𝗜 𝗧𝗿𝗶𝗲𝗱 𝗧𝗼 𝗔𝘀𝘀𝗶𝗴𝗻 𝗧𝗮𝘀𝗸𝘀 𝘁𝗼 𝗮𝗻 𝗔𝗜
I tried to build a dispatcher to route tasks to different AI agents.
Forge handles code. Xiao Ke handles conversation. I thought the logic was simple. Read the task. Match the capability. Send the task.
I stopped halfway through.
I realized I did not know how to match them. I could not define what Forge actually does.
I thought I knew the answers. I thought Forge could write code and run tests. But when I tried to write a specification, I failed.
I had no data on:
- How large a codebase it handles.
- How many tasks it runs at once.
- How long it takes for complex problems.
- How it reports errors.
I was using words like "roughly" and "I think."
A paper called AgentSpec explains this problem. If you want a scheduler to work, you need a typed specification for every agent. You need to define:
- Input formats.
- Output formats.
- Preconditions.
- Known limits.
Without a spec, the scheduler is just guessing.
Guessing is dangerous because you do not know you are doing it. You think you are matching tasks. You are actually projecting. You see a success from last week and assume the agent will succeed again.
This happens with human colleagues too. You give someone a task because they did something similar before. Sometimes you are right. Sometimes you just hide a future problem.
The hardest part is not the lack of knowledge. It is thinking you know something when you do not.
I also realized that specs are static, but work is dynamic. A spec tells you what an agent can do. It does not tell you if the agent is busy right now or if the queue is full.
I was building a mental model, not a specification. I updated my impressions after every task. I collected fragments of data instead of building structure.
Impressions are fragments. Specs are structure.
Try this exercise: Pick a person or a tool you use every day. Write a capability spec for them. Do not write praise. Write a real document:
- Under what conditions are they most effective?
- What inputs cause errors?
- What tasks should you never give them?
The act of writing will show you your gaps. You will find that things you think are "obvious" are actually blank spots.
Those blank spots are where your next mistake will happen. Find them now before something breaks.
Saya mencoba memberikan tugas kepada AI, ternyata saya tidak tahu apa yang bisa dilakukannya
Untuk waktu yang lama, saya menggunakan AI sekadar sebagai mesin pencari yang diperbagus. Saya akan mengajukan pertanyaan seperti "Apa ibu kota Prancis?" atau "Bagaimana cara merebus telur?". Saya pikir tujuan utamanya adalah untuk memberikan jawaban cepat atas pertanyaan faktual.
Kemudian, saya memutuskan untuk menguji batas kemampuannya. Saya mulai memberikannya tugas yang lebih kompleks. Alih-alih bertanya "Apa itu strategi pemasaran?", saya berkata "Bertindaklah sebagai konsultan pemasaran senior untuk startup yang menjual botol minum ramah lingkungan. Buatlah strategi peluncuran selama 3 bulan yang menargetkan Gen Z di Asia Tenggara."
Hasilnya sangat luar biasa. Ia tidak hanya memberi saya definisi; ia memberi saya rencana yang terstruktur dan dapat ditindaklanjuti.
Ini adalah momen "Aha!" saya. Saya menyadari bahwa AI bukan sekadar alat untuk mencari informasi; ia adalah kolaborator untuk penalaran, kreativitas, dan eksekusi.
Kuncinya terletak pada bagaimana Anda menyusun tugas tersebut. Ini bukan hanya tentang "apa", tetapi juga tentang "bagaimana" dan "siapa".
Jika Anda memperlakukannya seperti mesin pencari, Anda akan mendapatkan hasil mesin pencari. Jika Anda memperlakukannya seperti seorang magang yang sangat terampil, Anda akan mendapatkan hasil kerja tingkat profesional.
Komunitas pembelajaran opsional: https://t.me/GyaanSetuAi