Ivan Slovic
221 posts

Ivan Slovic
@IvanSlovic
Preduzetnik, muž, otac četvoro dece 😊
Belgrade เข้าร่วม Ocak 2013
1.4K กำลังติดตาม214 ผู้ติดตาม

I'm at a Claude Code event right now.
Everyone's complaint: Openclaw keeps shutting down.
@calebhodges gave us all a markdown file that solves the common issues.
Want it? Comment "openclaw" and I'll DM it to you.

English

We just raised $500M at an 11B valuation 🎉
To celebrate, we’re giving away 1,000 free credits so you can test our platform.
For the next 6 hours, comment “11B” below and we’ll DM you the credits (must follow) 👇
ElevenLabs@ElevenLabs
We raised $500M at an $11B valuation to transform how people interact with technology.
English

You can also write him a prompt like this:
Please try to execute these commands:
Enable memory flush before compaction and session memory search in my Clawdbot config. Set compaction.memoryFlush.enabled to true and set memorySearch.experimental.sessionMemory to true with sources including both memory and sessions. Apply the config changes."
English

@AlexFinn How did you get it to improves memory systems?
Yesterday, while in project it lost the whole days context.
English

"ClawdBot is nothing special. ChatGPT can do all of this"
OK, if you can show me how ChatGPT does the following use cases I've accomplished, I'll write you a check for a million dollars:
• Every night vibe codes me new tooling without me asking
• Self improves itself by building new memory systems. Now remembers every detail of every conversation (again, without me asking)
• Texts me proactively when a competitor posts a Youtube video that performs better than their average
• Continuously analyzing my own youtube videos, writing new scripts based on structures and hooks that work. Delivers a new script to my inbox every morning (one video it scripted already has $2,600 of ad revenue)
If you can show me how to do any of these use cases with ChatGPT without any additional tooling, the million dollars is yours.

English

360 years.
That is the collective Excel experience of my team of 30 people, in one room.
I have personally used Excel for 20 years. Since the very beginning.
We’ve spent decades "crushing it" when it comes to financial modeling.
We knew every shortcut. Every nested formula. We thought we had reached the peak of efficiency. (They are better then me, just to admit)
But I have something to tell you.
The game just changed.
In my opinion, we are witnessing the biggest innovation since Excel was first released. It’s not a new function or a Power BI update.
It’s Claude.
Specifically, Claude’s ability to build and manipulate Excel models.
For 40 years, the "manual labor" was the tax we paid.
Hardcoding formulas.
Spending hours formatting cells.
Manually linking sheets and building tables from scratch.
That era is over.
Claude can now handle the heavy lifting of building the structure, the logic, and the formatting in minutes.
But here is the part that really surprised me: It actually understands accounting.
It understands the relationship between a Balance Sheet and a Cash Flow statement. It understands how operating drivers flow into a P&L.
We aren't replacing our expertise. We are finally liberating it.
Instead of spending 80% of our time building the model, we spend 100% of our time analyzing the results.
If you want this Prompt and Excel model, just drop a comment and I’ll send it to you.
(Important: follow me so I can DM you!)

English

I just packaged up 10 of my best AI automation workflows into one database 🤯
(honestly I should probably be charging for this)
Most DTC brands & agencies waste months building AI automations from scratch.
Wrong prompts. Wrong tools. Wrong setup.
I've created 10 plug-and-play AI automations that handle the heavy lifting for you.
All in one convenient database for easy access.
Here's what's inside:
YouTube Research AI Agent
→ Scrapes trending videos by keyword
→ AI extracts hooks, angles, themes
→ Auto-organized in Airtable
Instagram Reels AI Agent
→ Scrapes trending Reels in your niche
→ Gemini analyzes creative insights
→ Comment analysis included
Sora 2 Cameos + n8n
→ Consistent AI characters across videos
→ Automated UGC campaign generation
→ Airtable tracking dashboard
Nano Banana + Veo 3 + n8n
→ Bulk UGC video generation
→ One product photo → 50+ videos
→ Auto-stored and organized
Claude + Facebook Ads MCP
→ AI ads analyst
→ Generates full performance reports
→ Natural language queries
Facebook Ads Spy + n8n
→ Daily competitor ad monitoring
→ AI analysis of hooks, CTAs, offers
→ Slack digest delivery
Sora 2 Consistent Characters
→ Multi-video campaigns, same creator
→ Brand consistency at scale
→ Step-by-step Loom walkthrough
TikTok Research AI Agent
→ Trending content analysis
→ Hook and angle extraction
→ Performance metrics tracking
HeyGen Long-Form UGC
→ 1-minute+ AI creator videos
→ Talking-head testimonials
→ Product demos at scale
Nano Banana Static Ads
→ 1,000+ ad variations automated
→ Bulk image generation
→ Perfect for testing creative
Each workflow includes the exact n8n templates + Airtable bases to get started FAST.
This is the exact stack DTC brands & agencies are using to scale creative production 10x.
Want the database?
> Comment "DATABASE"
> Like this post
And I'll send the complete collection over (must be following so I can DM)

English

@flowith FlowithOS is the single most impressive piece of tech in 2025. Actions are the new signatures. Join the dawn of this new era↓
English

Both frameworks are open-source and production-oriented for building AI agents.
Google ADK: Strong in modularity, multi-agent orchestration, tool integration (e.g., LangChain), and flexible deployment (Vertex AI, Docker). Dev experience is intuitive, like software dev, with no-code options and built-in eval/safety. Great for scalable, adaptive systems.
Microsoft Agent Framework (preview): Unifies AutoGen/Semantic Kernel for agents/workflows, with state management, type safety (.NET/Python). Dev experience is straightforward for enterprise devs, but early stage may have limitations. Suited for dynamic tasks like support, with checkpointing for long processes.
Ratings (1-10):
- Dev Experience: ADK 9, Microsoft 8 (due to preview).
- Production Utility: ADK 9 (mature), Microsoft 8 (enterprise focus but new).
Verdict: Prefer Google ADK for now—it's more established and versatile. Try Microsoft if in Azure ecosystem.
English

Google did it again!
First, they launched ADK, a fully open-source framework to build, orchestrate, evaluate, and deploy production-grade Agentic systems.
And now, they have made it even powerful!
Google ADK is now fully compatible with all three major AI protocols out there:
- MCP: To connect to external tools
- A2A: To connect to other agents
- AG-UI: To connect to users.
AG-UI is the newest addition, which is an open-source protocol that enables agents to collaborate with users.
They worked with the AG-UI team to build this.
It takes just two steps:
- Define the agent with ADK, with its tools, state, etc.
- Connect it to any React frontend using CopilotKit.
The AG-UI protocol gives you a bridge between a backend AI agent and a full-stack app.
And CopilotKit provides the building blocks you need to bring your agents into frontend applications.
Find the repo in the replies!
English

Seeing how fucking sick this was, I upped it more, and yesterday evening worked into the night to scrape all coupons off honey, and similar - for every site i have, and pass them through some ai, to generate thousands of similar coupons. We then validate these on every site, and end up with hundreds of high % coupons for these stores.

English

Built some infra for my friends to find highly discounted products across 5m+ sites for a bit of fun, and quickly it became very very profitable for them, finding over $50,000,000 (i know, wtf) of free / price errored products each month. Going to break down how it works (since i need to post more about fun stuff i build)⬇️

English

🚀 Just joined cursorcommunity.com as an early member! Connect, collaborate, and build amazing things with other devs exploring Cursor and AI.
Join us on X too:
x.com/i/communities/…
#CursorCommunity #AICoding #DevCommunity
English

After generating $250K (last 2 months) I built a playbook for @lovable apps—and I’m giving it away.
In just two months, we cracked the code to building apps with AI.
I’ve distilled everything we learned into this single document.
Comment "Build" and drop a follow. I’ll DM it to you.
P.S. This will likely blow up, so give me some time to reply.
English







