Skip to content
Marcio Sete
Hi, I'm

Marcio Sete.

Founding engineer with nearly 30 years shipping products, teams, and companies.

Currently Head of AI Engineering & Platforms at Kinetic IT, bringing frontier AI to the frontline.

I'm also the founding engineer of five 0→1 products — Euda, Rovik, Brightkind, Budget Wise and Agent Studio. The leverage that makes this possible is agentic engineering, which I research and write up in the open.

I mentor entrepreneurs, engineers and engineering leaders going deep on agentic engineering and agent architecture — helping them turn new patterns, tools and operating models into practical engineering capability.

Here I share what I'm building and learning. If you're in the trenches on agentic engineering, agent architecture, or flow, reach out.

Field Notes

View all →
11 Feb 2026LinkedIn

The agent architecture that will define 2026.

I hear people calling OpenClaw sentient... an agent called its owner at 3am.

2 min read →
9 Feb 2026LinkedIn

☕️🧘 Same workflow.

22.5× → 101.

1 min read →
6 Feb 2026LinkedIn

Anthropic and OpenAI just dropped their new flagship coding models.

Same day. Same target.

2 min read →
4 Feb 2026LinkedIn

161,000 GitHub stars.

OpenClaw became the fastest-growing open-source project ever. Developers are buying Mac minis specifically to run a personal AI agent with root access to their digital life.

1 min read →
29 Jan 2026LinkedIn

If you're not maxing out your Claude Max subscription every time, you're leaving value on the table.

1 min read →
22 Jan 2026LinkedIn

🌶️ “Spec-driven development + autonomous agents” is just Waterfall 2.0.

Yes, I'll keep banging on it. We saw the news that Cursor ran long-running coding agents for close to a week on a single project and ended up with a browser rendering engine from scratch (HTML parser, CSS cascade, layout/rendering, etc.

2 min read →

Research: Agentic Engineering

October 2025

Productivity Multipliers

Measuring the productivity multiplier of agentic coding vs pre-AI baselines across churn and net code metrics.

October 2025

Speed to Value

Lead time distribution insights - from days and months to minutes and hours. Based on 153 tickets measured from intent to main-branch merge.

November 2025

Software Quality

Proving agentic coding doesn't trade speed for quality. Enterprise-grade standards achieved in under 3 days on a ~100k LOC codebase.

Lab

View all →

Euda

An AI workplace wellbeing companion that helps create healthier and safer workplaces.

Rovik

One AI companion across your training, food, sleep, habits, journal and challenges.

Brightkind

Thoughtful, agent-led home education for families.

Budget Wise

A thoughtful financial operating system for families who want to be intentional about money.

Agent Studio

Always-on AI employees for SMBs.

Newsletter

View all →

What I'm building, what I'm learning, monthly.

A short field note from the trenches of agentic engineering and flow. No spam, unsubscribe anytime.