How to scrape Greenhouse and Lever job postings (public JSON APIs, no HTML scraping)
Pull every open role from the public Greenhouse and Lever APIs, add salaries, export to CSV and detect new jobs. Tested Python.
Latest articles
How to convert PDFs to Markdown for RAG (with page numbers, clean chunks and a missing-page check)
A tested, free Python pipeline: PyMuPDF4LLM, heading-aware chunks with page numbers, PDF clean-up and a scanned-page check.
Mining App Store charts and 1-star reviews for app ideas: a worked example (with the weak ideas left in)
Use Apple's free chart and review feeds to find recurring complaints, then read AI-suggested app ideas sceptically. Real run, Python included.
Pulling open jobs from Greenhouse, Lever and Ashby into one feed (and reading hiring signals from it)
Use the public ATS job-board APIs to collect open roles, normalise them and turn per-company counts into hiring signals. Python included.
Turning PDFs, Word files, slides and shared folders into Markdown for RAG (what works and what doesn't)
A hands-on walkthrough of document-to-Markdown preprocessing for RAG: chunks with page numbers, folder links, and catching silent content loss.