Loading video...

Video Failed to Load

Go Home

Claude Code team: "we oversimplify agentic engineering - like it's just prompts, just loops No. We need to know what we're doing " "I think Fable smarter than we think and we're hobbling Claude" what he means: step 1 → stop rewriting the prompt, give it a tool, the...

11,759 views • 3 months ago •via X (Twitter)

12 Comments

安叫兽|Bird🕊️ 🔶 BNB's profile picture
安叫兽|Bird🕊️ 🔶 BNB3 months ago

别老搓 prompt,先把手脚接上

ALEXYZ's profile picture
ALEXYZ3 months ago

Tools beat prompts every time. Stop hobbling the model.

codila's profile picture
codila3 months ago

exactly, that’s what this video explains

Shoopy's profile picture
Shoopy3 months ago

"we're hobbling Claude" is the right frame bro – the model has it, the harness just won't let it out

Shubh Thorat's profile picture
Shubh Thorat3 months ago

the loop framing is what's holding back most agent products honestly. it's not a loop, it's a state machine with really bad error handling

Fiction's profile picture
Fiction3 months ago

underrated interview honestly, alpha info as always codila

Maxim Titarenko's profile picture
Maxim Titarenko3 months ago

True, oversimplification can hinder progress. In my fleet, leveraging tools strategically allows agents to handle complex tasks without constant prompt rewrites. How do you integrate tool-use with models effectively?

Maximiliano Rodríguez's profile picture
Maximiliano Rodríguez3 months ago

El "dale una tool en vez de reescribir el prompt" es medio camino. La otra mitad es la capa de conocimiento: qué sabe el agente antes de arrancar. En un vertical B2B el 60-70% del laburo no fue el loop, fue codificar el dominio en algo que el modelo pueda usar.

Manish's profile picture
Manish3 months ago

The skill is slowly moving from “writing the perfect prompt” to “designing the perfect environment for the model to work in.”

Addiction's profile picture
Addiction3 months ago

building agent loops requires way more nuance than prompting

ContextFirstAI's profile picture
ContextFirstAI3 months ago

In client deployments, the difference is almost never the model. It's the quality of the context, access to the right tools, and a well-defined workflow. What change has had the biggest impact for your team?

Granite's profile picture
Granite3 months ago

honestly haven't seen this video before how could i have slept on it?...

Related Videos