I build production-ready Apify Actors for structured web data, monitoring, and AI/MCP workflows—focused on clean outputs, reliability, and compliance.

• Job & company data (Workday and other public career sites)
• Market / news / brand monitoring pipelines
• Docs & content prep for LLM and RAG workflows
• MCP tooling (OpenAPI → MCP, reliability checks)
• Scheduled extraction with stable schemas and clear logs

• Stock Market News Scraper  — tickers, Google News, India & crypto sources → structured JSON
• Workday Jobs Scraper  — public Workday listings with filters and API-friendly output
• Docs-to-RAG Optimizer  — public docs → clean Markdown / RAG-ready content
• AI Training Data Curator  — public sites → clean LLM training datasets
• Patent & IP Filing Monitor  — recurring USPTO monitoring for assignees & inventors
• Bluesky Brand Monitor  — brand mentions, keywords, and alerts on Bluesky

• Public data only
• Polite crawling (retries, rate limits, sensible concurrency)
• Stable schemas, deduplication, and clear run logs
• Pay-per-event pricing when it helps users control cost

Message me with target URLs, fields, volume/schedule, and constraints (proxy, geo, freshness).