Trending Society

A fully automated content platform that aggregates trending topics from social media and RSS feeds, processes them through a multi-stage AI pipeline, and publishes SEO-optimized articles, complete with real-time pipeline telemetry, newsletter delivery, and a multi-tenant SaaS admin dashboard.

typescript
nextjs
supabase
cloudflare
vercel

Pipeline Detail: AI Output Tab

Image Brief: Structured Visual Intelligence

What started as a simple blog evolved into a full content platform. The system aggregates from 19 RSS feeds and social platforms, classifies content with AI, enriches it with web research, generates long-form SEO articles with quality gates, creates editorial images, and publishes autonomously, with full cost tracking and observability across every step.

Blog Generations: Key Points, Insights & FAQ Schema

Social Media Tab: Source Embeds

Journey Log: Cost & Timing Waterfall

AI Output: Second Article View

Vision Enrichment: Image Brief Detail

Research Sources & Langfuse Trace Links

FAQ Schema: Structured Data for SEO

Social Media: Multi-Platform Source Embeds

Trigger.dev Dashboard: Production Tasks

The Platform

Trending Society is an end-to-end AI content platform. It processes content from RSS feeds and social media through a multi-stage AI pipeline, and publishes SEO-optimized articles at scale. Every step is observable, every cost is tracked, and the entire system runs autonomously.

Architecture

The platform is a Turborepo monorepo with clear separation of concerns:

Content Site: Next.js 16 on Vercel. Public reader-facing app at trendingsociety.com with RSS feed, news sitemap, and llms-full.txt for AI Engine Optimization (AEO).
SaaS Dashboard: Multi-tenant admin built on MakerKit with role-based access control. Article CMS, newsletter composer, social ingestion grid, media library, and cost analytics.
Pipeline Engine: 96 Trigger.dev tasks across 12 domains (article, social, content, media, cron, sync, AI, editorial, newsletter, video, repurpose, release). Langfuse tracing on LLM calls.
Database: Supabase (PostgreSQL) with RLS, multi-tenant isolation, and event-sourced analytics.

Pipeline

The article pipeline is the core engine. For each piece of source content:

Ingest: Aggregate from 19 RSS feeds and social channels via structured data extraction and RSS automation
Classify: AI categorization and topic extraction with Gemini
Research: Web research enrichment via Tavily for factual grounding
Rewrite: Long-form SEO article generation with quality gates (HTML cleanup, citation audit, FAQ schema)
Image: Editorial image generation via FLUX on Replicate with vision-enriched prompts
Publish: Autonomous publishing with metadata, structured data, and social distribution
Newsletter: Automated weekly newsletter assembly and Resend dispatch

Quality & Observability

AI generations are traced through Langfuse with cost tracking, quality scoring, and prompt versioning, and 15,000+ generations carry a trace. Quality gates catch and fix LLM output issues (hallucinated URLs, malformed HTML, thin content) before any article reaches production.

Scale

500+ published articles across multiple content verticals
2,200+ ingested sources from social media and RSS
13 scheduled tasks handling daily operations
Full cost analytics with per-article cost tracking across all AI services

Get in touch

Email me

Working end to end across design, creative, and engineering, where creativity, collaboration, and ownership build toward the company's goals.

jeffkliu@gmail.com