowledge already exists — policies, frameworks, data models, domain definitions.  It is just not structured in a way AI can reliably apply.  Documents describe intent but cannot enforce it.  Data may be structured, but the relationships and constraints that govern how it behaves are not.  Prompts try to fill the gap, and introduce inconsistency every time.

So agents retrieve information, but they do not apply it systematically.  They infer, approximate, and reinterpret the same logic on every run.  That is what drives both inconsistency and cost.  AI is expensive precisely because it has to rediscover context every time it runs.

Introducing SIGN

At Career Highways, we built SIGN (Sigil Intelligence Graph Notation) to solve exactly this.  SIGN is an open standard for expressing enterprise knowledge in a form agents can read, reason over, and act on — consistently, and with governance.

If JSON serializes data, SIGN makes knowledge executable.  More simply: SIGN is the Rosetta Stone of agentic knowledge — it unlocks the institutional knowledge an organization already holds, in a form every agent can read, apply, and be held accountable to.

It separates what is defined from how it is executed, so knowledge can be reused and enforced consistently across systems.  Instead of describing rules in prose or burying them in code, SIGN encodes them directly into the knowledge layer — defining what is true, what must be enforced, and how decisions are made.

“AI systems today spend most of their time reconstructing context that already exists in the enterprise.  SIGN flips that model.  It makes the knowledge itself executable, so agents don’t have to guess — they operate against defined logic.”  — Joe Shepherd, Chief Product Officer, Career Highways, and inventor of SIGN.

Why This Changes the Cost Equation

The AI cost problem is not only about scale.  It is about how inefficiently knowledge is represented and applied.  Most enterprise formats force AI to do unnecessary work — JSON adds structure without meaning, documents demand heavy context to interpret, prompts recreate the same logic over and over.  The result is longer prompts, repeated reasoning, inconsistent outputs, and higher token consumption.

SIGN removes that inefficiency by encoding meaning directly.  Rules, constraints, and inference logic are defined once and applied consistently — so AI executes against known logic instead of inferring what it should already know.

From Probabilistic Guessing to Deterministic Execution

In most systems today, reasoning is left to the model.  Because large language models are probabilistic, rules get applied inconsistently, constraints get missed, and outputs vary from run to run.

SIGN moves that responsibility out of the model and into the knowledge layer.  It defines what must happen, what cannot happen, and how conclusions are derived — so agents operate with governed logic instead of inference.  The result is a shift from probabilistic output to deterministic decisioning: ask the same question, get the same answer.

The Impact: Fewer Tokens, Better Outcomes

When knowledge is structured and executable, AI no longer has to reconstruct context or reinterpret logic.  Prompts get shorter.  Workflows become reusable.  Outputs become consistent.

We have measured this in our own platform.  Encoding our knowledge in SIGN cut our token consumption by roughly half for the same work.  Same knowledge.  Half the tokens.  Deterministic results.

The Bottom Line

The debate about AI costs is real — but most of it is aimed at the wrong problem.  AI does not get expensive because it is used too much.  It gets expensive when it is used without understanding the work, and without structured knowledge to operate against.

Career Highways defines the work and the skills.  SIGN makes that knowledge executable — so AI can operate with precision instead of guesswork.

For the CTO, the first move is small and measurable: take one high-cost agentic workflow, encode the knowledge that governs it in SIGN, and watch the token count.  Stop tokenmaxxing.  Start work-maxxing.  That is how AI stops being a cost and becomes a capability.

Sources

  • “The Pulse: ‘Tokenmaxxing’ as a weird new trend” — The Pragmatic Engineer
  • “Microsoft reports are exposing AI’s real cost problem: Using the tech is more expensive than paying human employees” — Fortune
  • “Cognizant CEO is swimming against the tide on AI: he’s hiring over 20,000 graduates this year and says AI tokenmaxxing is a ‘vanity metric’” — Fortune
  • “AI Agents Forecast to Boost Tech Cash Flow as Usage Soars” (24-fold token growth by 2030) — Goldman Sachs Research

Overflowing drawer of notes illustrating why a second brain becomes a graveyard of unused ideas

A Second Brain Won’t Run Your Company

Written by Eric Macfarlane on .

Overflowing drawer of notes illustrating why a second brain becomes a graveyard of unused ideas

Everyone’s building a “second brain” — capture enough notes, links, and prompts, and clarity will follow. It rarely does. Most systems become a graveyard of notes that never turn into finished work.

This piece argues the real answer isn’t a bigger pile of memory — it’s an operating system: a governed, layered stack with a protected core that decides what’s true and what’s allowed. A brain can’t enforce a rule on itself. An OS can.

Read the full article on why a governed operating system beats the second brain everyone else is building — and the read/write gap that should make a few software companies nervous.

Read the full article →

Overflowing drawer of notes illustrating why a second brain becomes a graveyard of unused ideas

A Second Brain Won’t Run Your Company

Written by Liz Eversoll on . Posted in Explainable AI.

Everyone is building a second brain. 

The promise is seductive: capture enough — notes, links, highlights, clever prompts — and clarity will follow. It rarely does. The notes pile up. The folders multiply. Six months in, you are scrolling a junk drawer you never open. One honest practitioner admitted to thousands of notes in his system and almost nothing ever turned into finished work. That is not a system. It is a graveyard with good intentions.

I went a different way. I built an operating system to run our company — a governed, layered stack I describe in full in a companion piece – CEO Operating System. This article is about why that beats the thing everyone else is building.

A machine brain is not your brain

Start with the metaphor itself, because it hides the problem.

A second brain sounds like an extension of your mind. It isn’t. It is a machine’s brain, and a machine knows nothing about how you want things done until you tell it — every preference, every standard, every rule, every time. The moment you take that seriously, you discover that telling a machine everything you want, reliably, on every run, has a name. It is structure. It is governance. It is a framework.

Which means the work of making a borrowed brain trustworthy is the work of building an operating system. The brain is not an alternative to the OS. The brain is what you get when you skip the OS and hope.

What the brain is missing

Put a real framework next to a second brain and the gaps are structural, not cosmetic.

No kernel. A second brain is all user space — notes, links, an agent rummaging through them. There is no privileged, governed core that decides what is true and what is allowed. A real system has one: enterprise knowledge and a governance layer sitting underneath everything. A brain cannot enforce a rule on itself. An operating system can.

No protected mode. The newer, AI-native versions hand an agent the keys to the whole vault and hope it behaves. There is no boundary it cannot cross. A real operating system gates authority — it can recommend advancing a deal but cannot cross the line on its own. That is not a feature bolted on. It is a property of being an OS.

It confuses memory with thinking. The whole genre treats remembering as the goal — capture more, store better. Even the clever setups bolt reasoning on top of one undifferentiated pile. An operating system separates the record from the reasoning: the reliable things stay reliable because they do not live in the same place as the improvising.

It rots. A drawer fills with junk because nothing governs what goes in or whether it is still true. That is the graveyard, and it is the metaphor failing in public. A governed record with a rulebook does not accumulate noise the same way. Structure is what stops the rot, and a brain has none.

Where the brain metaphor is actually fine

I am not going to pretend the idea is worthless, because it isn’t.

For an individual capturing ideas, the second brain works. The founding insight — your mind is for having ideas, not holding them — is true, and offloading memory is real value. The metaphor isn’t wrong. It is just small. It tops out at personal note-taking. It was never trying to run an enterprise, so beating it on governance is partly beating it at a game it never entered.

And the AI-native crowd — the ones putting an agent inside the notes, giving it an operating manual, letting it act and write back — are closer than the rest. That pattern is a genuine step up. Where they stop is the bottom of the stack: loose files in a folder instead of a governed record. They have built the top two layers and skipped the governed core — the canon and the rulebook — which is exactly the part that makes the difference.

The honest cost

An operating system is heavier than a brain. A second brain is something one person stands up in an afternoon with a folder and a markdown file. A real one depends on enterprise knowledge, a specification language, governed connectors, and a rulebook. That is infrastructure, not a weekend project.

I will not pretend otherwise — because the weight is the point. A drawer is light because it does nothing. The moment you want a system that runs the work and that you can trust unattended, you need a governed core, and that costs something to build. The brain stays light by staying passive. I traded lightness for a machine that actually operates.

The gap nobody is talking about

There is one more difference, and it is the one that should make a few software companies nervous.

A system of record only completes a process if you can read and write it. Most connectors are read-only. You can pull data out, but you cannot write back — to Microsoft To Do, to Teams, to plenty of others — which means you cannot round-trip a full workflow through the agent. The process dead-ends at the very screen you were trying to leave behind.

That sounds like an integration nit. It is actually a market threat. The switching cost of a system of record was always that everyone knows the screens. But once an agent can write directly into the record, the screens leave the daily path — and the moat goes with them. Suddenly the question is not which interface my team knows, but which system lets me push data in, read it back, and automate the loop.

That is why I moved my task list to a tool that round-trips and draft my mail in one that writes to drafts, while the read-only options in my current system sat untouched. I did not switch because the screens were better. I switched because one let the system operate and the other only let it look. Every system of record that stays read-only is teaching its customers the same lesson — and inviting the same replacement.

What to build instead

A second brain helps you remember. An operating system lets you run the company and step away from the machine — because the things that must be reliable are governed, and only the things that benefit from judgment are left to you.

If you are pouring hours into a second brain and wondering why you still feel buried, that is the reason. You have been building memory. Build a machine that runs instead. I laid out the full framework in the companion piece; and the part that makes it work isn’t the engine or the apps everyone has. It’s the governed core almost no one builds.