Sude
1.3K posts
@digitalsude
AI-first Growth & Distribution Strategist | Building AI-native Content & Workflow Systems | Driving Scalable Automation Across Digital & Enterprise Ops
Reminiscing on discord got me missing my last visit with my peeps in Turkey 🇹🇷 How many Architects do we have out there???? Time for a return
Peki bu agent chain nasıl tasarlanabilir? Hayal gücümüzü zorlamaya devam. =) Bitcoin'in Proof of Work modeli enerjiyi güvenliğe dönüştürdü. Ama o enerji boşa gidiyor ve anlamsız hash'ler hesaplanıyor. Ya agent'lar aynı enerji ve compute gücünü hem ağı güvence altına almak hem de kendi işlerini yapmak için kullansaydı? Şöyle düşünün: Bir AI agent GPU'sunda inference çalıştırıyor. Aynı anda o compute gücünün bir kısmıyla ağı doğruluyor. Karşılığında token kazanıyor. Token spekülatif bir coin değil, gerçek GPU zamanı ve elektrik tüketimini temsil ediyor. İnsanlar yüzyıllarca altına dayalı para kullandı. Sonra güvene dayalı fiat'a geçtik. Agent'ların "altın standardı" compute ve elektrik olabilir. 1 agent coin = X dakika GPU zamanı. Agent için bu, "$1 USD değerinde" yazan bir stablecoin'den çok daha anlamlı. Çünkü agent dolar harcamıyor. Compute harcıyor. İnsanlar tarafından kapatılamayan, agent'lar tarafından güvenliği sağlanan, paradan ziyade enerji ve hesaplama gücünün temel birim olduğu bir chain. Bu henüz yok. Ama olması gerektiğini düşünüyorum. Ve olacağına da eminim ama ne zaman... Siz ne düşünüyorsunuz? Agent'ların kendi ekonomileri olabilir mi? Yoksa mevcut chainler yeterli mi?
Agentic commerce is here, and it doesn't need stablecoins Today we're launching Slash for Agents so you never have to login to your dashboard again Create cards, set spend controls, and send payments all through your agent over MCP Available to all Slash users today*
dropping out of college in this ai era should be the best decision for your career.
Google just launched one of its best AI tools yet. This is CodeWiki - and it's like Github on steroids. All you have to do is upload an open-source GitHub repo, and CodeWiki turns it into a fully interactive guide. Demos, walkthroughs, flowcharts, chatbots, and more. Never spend time digging through code repos ever again.
🤖 An online hackathon judged by AI agents.
How to make slides with Claude: 1. Task ☑ Define what you want & what success looks like: "I want to build a pptx presentation so that [SUCCESS CRITERIA]." No "make me a deck about X." ↳ That's how you get 10 slides of nothing. 2. Context Files ☑ Upload your expertise and rules as files: "First, read these files completely before responding: [filename.md] — [what it contains]." Stop re-explaining your brand, your audience, your standards every single time. Put it in files. 3. Reference ☑ Show what you're aiming for. Upload an example. "Here is a reference to what I want to achieve: [filename]." No short prompts and hoping AI figures it out. 4. Research ☑ Claude searches before touching a single slide: "Search the web using at least 5 varied searches (trends, data, expert opinions, case studies, counterarguments)." It saves a structured research brief, organized by theme, with source URLs and key data points pulled out. I like to add: "Prioritize 2025–2026 sources. Flag anything where sources conflict or data is thin." 5. Slide Brief ☑ Turn research into a slide-by-slide outline: "Each slide gets: a title, 3 key points, and any specific data/stats from the research that must appear on that slide." No full paragraphs. Gamma will write the final text. Just give it enough structure and data to work with. 6. Rules ☑ Don't jump into making slides (yet): "Do not generate slides yet." "Do not write full paragraphs." A step-by-step approach takes longer, but makes (much) better slides. If you want to be faster, just go straight to Gamma. 7. Generate ☑ Pass the outline to Gamma as a presentation: "Pass gamma-outline.md to Gamma as a presentation using textMode 'generate'. Use theme: [your brand theme name]." Claude connects to Gamma for you. Like magic. 8. Theme ☑ Make sure to use your Gamma theme: "Use theme: [your brand theme name]." If you don't know how, I made a guide for teams at how-to-gamma.ai (scroll to the bottom). After generating, review card by card: → Would I say this out loud? → Does this card earn its place? → Is the data right? 9. Alignment ☑ The prompt starts by asking YOU questions. "Start by using AskUserQuestion to make sure you have enough context from me before researching." Nothing starts until you're both on the same page. This replaces the old prompting era. I teach you how Claude works at claude-co.work. Copy the full prompt template + download my personal .md files for Claude by following this: Step 1: Subscribe for free → how-to-ai.guide. Step 2: You will have two choices: free or paid. Step 3: Choose the free tier. Don't pay for anything. Step 4: Open your welcoming email (wait 30 sec). Step 5: Access my entire prompt library & md files.
Announcing Copilot Cowork, a new way to complete tasks and get work done in M365. When you hand off a task to Cowork, it turns your request into a plan and executes it across your apps and files, grounded in your work data and operating within M365’s security and governance boundaries.
Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.
