engineerball

Teerapat Khunpech

[Anatoli Kopadze @AnatoliKopadze]

A Google Cloud engineer just showed how to build a full app with Claude from scratch

he spent 26 minutes live on stage doing what most teams take weeks to do

worth more than any $500 vibe-coding course

here's what he covers:
> zero to deployed app in a single session
> handling five engineering roles alone with Claude
> the exact workflow Google uses internally
> no team, no setup, just Claude and a goal

the people who figure out what Claude can actually do are building things everyone else thinks requires a team

that's exactly why I wrote a step by step guide on how to build your first AI agent

the guide is in the article below

[Ruben Hassid @rubenhassid]

Prompting is dead.

Here's what to actually do instead (in one image):

1. Download the Claude desktop app (free).
2. Create a folder names "Claude Cowork".
3. Create 3 subfolders: about-me, output, templates
4. In about-me, create 3 .md files: about-me, anti-ai-writing-style, my-company.
5. Fill them with your tone, rules & non-negotiables.
6. Download my files (for free) here https://t.co/psB7XxAv8w
7. Don't pay anything. Reply to the welcome email.
8. Open Notion link → .md files folder → download.
9. Go to Claude app → Cowork. Select your folder.
10. Go to Settings → Cowork → Global Instructions.
11. Type: "Always read about-me first."
12. Now write 1-line prompt. It already knows you.

By the way, here's the red flags to know you're still prompting like it's 2025:

1. Your prompts are 500 words. Cowork needs 5.
2. You re-upload the files. They auto-load now.
3. "Act as a copywriter…" Stop. Claude needs files.
4. You created Projects. Cowork is one folder
5. No anti-AI file. So Claude sounds like Claude.
6. You re-explain your tone. Put it in a .md once.
7. Your outputs sound generic. Lack of context.
8. You blame Claude. The problem is missing files.
9. You copy prompts. They don't know your voice.
10. You think "prompting" is a skill. It's already over.
11. You never tried Cowork. The biggest feature.
12. You're still in chat. The top 1% are operating.
13. You never read this: https://t.co/LyV7fegv4c

People still type 500-word prompts in 2026.

You want to help your network upgrade?
♻️ Repost this so they finally try Cowork.

[Samuel Wong @samuel_wong_]

Agentic Engineering - Part 1

https://t.co/12Fmtd9VXD

[Khairallah AL-Awady @eng_khairallah1]

ANTHROPIC JUST RELEASED THE OFFICIAL PLAYBOOK FOR BUILDING A COMPANY WITH CLAUDE CODE.

30 minutes. free. from the engineers who built it.

Bookmark this before you forget.

CEO: 1 human. Employees: AI agents. Operations: fully automatic.

The zero-headcount company is no longer a joke.

[Rishabh @Rixhabh__]

Anthropic pays engineers $750,000+ a year to understand how LLMs work.

Stanford just put a 2 hour lecture that covers 80% of it for FREE.

Bookmark this. Give it 2 hours today.

[Ruben Hassid @rubenhassid]

Instead of watching Netflix tonight.

Spend a day mastering Claude here: https://t.co/Vn60ElPZ2i

→ Level 1 - 24 min: The basics.

Claude For Dummies: https://t.co/HNa5MrCLVU
Claude Setup: https://t.co/jw2qdIcjnh

→ Level 2 - 1 hour: Real workflows.

Claude Cowork: https://t.co/uWTpOI3Woc
Claude for teams: https://t.co/qxlcqhf8bM
Claude Design: https://t.co/ZY8Fg5D2ea
Cowork + Projects: https://t.co/Q7AN9CZAbO
Claude for slides: https://t.co/L0bPMgXci6
Claude Skills: https://t.co/6cHYYfjXEA

→ Level 3 - 3.5 hours: The pro moves.

Avoid sycophancy: https://t.co/5i8xSJBGUl
Claude Code: https://t.co/UgE9xBXVbE
Claude 101: https://t.co/OvBmlvnVqL
Stop hitting Claude limits: https://t.co/j5fEzSH5br
Stop Prompting: https://t.co/j1LATSJiat

→ Level 4 - 8 hours: Expert mode.

Claude Computer: https://t.co/TxYuHPjgbV
Build with Claude API: https://t.co/RcCbfNjlzz

Pro tip: Don't binge it. Do one level per sitting.

Actually apply each guide before moving to the next

[Ramya Chinnadurai 🚀 @code_rams]

Obsidian is the IDE. The LLM is the programmer.
OpenClaw is the build system. The wiki is the codebase.

Implemented Karpathy's LLM Wiki pattern in OpenClaw today. Here's what the spec actually means in practice once agents are writing into it daily.

1. Five page types, fixed taxonomy: entities (real-world things - people, companies, products), concepts (ideas and patterns), syntheses (compiled analysis pulling from multiple sources), sources (raw imports, articles, transcripts), reports (auto-generated dashboards from the rest).

2. Agents must search before they write. Existing pages get appended to, not duplicated. Without this rule, you wake up to twelve duplicate pages a week in.

3. Backlinks are automatic, not optional. Every cross-page reference uses Obsidian wikilinks. Open the graph view, the structure surfaces. Open the same vault without backlinks, you get a folder of orphans.

4. Contradictions get flagged on the page, not silently overwritten. The wiki admits when two sources disagree. The agent writes a tension note, not a confident lie.

5. Multi-agent attribution lives in frontmatter, not folders. One vault, multiple OpenClaw agents writing in. The frontmatter says who wrote what, when, and why. Folders looked clean on paper but broke search and graph view.

6. Single vault is the only model that works. Per-agent vaults seemed cleaner. The plugin doesn't support cross-vault graph or search. Forcing the structure breaks the plumbing.

The catch: the pattern needs strong system prompts in every agent. Without explicit "search before write, file by type, link before duplicate, flag contradictions" rules, agents default to dumping markdown notes into a folder. The pattern is a discipline encoded in prompts, not a feature shipped in code.

Wikis maintain themselves only when the agents writing into them are prompted to maintain them. OpenClaw made the agent layer easy. Karpathy's pattern made the storage layer make sense.

[Tom Dörr @tom_doerr]

AI marketing suite for Claude Code

https://t.co/ASlBCBir7O

[yourclouddude @yourclouddude]

Pov: you finally understood AWS🚀

[Tech Fusionist @techyoutbe]

MLOps on Kubernetes Explained Visually

https://t.co/jdrbsJ4gJS

[Piyush @piyush784066]

Learn Linux by playing games 🎮

1. Kubernetes
https://t.co/jIW4FYnqPv

2. DevOps
https://t.co/8UGmGT0DzH

2. Linux
https://t.co/hcl09eXGyX

3. Git
https://t.co/xYJFoJspz1

4. Python
https://t.co/ToCYmJxWi2

5. 25+ programming languages
https://t.co/bkA0302nGc

[William AI @wiliam23820a]

Public Speaking Secrets From Steve Jobs.

Follow For More, ✅🤝
@shipul2382

[angel @angeldot_]

El equipo de Anthropic acaba de publicar cómo hacer prompts en Claude para sacarle el máximo partido.

24 minutos. Gratis. Directo de los que lo construyeron.

Lo he subtitulado al español.

Guárdalo 🔖

[Sakhil Khan @sakhil_ai]

Most people say "build an AI agent."

Very few know what that actually means.

Here’s the real blueprint to go from idea → working agent 👇

1. Define the job
What problem are you solving?
Who’s the user? What does success look like?

2. Design the brain
Clear system prompt, role, instructions, guardrails
(This is where most agents fail)

3. Pick the right model
Speed vs cost vs intelligence
Don’t overpay for simple tasks

4. Add tools
APIs, databases, MCP servers, custom functions
Agents become powerful when they can act, not just answer

5. Give it memory
Short-term + long-term context
So it learns, adapts, and improves over time

6. Orchestrate everything
Workflows, triggers, retries, agent-to-agent communication

7. Build the interface
Chat, app, API, Slack bot
Make it usable, not just functional

8. Test + improve
Evals, latency checks, real-world feedback
Iteration is the real moat

💡 Truth:
An “AI agent” isn’t one prompt.

It’s a system.

And the people who understand systems…
are the ones building unfair advantages right now.

📌 Save this (you’ll need it when you build)
🔁 Repost for builders
➕ Follow
@sakhil_ai
for practical AI breakdowns (no fluff) 🚀

[Vaishnavi @_vmlops]

AI Harness Engineering
Interview Preparation Handbook

https://t.co/tSb85mN8JO

[Jouhatsu | AI Influence Operator @Jouhatsu_ai]

L’équipe d’Anthropic vient de montrer comment utiliser correctement Claude Code.

30 minutes. gratuit. présenté par la personne qui a créé Claude Code.

Regarde le workshop. Ajoute en signet 🔖

Ça vaut plus que tous les cours à 500$ que t’as failli acheter.

[McKinsey & Company @McKinsey]

Agentic AI is changing how tech services create value.

We’re starting to see four distinct roles take shape, each with a different set of capabilities, bets and trade-offs.

The question isn’t whether to play but where to focus and how to build around it. https://t.co/Kg9LETGDur

[Sebastian Raschka @rasbt]

April was a pretty strong month for LLM releases:
- Gemma 4
- GLM-5.1
- Qwen3.6
- Kimi K2.6
- DeepSeek V4

All are now added to the LLM Architecture Gallery.
More details once I am fully back in May!

[TRAE @Trae_ai]

https://t.co/vdDiOj8k7l

[Google Cloud Tech @GoogleCloudTech]

Our official Agent Skills repository on @github is here!

Skills are a simple, open format for giving agents new capabilities and expertise. Think of a skill as compact, agent-first documentation for a specific tech or task.

Learn more → https://t.co/7w887vz3lE #GoogleCloudNext