Head of Claude Code:
"85% of our engineers are running dozens or hundreds of agents. The way you do it is graph engineering."
In 40 minutes he explains how a single engineer now does the work of a whole team, how far this has gone inside Anthropic and where it goes next.
This is something you can't skip if you don't want to be left behind.
Watch it, then read the full guide on graph engineering below.
Rethinking code/PR review
Karena code sudah 100% AI generated, code review itu sekarang utamanya lebih buat dua hal:
1. Human memahami systemnya => belajar
2. Human memverifikasi hasilnya
Ibarat punya orang super smart di pocket kita, kita harus selalu upgrade pengetahuan kita agar tetap bisa komunikasi dengannya. Otherwise, kita akan loss dia ngomong apa, dan akan jadi ngangguk2 aja karena udah gak ngerti projectnya gimana
Berdebat soal styling, guideline, performance, clean code, dll di code review itu akan less and less relevant. Kalau untuk itu, bisa tinggal trigger yet another AI agent buat saling debat
Nah, karena goalnya untuk belajar, maka high leverage task kita adalah mempermudah itu, supaya tidak belajar thousands of code manually. Gimana? Pake AI juga 😁, bikin AI teacher yang goalnya adalah membuat human cupu ini paham
Bisa bikin skill /pr-explainer yang jelasin step by step. Bisa juga minta output HTML buat visualize penjelasannya. Bisa juga diakhiri dengan quiz, memastikan si human ini paham dengan masterpiece AI
As engineering, product, design, DS, etc. melt into a new kind of role, I was reflecting on what roles might look like in the future. For example, when I look at the Claude Code team I see what I think is five archetypes:
1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship
2. Builder: quickly turns a prototype/idea into production-grade product/infra
3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance
4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit
5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales
Many people span across 2 roles, and sometimes 3 roles. I also notice that these roles are not really tied to job function -- eg. across Anthropic, some designers match category 1, some 2, some 3; same for engineers, PM, DS.
A healthy team needs a mix of these, depending on the product:
- A product that is new and pre-PMF needs people that are strong at 1+2+3
- A product that is growing and has found PMF needs 2+3+4 and some 5
- A product that has strong PMF needs 3+4+5 and some 2
Maybe product roles of the future will look more like this, and less like the domain-specific roles of today?
Three key messages
You can outsource memory and computation, but you cannot outsource understanding.
Real value is created when everyone – teachers, technicians, managers, engineers, doctors, lawyers, even ministers – who understand their work, are provided with AI tools that transform how they get the job done; or even better, re- engineer their entire workflow.
The barriers for access to these tools have just collapsed.
https://t.co/XTAY11obLt
Agar tidak gatekeep. Daftar artikel saya soal kerja di LN:
- Mencari kerja https://t.co/yxVhv3vAuG
- Relokasi atau remote https://t.co/TvmBJ9EqH6
- Cara belajar bahasa https://t.co/kF69faDz0X
- Pengalaman PHK https://t.co/PZ99OTWtJD
- Relokasi bawa kucing https://t.co/pVeSvEfzKj
Pro tip for coding with agents:
custom linters on your pre-commit hook
Super pro tip:
design system with tokens (colors, spacing, sizes) enforced with a design-system custom linter on your pre-commit hook
Beyond the winners of our "Built with Opus 4.6 Claude Code Hackathon," there were so many amazing projects that deserve a shoutout.
Today I want to highlight Pasal by Ilham Putra. 280 million Indonesians can't easily search their own laws. Pasal fixes that.
In 2026, every engineer should ship:
> At least one API
> One agent
> One production-grade RAG, MCP.
Even if it’s small. It proves systems thinking.
I've been grinding with Codex (on Extra High) through setting up our repo for Harness Engineering.
The goal is to have Codex right and review 100% of the code.
Getting much closer.
https://t.co/synYBpsGYA
Ngga lama, Ibam dikontak recruiter Facebook. Mereka cari lead untuk tech team di London.
Setelah 2x ke London untuk wawancara, Ibam lolos seleksi dan dapat offer:
- Gaji Rp192 juta/bulan
- Bonus tahunan Rp346 juta
- Saham Rp3,8 miliar
- Relokasi sekeluarga ke Inggris Raya 🇬🇧