What Working with AI Taught Me About Knowledge Management

What You Don't Know You Know

You know things you've never said out loud.

Not secrets. Working knowledge. The decision tree you run when a client pushes back on timeline. The questions you ask before signing off on a deliverable. Questions nobody taught you, that you couldn't trace to a training or a book. The sense that a project has shifted before you can name what.

You've never had to articulate most of it. With colleagues, you can say "you know how we handle that" and they do. The tacit stays tacit. The knowledge lives in the relationship, distributed across minds that built shared understanding over time.

Then you start working with a tool that has no shared understanding.

Every session starts from zero. No memory. No continuity. Whatever you don't make explicit doesn't exist. At first, this felt like a limitation to work around. I'd copy context into prompts, rebuild shared understanding, explain things I'd explained before. Frustrating.

Then something shifted. The friction became useful. The act of externalizing knowledge for a tool that couldn't remember anything revealed something I hadn't expected: I didn't actually know what I knew.

What I thought was expertise turned out to be a mix of genuine judgment and accumulated habit. What I called "intuition" was sometimes pattern recognition I could articulate and sometimes genuine creativity I couldn't. The discipline of writing things down for AI didn't just help the AI. It showed me the structure of my own work.

These lessons started as coping strategies. They became something else.

The Forcing Function

Here's what makes AI that forgets interesting rather than just annoying: it won't let you coast on shared context.

With a colleague, you can say "you know how we handle that" and they do. The tacit stays tacit. You never have to articulate the decision tree, the edge cases, the reasons behind the reasons. The knowledge lives in the relationship, distributed across two minds that have built shared understanding over time.

AI has no shared understanding. It has whatever you give it in the moment. This is a constraint, but constraints reveal things. The constraint of externalization reveals which parts of your knowledge were ever explicit in the first place.

Most of mine weren't.

I'd been operating on a mix of documented process, undocumented heuristics, and pure feel. The documented parts transferred easily. The heuristics required work to articulate but could be articulated. The feel? That's where things got interesting.

Some of what I called "feel" turned out to be pattern. When I forced myself to write it down, it became rules. Not rigid rules, but conditional logic: "When X and Y, do Z unless W, in which case do Q." Complicated, but expressible.

Other parts of "feel" resisted articulation entirely. Not because I was lazy, but because they genuinely required presence. Reading a room. Sensing when someone was ready for feedback versus when they needed space. Knowing when to push and when to hold. These don't compress into instructions.

Six Lessons from the Discipline

The practice of externalization revealed things about my own work that had nothing to do with improving AI.

These lessons accumulated over months. Individually, they seemed like tactics for working with a limited tool. Together, they pointed somewhere else.

What This Actually Reveals

The discipline of externalizing knowledge does something unexpected. It makes visible a distinction that was always there but easy to ignore: the difference between work that follows pattern and work that requires presence.

Most knowledge work mixes both. The discipline of externalization reveals the ratio.

What surprised me was how much of my work turned out to be pattern. I'd been treating it as judgment because it felt effortful, because I was the one doing it, because I'd accumulated skill at it. But effort isn't the same as irreducible human presence. Skill at a pattern is still pattern.

This isn't a comfortable realization.

It raises questions about what exactly justifies your seat at the table. If most of what you do follows pattern, even the complicated, earned kind that took years to learn, then the story you've been telling about your own indispensability needs revision. Not all of it. But more than you'd like.

And the discomfort doesn't resolve neatly. You can't just say "I'll focus on what requires me" because the pattern work and the presence work are tangled. The judgment that matters often shows up inside the pattern work: the moment where the rules say one thing and the situation says another. Presence isn't a separate category. It's what you bring to the pattern when the pattern isn't enough.

But the line, even blurry, is clarifying. Once you see the distinction, you can stop spending human attention on pattern work. You can protect the parts of your work that actually require you. You can stop confusing "I'm good at this" with "this requires me."

Two Kinds of AI, Same Discipline

This framework applies whether you're working with AI that waits for you or AI that acts on its own.

With conversational AI assistants, incomplete externalization costs you effort. You compensate in real time. You catch mistakes because you're in the loop. The knowledge gaps show up as friction: extra prompting, more back-and-forth, results that need heavy editing. You're there to fill in what the documentation doesn't say.

I didn't realize how much I was compensating until I started working with agents: AI that operates with more autonomy, executing multi-step processes, making intermediate decisions without checking in.

With agents, the gaps don't show up as friction. They show up as drift. The agent executes faithfully based on what it knows, which may no longer match reality. You're not there to catch it. The first time an agent confidently completed a task using documentation that had drifted from current practice, I understood: documentation quality isn't a convenience for agents. It's reliability.

The discipline is the same. The consequences compound differently.

The Benefit Beyond AI

If AI tools suddenly became perfect, with infinite memory and flawless context retention, would this discipline still matter?

Yes. And that's the point.

The act of externalizing knowledge produces value independent of who or what consumes it. The documentation that serves AI also serves new team members. The structure that makes context portable also makes thinking clearer. The failure modes you articulate for AI are the same failure modes that trip up humans who lack your experience.

And the spectrum it reveals matters beyond any tool. Knowing which parts of your work require human presence and which follow pattern tells you where to spend your attention, what to protect, what to systematize, what to let go.