I built a system that scans Twitter, news websites, and YouTube every morning — filters out the noise, clusters duplicate coverage into stories, and scores everything by relevance. No more doomscrolling 10 tabs to stay informed. In this video I show the full system live and walk you through building your own. Here's the quick setup guide: 1. Connect your data sources Claude Code supports external tools through MCP and API integrations. For this system you need: - Apify — scrapes Twitter/X accounts and YouTube channels. Get an API key at apify.com, add it to your .env as APIFY_API_KEY. Claude Code calls Apify actors via REST API to pull tweets and video metadata + transcripts. - Firecrawl — scrapes any website (blogs, news sites). Get an API key at firecrawl.dev, add it as FIRECRAWL_API_KEY. Claude Code uses it to grab article content from pages like techcrunch.com, openai.com/news, etc. - Kie AI — (optional) for generating visual assets from your trend data. Add as `KIE_AI_API_KEY`. 2. Define your sources Create a list of Twitter accounts and websites relevant to YOUR niche. Mine are 10 Twitter accounts (@OpenAI, @AnthropicAI, @karpathy, @sama, etc.) and 5 news sites. You can track any industry — crypto, biotech, marketing, whatever. 3. Write a Claude Code slash command Create a file at `.claude/commands/trends.md` that tells Claude to: - Fetch latest posts from your Twitter accounts (via Apify) - Scrape your news websites (via Firecrawl) - Filter to news only (drop opinions and commentary) - Cluster items about the same event into stories - Score each story 1-10 for relevance to your niche Then just run /trends in Claude Code and it does everything. 4. Generate a web interface Ask Claude Code to build you a simple Next.js page that displays your stories grouped by day, sorted by score. Mine has color-coded badges (green = high relevance, gray = low), expandable source lists, and voting buttons so the system learns what I care about over time.

New hire submitted paperwork. I-9 missing signature on page 2. Alert hit HR Slack before the folder was opened. Built onboarding processor. Compliance checks automatic. Missing fields flagged instantly. THE ONBOARDING PAPERWORK NIGHTMARE: 15 new hires monthly. Stack of documents per person. I-9, W-4, direct deposit, emergency contact, NDA, benefits enrollment. Each requires manual review. Each has different compliance requirements. Missing signatures discovered days later. THE DISCOVERY: Document extraction identifies document type. Pulls required fields. Code checks completeness and flags missing items. Same extraction handles all document types. Status assigned automatically. THE WORKFLOW: Google Drive trigger watches onboarding folder → Download document → Document extraction pulls employee info, employment details, signatures, compliance fields → Code checks completeness and determines status → Sheets logs to onboarding tracker → Slack notifies HR with status and specific issues. 6 nodes. Compliance gaps caught immediately. THE COMPLIANCE CHECKS: Code validates: - All signature fields completed - Required fields present - I-9 specific requirements met - Emergency contact included Status assigned: Complete / Incomplete / Needs Review. THE DOCUMENT TYPE HANDLING: Extraction recognizes: Offer Letter, I-9, W-4, Direct Deposit, Emergency Contact, NDA, Benefits Enrollment. Different fields extracted based on type. Same workflow handles all. THE TRANSFORMATION: Before: 38 minutes per document for manual review. Missing signatures found days later. HR chasing paperwork. After: Instant compliance check. Issues flagged immediately. Specific missing fields listed. THE NUMBERS: 127 documents processed last month 23 compliance issues caught same-day 12 missing signatures flagged 38 minutes → 3 seconds per document Template in n8n and All workflows in Github