Zum Hauptinhalt springen
Echtzeit-Radar & Feeds
Alle RSS Feeds ➔
👥 Community & Social
Sicherheitslücken (CVE)CVE-2022-45435 | SailPoint IdentityIQ authorization (EUVD-2022-48307)(02.10.2026 um 06:58 Uhr)
•••••••••
AI & KI NachrichtenRakazo vs ChatGPT dots: Self-Hosting vs Managed AI Teammates(02.10.2026 um 06:42 Uhr)
•
Sicherheitslücken (CVE)CVE-2022-45435 | SailPoint IdentityIQ authorization (EUVD-2022-48307)(02.10.2026 um 06:58 Uhr)
•••••••••
AI & KI NachrichtenRakazo vs ChatGPT dots: Self-Hosting vs Managed AI Teammates(02.10.2026 um 06:42 Uhr)
•
Intelligence View
⚡ tsecurity.de Intelligence

I Spent 6 Hours Per Blog Post Until I Built This AI Content Platform

Three months ago, I was billing clients $25-40 per blog post. Sounds great, right? Wrong. Each post took me 4-6 hours of work: 1-2 hours researching keywords…

Beitrag
0
Seite
0
↗ Quelle (dev.to)
Social ReaktionenReagiere als Erste:r — dein Feedback zählt!

Three months ago, I was billing clients $25-40 per blog post. Sounds great, right? Wrong.



Each post took me 4-6 hours of work:




  • 1-2 hours researching keywords and competitors

  • 2-3 hours writing and editing

  • 1 hour (yes, ONE HOUR) manually converting Markdown to Sanity's Portable Text format



That last part? That's what broke me.






The Portable Text Problem



If you've ever worked with Sanity CMS, you know the pain. Portable Text is powerful, but converting content manually is soul-crushing:




{
_type: 'block',
children: [
{
_type: 'span',
text: 'Just trying to format a simple paragraph...'
}
]
}






Multiply that by 2000 words, add images, links, headings, and you're looking at serious time sink.



I tried existing tools. They either:




  • Broke on complex formatting

  • Didn't support Sanity properly

  • Required manual cleanup anyway

  • Cost more than they saved



So I built my own solution. Then I kept building.






Enter Terradium







What started as a "convert Markdown to Portable Text" script evolved into a full AI-powered content platform.



Here's what it does now:






1. AI Multi-Agent System



I implemented a multi-agent architecture where specialized AI agents handle different parts of content creation:





  • Master Coordinator - Plans the entire content strategy


  • SEO Research Agent - Uses Perplexity AI for real-time competitive analysis


  • Content Writer - Generates SEO-optimized articles


  • Content Improver - Reviews and enhances quality


  • Sanity Publisher - Handles the dreaded Portable Text conversion automatically






2. Content Planning at Scale



Instead of one-off articles, you can generate entire content strategies:




Input: "AI tools for developers"
Output: 12-article content plan with:
- Keyword research
- Topic clusters
- Publishing schedule
- SEO optimization









3. The Electron System



I got tired of unpredictable AI costs, so I built a transparent usage system:




  • Every operation costs "electrons"

  • Real-time balance tracking

  • No surprises in your bill

  • Mix subscriptions with one-time booster packs



Example: Full article with SEO research = 6 electrons (~$0.40-0.60 depending on your plan)






The Tech Stack



Built with modern tools developers actually want to use:



Frontend:




  • Next.js 15 with App Router

  • TypeScript (because we're not animals)

  • TailwindCSS v4

  • Shadcn/ui components



Backend:




  • Convex for real-time reactive database

  • Clerk for auth (JWT integration was smooth)



Key Feature:

Everything is real-time. You literally watch the AI agents work through each step. No black box, no waiting.





What I Learned Building This





1. Streaming AI Responses Are A Game-Changer



E.g., Using OpenAI's streaming API instead of waiting for complete responses:




const stream = await openai.chat.completions.create({
model: "gpt-4",
messages: [...],
stream: true,
});

for await (const chunk of stream) {
// Update UI in real-time
updateProgress(chunk);
}






Users see progress immediately. Huge UX win.






2. Convex Made Real-Time Stupidly Easy



Coming from traditional REST APIs, Convex's reactive queries were mind-blowing:




const content = useQuery(api.content.get, { id });
// Automatically updates when data changes. That's it.






No websockets. No polling. No Redux hell.






3. AI Agents Need Guardrails



Early versions would go off the rails. The solution? Structured outputs and validation:




const schema = z.object({
title: z.string().max(60),
keywords: z.array(z.string()).min(3).max(10),
outline: z.array(z.string()),
});






Now agents can be creative within constraints.






The Beta Launch



I'm launching Terradium in beta at terradium.io this week.



What works:

✅ AI content generation with multi-agent system

✅ Automatic Sanity CMS publishing

✅ Content planning and bulk generation

✅ Real-time progress tracking

✅ Transparent electron-based pricing



What's coming:




  • More CMS integrations (WordPress, Contentful)

  • Custom AI model support

  • Team collaboration features

  • Advanced analytics






Pricing Philosophy



I wanted pricing that doesn't feel like highway robbery:





  • Free tier: 30 electrons (~10 articles) to try it out


  • Fusion: $19/mo for 270 electrons (~90 articles)


  • Reactor: $49/mo for 800 electrons (~265 articles)



Plus one-time electron packs if you need a burst of content.



Compare that to hiring writers at $100-400 per article. Even if you use this for 10 articles a month, it pays for itself.






Try It Yourself



If you're:




  • Spending hours on content creation

  • Fighting with CMS formatting

  • Doing client content work

  • Running a dev blog or documentation site



Give Terradium a shot. The free tier is actually generous (30 electrons), and I'd love your feedback.



Beta access: terradium.io






Open Questions for the Community



I'm still figuring some things out:




  1. Would you want this to work with static site generators (Hugo, Gatsby)?

  2. Is the electron system intuitive or confusing?

  3. What other CMS platforms should I prioritize?



Drop your thoughts in the comments. Seriously, I'm one developer trying to solve a real problem I had. Your feedback shapes where this goes.






TL;DR: Built an AI platform that turns 6-hour blog posts into 10-minute automated workflows. Uses multi-agent AI system, automatically converts to Sanity Portable Text, transparent electron-based pricing.

🔍 CTI & Forensik

Cyber Threat Intelligence & Forensik

Bedrohungsgraph · ATT&CK-Mapping · Exploit-Belege
CTI Threat Relationship Graph
Akteure · Techniken · Beziehungen
2 Knoten · 1 Relationen
CVE / Incident Threat Actor Software MITRE ATT&CK CWE Weakness IoC
Ähnliche Beiträge
🔍 Verwandte News

Auch interessante Nachrichten I Spent 6 Hours Per Blog Post Until I Built This AI Content Platform

Thematisch verwandte Begriffe: Spent, Hours, Blog, Post · 6 Treffer

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

💬 Kommentare werden geladen…
Zum Aktualisieren ziehen
tsecurity.de Icon
Offline-Lesen, Eilmeldungen & 0ms Ladezeit

Installiere tsecurity.de direkt auf deinen Home-Bildschirm für das ultimative Vollbild-Magazinerlebnis ohne Browser-Leisten.

Nächster Beitrag