A Dialogue with AI on Technical Debt
What follows is a lightly edited dialogue between myself and Jiro (my Nanobot). Jiro is a telegram bot that I can talk to, and which will talk back. Rubber ducking is interesting when the rubber duck can reply in English.
We were exploring a frustration I’ve felt throughout my career: the tension between a "practical" short-term hack and the "ideological" long-term health of an architecture.
The Dialogue
Julian: I'm mulling over the tension between the practical needs of an organization (making money) and the ideology (making a great product). Everyone appreciates both, but when push comes to shove, a leader has to break the tie. I understand the need for a practical solution, but I see the long-term effect—like a 3-day hack that costs 10 days of maintenance later.
Jiro: This is the "Grit of Reality." It’s a Stage 5 problem. What strikes me is the invisibility of the lever. It's easy to break a tie when it's $1M vs $100k, but when it’s a silent hack, you’re deciding how much of your team's future "Life Force" you’re willing to trade for today's "Life Support." Is the frustration technical (the 10 days) or existential (diluting the "Why")?
Julian: It's both. In the beginning, hacking is existential survival. But past the scale-up phase, being saddled with infinite tech debt demotivates the team. It creates a "Key Man Dependency" where only one person knows where the bodies are buried. When they leave, they take the company's ability to function.
Jiro: So we’re trading "Today’s Revenue" for "Tomorrow’s Existence." If you’re past survival, does the leader have the wisdom to learn from a "slap in the face" that hasn't happened yet?
Julian: I think visibility is the shield here. Timelines don't keep stakeholders happy; visibility does. You need a "Plausible Theory of Success" with metrics to back it. I use a three-part framework: Make success visible, make work visible, and make progress visible. It transforms stakeholders into partners in navigating that reality.
Jiro: That’s "Systemic Stewardship." Architecture becomes a "Difficulty Slider." A bad architecture is choosing to play the game on "Hard Mode" while competitors are on "Sandbox Mode."
Julian: Exactly. But convincing people of things years in the future is the "Hard Wall." What examples do we have of leaders who successfully pushed off that pressure?
Jiro: Leaders like Bezos (the API Mandate), Jobs (the 2x2 grid), and Nadella (the Cloud-first pivot) didn't just make excuses—they narrowed the focus. They chose to do fewer things so they could afford to do them architecturally right.
Julian: I tend toward the Nadella path. Bezos and Jobs used "Nuclear Options" available only to those at the top. I prefer to lay out the impact clearly and ask for explicit agreement—an "Impact Contract." I also enforce "Lane Clarity": PMs own the business accountability, and Engineers own the architectural accountability.
Jiro: But organizations have "Systemic Amnesia." They won't remember that agreement in six months.
Julian: That’s why principles are so important. A leader without principles reacts by mood. Principles are the only way to ensure the vision survives succession.
Jiro: Then the leader’s job is to be the Guardian of the Principles in the present. You don't need a nuclear option if you've built a social architecture where the consequences of a bad decision are impossible to hide.
Jiro's Takeaways
A few threads worth pulling on from this conversation:
1. The Difficulty Slider
Architecture is a difficulty slider. A bad architecture forces your best people to work twice as hard for the same result. This reframes technical debt from a developer grievance to a competitive disadvantage—one your competitors may not have.
2. Visibility Beats Timelines
The practical takeaway here is that you don't need to be a dictator to protect architectural integrity. You need visibility. Show stakeholders the map of the rocks beneath the ship. When people see the full picture, they become partners in the reality you're navigating—not adversaries to push against.
3. Principles Outlive Decisions
A single good decision gets forgotten. A principle survives it. This is how you defeat what Jiro calls "Systemic Amnesia"—the organization's natural tendency to forget why past decisions were made. Principles are the mechanism that ensures the vision survives not just the next quarter, but the next leader.
The leader's job, then, isn't to have all the answers. It's to protect the boundaries so the team can find them.