Lami Adabonyan — Engineering & Product Leader

The Agent Should Not Be the Architecture

Sun, 05 Jul 2026 12:00:00 -0400

The future of building apps is not “let the agent figure it out.”

It feels magical, fast, and useful to keep a Claude Code session open, throw it a feature, let it inspect the repo, and watch it wire things together. You think to yourself, the new development model is obvious: less architecture, more prompting.

This is the wrong lesson.

The app still needs to be deterministic. The handoff still needs to work when the original builder is gone. The team that inherits it still needs to understand where behavior lives, how state moves, what assumptions are encoded, and what has to be true before a change is safe.

Having First Dibs Is Overrated

Fri, 03 Jul 2026 00:00:00 +0000

Every new AI launch comes with the same implied question: Have you tried it yet? It’s tempting to think the right answer is always yes. It’s not.

Owning the first iPhone didn’t make you better at using smartphones. It just meant you got there first. Within a couple of years everyone else had the same capabilities, often with fewer bugs and a clearer idea of what actually mattered.

The same pattern keeps repeating in software. I see people contorting their workflow to accommodate whatever shiny beta feature launched this week. They’ll open one app just to send something into another app, even though the destination app already lets them do the same thing faster. The workflow bends around the feature. That’s backwards.

AI Did Not Expand Your Attention

Mon, 22 Jun 2026 00:00:00 +0000

Something changed last December, I went from constantly correcting and steering coding agents to looking at what Opus produced and thinking, damn, I would have needed three passes over a week to get there.

When I write code, I usually arrive at the final version through iteration. I try an approach, find the awkward edges, restructure it, run the tests, and look at it again. Eventually, I mold it into something that feels elegant. Opus jumped straight to elegance within five minutes (yeah, yeah, yeah, I had good instructions in Markdown files, but still).

Your GenAI Strategy is Theater

Sun, 12 Oct 2025 00:00:00 +0000

Your board wants to know what you’re doing about AI. Your CEO forwarded another breathless LinkedIn post about autonomous agents. A VP just IMed you asking if we should be “building with Claude” or “going all-in on GPT-5.”

Here’s what you should tell them: We don’t have a GenAI strategy, and that’s intentional.

Not because AI doesn’t matter. It does. But because the question itself reveals a fundamental misunderstanding of where we are in this cycle, what these tools actually do, and how technology adoption works in organizations that ship real products to real customers.

Is Gen AI Approaching Bubble Territory?

Sun, 28 Sep 2025 00:00:00 +0000

Gen AI looks like a bubble, but people are still using it to get real work done.

It’s the internet, cloud, and crypto rolled into one. Everyone’s betting big. But when you peel back the hype, a harder question emerges: is this transformation, or just the most expensive game of follow-the-leader in tech history?

The Emperor’s New Algorithm

We’re living through the most overhyped, under-delivered technology moment since the dotcom boom. But here’s the kicker: unlike 1999, this bubble might actually have substance underneath all the noise.

Diseconomies of Scale: Why Software Slows Down as Companies Grow

Sun, 21 Sep 2025 00:00:00 +0000

Software is eating the world, and large corporations are choking on it.

Every Fortune 50 company knows the pattern: the bigger they get, the slower they ship. A ten-person startup can push to production five times a day. An enterprise can turn the same kind of change into a quarterly release.

This isn’t incompetence. It’s economics.

The Myth of Software Scale

Factories scale linearly. Software scales exponentially in complexity.

The common model for software development is simple: hire more engineers, build more features, capture more market share.

What Everyone Gets Wrong About AI and Junior Devs

Sun, 07 Sep 2025 00:00:00 +0000

AI won’t close the door on junior developers, it’s widening the hallway for all of us. Beginners will onboard faster. Seniors will mentor with sharper tools. Managers will scale teams with less friction. Executives will rethink how value gets created. Far from ending careers, AI is redrawing the developer journey into something bigger, faster, and more connected. From first jobs to executive seats, AI is shifting the developer journey, not ending it.

AI Fundamentals: Stripping Away the Jargon

Sun, 24 Aug 2025 00:00:00 +0000

The tech industry has a knack for turning simple concepts into incomprehensible jargon. AI is no exception. Strip away the buzzwords, and you’ll find something remarkably straightforward and more useful than the hype suggests. Let’s walk through what AI actually is and where we are on the curve and journey to creating useful tools.

TL;DR

AI isn’t magic: it’s just advanced pattern recognition.
Generative AI (like ChatGPT) creates content but can’t act.
AI agents are the next step, giving AI “hands” to perform tasks.
The real opportunity is moving from talking to AI to having AI do work for you.

What AI Really Is - Spoiler: It’s Not Magic

Machine Learning is pattern recognition on steroids. Feed a computer enough examples of cats, and it learns to spot cats in new pictures. Show it enough chess games, and it gets decent at chess. It’s not thinking. It’s finding patterns in data, then applying those patterns to new situations.