David Čampar
35 posts
@ryanflorence What are you studying the most, UX/UI part or backend/network tab?
English
Studying linear UIs today and man they are making my job hard
English
@knowlestech @AmanVirk1 Why is Filament better than Nova? Does it have more features or a cleaner syntax?
English
@campardev @AmanVirk1 Nova is not great something like Filament would be better.
English
Are we (JS devs) using Admin panels?
Laravel has Nova. Rails has Active Admin. Django ships one out of the box. What do we have 👀
Genuinely curious what everyone is using, or if this just isn't a thing in the JS world.
English
@AmanVirk1 Plus, it could be a great revenue stream for AdonisJS Team. A one-time license fee and devs like me would happily pay for it.
Official or not, I'm already thinking about building something like this for my own needs.
English
@campardev Only if there is enough demand 😅
I genuinely feel its a missing piece, but the broader ecosystem have to feel the same.
English
@AmanVirk1 Every time I build a custom solution for a client, I end up creating an admin dashboard from scratch. Having a solid starting point in the AdonisJS ecosystem would be a game changer.
English
eCom advertorials are STILL criminally underrated...
Just today I found 27 new ones being scaled on Meta as we speak.
Want the doc?
RT + Comment “Ecom” to get in DM! (must be following)
English
I've written 12+ guides for AdonisJS Kit so far, and it got me thinking.
Wouldn't it make more sense if these full-stack components could be created on-demand using AI?
Not generic codegen, but something that understands AdonisJS deeply and writes features the way I would
Curious what do you think 🤔
English
This Shopify brand is running 500+ AI-generated ads on Facebook right now
And they’re publishing 25 new UGC-style ads every single day.
No creators.
No studios.
No editors.
All automated powered by Linah AI + Nano Banana + n8n.
I pulled their entire Facebook Ad Library and broke down exactly how they’re doing it.
This workflow is the future for eCom brands that need constant creative testing but hate the pain of coordinating creators, shoots, and revisions.
Here’s the system behind it 👇
→ Their product catalog sits in Airtable.
→ n8n fetches data + ad angles daily.
→ Linah AI generates UGC-style videos (hooks, demos, testimonials, product-in-hand).
→ Each video gets auto-styled for TikTok, Meta, and Instagram virality.
→ Airtable logs every version, performance metric, and winning creative.
The result?
✅ 24/7 ad production
✅ Pennies per video
✅ Consistent brand visuals
✅ Zero dependency on UGC creators
Most brands struggle to make 5–10 new creatives a month.
These guys are shipping 20 a day.
And it’s working their account is packed with hundreds of live AI-generated ads running across multiple angles and scenarios.
This is exactly what Linah AI was built for:
Instant product-in-hand ads.
Endless creative volume.
Faster testing → faster scaling → lower costs.
Want to deploy this inside your brand?
1️⃣ Follow me
2️⃣ Comment "SYSTEM" below and REPOST this post
(I'll DM you the complete system once you follow me)
English
David Čampar รีทวีตแล้ว
Build, test, and optimize MCP tools
x.com/omarsar0/statu…
elvis@omarsar0
Don't sleep on Skills. Skills is easily one of the most effective ways to steer Claude Code. Impressive for optimization. I built a skill inside of Claude Code that automatically builds, tests, and optimizes MCP tools. It runs in a loop, loading context and tools (bash scripts) efficiently to test and optimize MCP tools based on best practices, implementation, and outputs. Heck, you could even run MCP tools within it if you like, but that wasn't what I needed here. One of the most impressive aspects of using Claude Code with Skills is the efficient token usage. The context tiering system is a game-changer compared to using subagents. It's also like having the best context engineer that's extremely aware of its environment and can self-improve context and tools to help the agent (in this case, Claude Code) to be incredibly well-versed at any task you give it. This is the first time I feel like Claude Code really understands the problem, the code, pulls the right context, and fully leverages the power of the filesystem. The name Skills is really clever when you actually think about it. The more I play with it, the more I am seeing how this complements MCP and subagents, but I will share more thoughts on this in a future post.
English
David Čampar รีทวีตแล้ว
The most AWSome Halloween costume. 💀
That face is every on-call engineer that Monday.
English
David Čampar รีทวีตแล้ว
David Čampar รีทวีตแล้ว
Most marketers spend hours daily trying to analyze ads performance
GoMarble MCP + n8n workflow does it in 2 minutes:
-Pulls Meta+ Google + GA4 + Shopify data
-Finds budget waste & opportunities
-Automated reports delivered to email/slack
Comment "GO" & I'll DM you the workflow
English
David Čampar รีทวีตแล้ว
AdonisJS has been around for a decade now 🎉
From a humble idea to a modern, debt‑free framework, thanks to a passionate community pushing it forward.
Read more about the journey & what comes next 👇
adonisjs.com/blog/a-decade-…
English
David Čampar รีทวีตแล้ว
David Čampar รีทวีตแล้ว
David Čampar รีทวีตแล้ว
David Čampar รีทวีตแล้ว
Gemini 2.5 Pro is available in Preview in AI Studio, Vertex AI and the @GeminiApp — stay tuned for general availability in the coming weeks. goo.gle/43O0hMk
English
David Čampar รีทวีตแล้ว
From napkin sketch to fully coded app ✨ Bring your ideas to life with Gemini 2.5 Pro. Learn more about the latest updates to our 2.5 models → goo.gle/4j9roHe #GoogleIO
English