James Li

[Femke Plantinga @femke_plantinga]

A few weeks ago everyone was talking about loops. Now it's graphs.

Both live or die on one thing: your company brain.

This week, Shann Holmberg shared how he runs his marketing on graphs.

Here's the difference (resolving a support ticket):

𝗟𝗼𝗼𝗽𝘀 → you set the frame, the agent owns the path.
Hand it a goal and a bar. It drafts, checks, fixes, and loops until it clears.
You don't pick the steps. The agent does.

𝗚𝗿𝗮𝗽𝗵𝘀 → you draw the path first, the agent fills each node.
read → triage → draft → QA → send, with a checkpoint at each step.
The agent solves each box, but the map is yours.

Every one of those nodes pulls from the same place.

Triage needs past tickets. Draft needs the policy and product docs. That shared context (your company brain) is what each box reaches into as the work moves through. The brain has that map, the graph is that process, inferred explicitly.

𝗦𝗼 𝘄𝗵𝗲𝗻 𝗱𝗼 𝘆𝗼𝘂 𝘂𝘀𝗲 𝘄𝗵𝗶𝗰𝗵?
→ Reach for a 𝗹𝗼𝗼𝗽 when it's one-off work, no clear path yet. Let the agent figure it out.
→ Reach for a 𝗴𝗿𝗮𝗽𝗵 when it's repeatable work you already know the steps for. Lock them in.

Loops are for exploring. Graphs are for scaling.

Which one are you running right now? 👀

[Cursor @cursor_ai]

See how every model compares: https://t.co/61FZktI8K1

[James Li @JamesLi2k77]

@weizekong Great work!

[James Li @JamesLi2k77]

awesome

[Boris Cherny @bcherny]

New in Claude Code: /checkup

Run /checkup to:

1. Clean up unused skills/MCPs/plugins and save context
2. Dedup your local CLAUDE.md against the checked in CLAUDE.md
3. Break up root CLAUDE.md into nested CLAUDE.md's + skills
4. Turn off slow hooks
5. Update your Claude Code to the latest version
6. Enable auto mode by default
7. Pre-approve frequently denied read-only commands

.. And a few other goodies.

/checkup confirms with you before making any changes. Enjoy!

[Aiswarya Venkitesh @AiswaryaVenkit1]

Anthropic engineer:

"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."

In 45 minutes she breaks down how Anthropic builds agents that remember, learn from their mistakes, and get smarter with every run.

Worth more than any paid course you'll find on building agents.

Watch the session

[Chesny @chesny]

EL CREADOR DE CLAUDE CODE YA NO ESCRIBE PROMPTS EN FABLE 5

Boris Cherny, la persona que construyó Claude Code, dijo esto en una entrevista:

"Con Fable 5 no escribo prompts. Escribo loops, y los loops hacen el trabajo. Mi trabajo es escribir loops."

Mientras la mayoría de devs sigue puliendo el prompt perfecto, él ya pasó a otra cosa.

En 30 minutos enseña su setup diario real:

→ Claude Code (Fable 5) + loops + workflows dinámicos
→ Su flujo de trabajo de cada día
→ Cómo aplicarlo desde hoy

Vale más que cualquier curso de 500$.

Gratis. Subtitulado a español e inglés.

Y después lee este artículo:

Todo lo que necesitas saber sobre loops para aplicar lo que cuenta Boris ↓

Guárdate esto.
Ya tienes plan este finde.

[ClaudeDevs @ClaudeDevs]

A second strategy: use Fable 5 as an orchestrator.

Fable 5 plans and delegates to workers (Sonnet 5).

Most tokens are billed at the lower worker rate.

[ClaudeDevs @ClaudeDevs]

A few patterns we frequently use with Fable 5:

Use Fable 5 as an "advisor."

An executor (Sonnet 5) calls Fable 5 for guidance.

Most tokens are billed at the lower executor rate.

[James Li @JamesLi2k77]

@labikyo node.js is much more important than I imagined. Carry on~
Still in school? or working now?

[James Li @JamesLi2k77]

@labikyo any news about you?

[James Li @JamesLi2k77]

@labikyo a twitter life with a photo... I used to be an egg photo.

[James Li @JamesLi2k77]

new photo, new life. I'm back twitter.

[James Li @JamesLi2k77]

.

[James Li @JamesLi2k77]

@lqs MLGB de

[James Li @JamesLi2k77]

@lqs You are 悲剧ed.