Marvin
Aziz
Marketer turned agentic builder, shipping software at an unreasonable pace.

Growth Engineer at Lindy in San Francisco, running product-led growth experiments. Built agents with thousands of professionals through a community we grew, before becoming what I like to call an "agentic builder" — a fancy way of saying I built myself a system with agents to ship software at an unreasonable pace. This site is where I write about it as I go.
git log --since="20 weeks ago"--since="Jan 1" --author=marvtub
github.com/marvtub ->ls -lt ./blog | head -5
- How I make videos with Claude Code~2308 tok · 9 min
- How to trust your agent~2447 tok · 10 min
- How I ship code I can't read~3271 tok · 13 min
- Why My Coding Agents Live on a VPS Now~1619 tok · 7 min
- The Four Layers of Agentic Engineering~3122 tok · 13 min
tail -n 4 ~/into.log
- [note]
Built Orc, an orchestrator in Herdr, to do less context switching throughout the day. I can manage my fleet of 20 plus agents more effectively while keeping things transparent.
- [note]
Padel. Mexico was really fun for it and I want more. I don't know anyone who plays, so it's open community sessions and maybe a trainer.
- [link]
Built Takes. I record, Claude Code does the edit. First for myself, now for others. It's the most fun project I have ever worked on.
- [note]
My AI coding agent spend is getting ridiculous: 2x Codex Max, Claude Code Max, Cursor Max, OpenRouter, DeepSeek API, Baseten, and Cerebras.
ls ~/projects
total 5- gettakes.app
takes2026The Mac app I built for everything after the recording: the cut, the captions, the posts.
- wpm.marvinaziz.de
wpm-screener2026Typing speed and accuracy gauntlet. Built as a hiring screen, then I got hooked.
- heynimo.com
nimo2026Website performance as a service. Subscribe to speed, not to charts.
- tennis.marvinaziz.de
sf-tennis2026Real-time availability map for public tennis and pickleball courts in SF.
- videobrainstorm.com
videobrainstorm2026One rough prompt becomes several image directions, then videos, finals and polls.
My coding-agent token usage
52.2B
tokens went through my coding agents in the last 30 days, across 8,127 sessions. This is who did the work.
50.6B of that is cache reads: context the agents re-read on every turn. 1.62B is new input, output and cache writes.
- gpt-6.1-sol51.7%
- claude-opus-5-529.8%
- gpt-5.6-sol8.6%
- gpt-5.6-luna5.6%
- claude-fable-5-22.3%
- other (9 models)1.9%
- codex56.4%
- claude code33.1%
- pi10.5%
activelindy
activemuse
activehermes
activeopenclaw
activegrok bot