CPO @vidio | Product Builder | Agent Orchestrator
Jakarta
Joined July 2007
- Tweets8.3K
- Following710
- Followers1.1K
- Likes4.8K
Pinned Tweet
Use Case OpenClaw agent dan Review setelah 2 bulan 🦞
Dari awal tujuannya adalah bikin "sistem" yang memudahkan manage personal life dan project. Prinsip Atomic Habit, build system to make new habit.
Jadi setup Openclaw-nya cukup challenging: multiple agent, model, users.
Gw pake tema My Hero Academia buat naming karena setiap agent punya karakter, domain, dan "kekuatan" masing-masing. Total ada 6 agent.
All Might: Chief of Staff & Orchestrator Agent
Ini karakter utama, chief of staff. Setiap pagi dia kirim briefing ke WhatsApp gw, semua Todo yg perlu perhatian (connect dengan Workflowy, Calendar). Semua reminder dan notifikasi dari agent lain juga lewat dia. Intinya dia sbg orchestrator, bahkan bisa modify behavior agent lain.
Multiple channel, aturan simpelnya: kalau butuh perhatian gw → WhatsApp (dan di pin atas).
Kalau mau diskusi detail → Telegram.
Aizawa: Parenting Agent
Bisa buat journaling anak, diskusi soal parenting, pola perilaku anak, reminder jadwal sekolah. Anak-anak juga bisa tanya langsung via WhatsApp mereka sendiri yang lebih secure karena ada guardrails.
Yang menarik, knowledge dan wisdom dari berbagai framework parenting yg cocok udah diajarin sebagai skill.
Deku: Product & Coding Agent
Semua urusan product development side project gw masuk sini. Mulai dari yg non profit darisini.com, ruangkajian, dan jg wellness di activebarn, sgym.
Deku tau knowledge-nya, konteksnya, stack-nya, ga perlu gw jelasin ulang tiap sesi. Urusan coding pakai Claude Code, agentic dan iteratif.
Deku paham semua knowledge dari Lenny Ratchitsky database dan wisdom dari Shreyas Doshi dan bbrp thought leaders product & tech.
Hawk: Business Agent
Semua urusan business lewat Hawk. Yang bikin menarik: agent ini di-share ke pasangan dan saudara gw via WhatsApp, masing-masing dari nomor mereka sendiri.
Jadi mereka mau tanya atau minta apapun bisa lebih mudah, karena Hawk uda ngerti semua informasi2 penting.
Momo: Finance Agent
Buat urusan personal finance, budget, tax, dan investment. Sengaja dipisah karena datanya penting dan perlu set model yang lebih canggih/mahal Claude Sonnet karena analisis keuangan butuh reasoning yang lebih kuat.
Todoroki: Research Agent
Ini yang paling beda. Todoroki jalan di framework terpisah, NanoClaw, berbasis Claude Code SDK. Dia ga cuma jawab sekali. Dia search, evaluate, re-search, baca pdf, web, dan terus iterasi sampai dapat jawaban yang beneran.
Yg gw suka dari Claude code adalah Agentic browsing-nya beda kelas dengan yg lain. Dan hasil summary jawabannya verbose bgt.
Output-nya langsung tersimpan ke Obsidian vault gw (sync Google Drive). Satu tempat, searchable selamanya.
Kesimpulan
Setelah jalan dua bulan, gw merasakan sendiri banyak bgt manfaat yang didapat, waktu yang dihemat, dan bisa lebih fokus. Next level productivity tool.
✅ Multiple agent yang punya spesialisasi dan bisa bekerja sama
✅ Multiple channel bisa di telegram dan whatsApp sekaligus
✅ Multiple user, pasangan dan keluarga gw bisa akses agent yang relevan
✅ Multiple model via OpenAI Oauth dan OpenRouter
✅ Terintegrasi Google Workspace, Workflowy, Obsidian, etc
Overall experience sudah ok. Setup awal agak ribet tapi ternyata yang paling challenging setelah digunakan cukup lama adalah "maintenance" supaya hasilnya ttp konsisten.
Kita harus tau cara kerjanya Openclaw untuk menutupi kekurangannya, file yg digenerate bisa cukup messy, jadi perlu tweak terus supaya hasilnya rapi dan konsisten.
Tapi kalau udah ngerti caranya, you'll never go back to the "old" system.
Berikutnya gw akan post lebih detail teknis setup Openclaw dan skill masing-masing agent. Stay tune!
Hypeless!
Ada banyak banget use case di Vidio soal automation, AI workflow. Salah satu yg baru live adalah, auto highlights.
Intinya automation dari full match bola jadi highlight 2 menit atau mini match 8 menit, dan langsung publish di Vidio, 10 menit setelah match selesai.
Share your best AI workflow and get featured in my
newsletter!
We're all sick of overhyped AI demos and workflows. Stuff that looks/sounds amazing but doesn't actually work. This project we're calling "Hype(less)" aims to collect and share the most real, impactful, and repeatable AI workflows that have created real value for you and your teams.
You have until Friday, Oct 30th to submit your entry: tally.so/r/dWL6Xd
Kedengeran simple tapi sebenarnya kompleks,
1. Data, harus paham key moment mulai dari goal, shot on goal, saved, foul, dan kapan terjadi. Heavy data training.
2. Clip, durasi clip tiap momen harus pas, dari build up sampe replay.
3. Edit, stiching clip + motion graphic
Makin keren aja nih Grokbot. Brb cobain.
Grok Bot just got a very big upgrade on iOS and Android
Grok Bot can now directly interact with apps on your phone and handle everyday tasks for you
New capabilities include:
• Messages: Read and send messages
• Calendar: Check schedules and create events
• Reminders: Set and manage reminders
• Contacts: Find and add contacts
• Location: Find nearby places
• Home: Control lights, locks, and other smart home devices
Instead of you constantly switching between apps, you can simply ask Grok Bot to get things done for you
This is a huge step toward having a personal SI agent that can actually interact with your phone and make everyday life easier
Rolling out now on iOS and Android. Update Grok Bot to try it
Habis bandingin Claude Duet sama Grok Bot, ternyata konsep "punya komputer"-nya beda bgt.
Duet sebenernya jalan di VM cloud sendiri, tapi tertutup. Ga bisa diliat, ga bisa di take over, dan aksi penting harus approval. Jadi lebih ke Claude yg jadi proaktif. Appnya jg baru mobile, UIUX konsep task dan make-nya menarik.
Sedangkan Grok Bot akses komputernya terbuka. Lebih bebas bisa install2 tools, jalanin script, bikin file, browser yg tetep login, sampe login website lewat 1Password tanpa harus kasih password ke agentnya. Di Duet, 1Password masih coming soon.
Kesimpulan sementara gw, utk personal AI agent masih vote Grok Bot. IMO bedanya bukan siapa yg punya komputer, tapi siapa yg ngasih kita kunci komputernya.
claude.com/resources/article…
Anthropic rilis Claude Duet, agent proaktif yg kerja di background.
Konsepnya mirip GrokBot/Muse/Dots. Tiap pagi kirim brief dari app2 yg di-connect, terus cek tiap bbrp jam dan baru message kalau ada yg butuh perhatian.
Masih research preview, pake waitlist, dan baru utk Pro/Max di US. Background check-nya jg ikut makan usage limit.
Sementara gw masih setia pake kombinasi Grokbot dan OpenClaw.
claude.com/resources/article…
Akhirnya Claude Max & Team dapet API credit bulanan
Max 5x dapat $100, Max 20x $200, Team sampai $500 (pooled). Pro ga kebagian 🥲
Bisa dipake utk Claude API, Managed Agents, Agent SDK.
Jadi agent yg jalan pake Agent SDK (kayak nanoclaw, walau sampe sekarang masih jalan) atau app kecil buatan sendiri bisa jalan dari credit ini dulu.
Apalagi digabung sama Haiku 5.5 yg $0.10 per 1M input, $100 harusnya bisa lumayan jauh
Claim di claude.ai Settings > Billing, link ke Console org
platform.claude.com/docs/en/… – at Seoul, Republic of Korea
Agent teams di Claude Code
Fitur eksperimental: satu agent jadi lead, terus dia bikin beberapa agent lain yang masing-masing punya context sendiri.
Use case: Belum tau buat apa 🤣
code.claude.com/docs/en/agen… – at Kebayoran Lama, Indonesia
Makin penasaran sama Meta Muse, tiap user dapat full Ubuntu VM di cloud. Bisa install, compile, browsing. Mirip grok bot sih.
Yang menarik Nat Friedman bilang Muse banyak terinspirasi dari OpenClaw (pola SOUL.md/workspace), tapi dibangun from scratch 🦞
Dan lebih seru kalau nantinya seamless connect ke ecosystem WA, IG, etc. Jadi the new app store.
techcrunch.com/2026/09/22/me… – at Kebayoran Lama, Indonesia
Grok Bot Review.
Super convenient! Gampang setup-nya dan cocok utk personal productivity agents krn bisa punya multiple bot sekaligus.
Yang udah gw test:
- summary YouTube
- analisa saham IDX & US
- pantau berita real time
- connect Google Drive, Gmail, dll
- bikin web app simple (hyrox related)
Semua bisa dikerjain cukup cepet, memory juga ok (gak pelupa), bisa pake browser sendiri, ga perlu maintenance bot.
Yang enak juga connect ke X gampang, jadi bisa dpt real-time social data.
Total cost sekitar $30 per bulan.
Recommend bgt buat yang pengen punya Al agent tapi ga mau ribet setup Openclaw/Hermes di MacMini atau PC. – at Kebayoran Lama, Indonesia
Hadikusuma Wahab retweeted
OpenClaw is now on iOS + Android 🦞
📱 Native mobile apps, finally
💬 Agents in your pocket
🔔 Channels, tasks, replies on the go
Run agents from wherever your thumbs are.
iOS: apps.apple.com/us/app/opencl…
Android: play.google.com/store/apps/d…
Hadikusuma Wahab retweeted
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?
Hadikusuma Wahab retweeted
Joe Hudson is one of the most sought-after executive coaches in tech, working with leaders across OpenAI, Apple, Google, and more.
Here's his 5-part framework for how to run a company effectively
The biggest upheaval to work in our lifetime is here.
Joe Hudson (@FU_joehudson) coaches the research team at @OpenAI (along with @sama and leaders across Apple and Google), and from that front-row seat, has noticed the people doing best in these AI-forward environments aren't winning for the reasons you'd expect.
It's not more knowledge or more effort. Those are the exact two things AI does best.
Instead, they win on "emotional clarity": staying in hard conversations, not turning on themselves (and others) when things get tough, and pushing forward through failure.
In today's incredible guest post, Joe shows you exactly how to build this skill within yourself and your team.
Inside:
+ How AI is changing work: the NBA-ification of teams
+ The new inner game: the "wisdom stack" that will set you apart
+ How to build a team that can metabolize fear
Don't miss this one: lennysnewsletter.com/p/the-n…
Hadikusuma Wahab retweeted
Many people think any given ML project is 99% training.
In reality, it’s 50% evaluation, 40% data cleaning, 8% integration, and 2% training.
The first two set the noise floor for learning. No ML magic matters; the model cannot lower the noise floor, as that’s the optimal bound of Shannon encoding of your data.
Thus, not a single day goes by without me thinking about ontology. Even the old labels have to be constantly reviewed.
Hadikusuma Wahab retweeted
Built a personal AI agent - why I did that and what it means. go.gov.sg/aiesingapore
Akhirnya Claude subscription bisa juga dipake buat openclaw, dll.
Tapi ... konsepnya jadi credit, pro cuma dapat $20, max 5x dapat $100 dst.
Credit utk programmatic usage, agent sdk, claude -p, github actions.
Jadi kalau panggil Claude -p dari openclaw, atau nanoclaw yang pake agent SDK, akan pake creditnya.
Kalau pake Opus sih pasti cepet habis 🥲
