Skip to content
whoami

Marvin
Aziz

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

Marvin Aziz
growth engineerlindy · sf

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" --author=marvtub

github.com/marvtub ->

ls -lt ./blog | head -5

All 9 posts

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.

More of what I'm into

ls ~/projects

total 5

My coding-agent token usage

$ stack --since 30d

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.

$ stack --by model14 models
  • 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%
$ stack --by assistant3 assistants
  • codex56.4%
  • claude code33.1%
  • pi10.5%
$ stack --personal-assistants5 active right now
  • active
    lindy
  • active
    muse
  • active
    hermes
  • active
    openclaw
  • active
    grok bot