Structured Data Extraction with LLM JSON Schemas
How to use OpenAI's structured outputs to turn unstructured text into reliable database records — without parsing fragile prose.
Read more →How to use OpenAI's structured outputs to turn unstructured text into reliable database records — without parsing fragile prose.
Read more →How to build web scrapers that handle thousands of pages, recover from failures, and parallelize LLM calls without hitting rate limits.
Read more →How to build an evaluation harness that catches LLM regressions before they hit production — using YAML test cases and structured comparison.
Read more →Why wrapping LLM calls in provider classes is essential for production AI features — and how to design the abstraction layer.
Read more →How to build an LLM agent that generates contextual messages by combining conversation history, user preferences, and available data.
Read more →A four-part series documenting the systematic refactoring of a bloated admin controller into clean, reusable patterns.
Read more →A four-part series building an end-to-end AI recruiting pipeline — from scraping job listings to generating personalized candidate messages.
Read more →Let models declare field config, let a resolver infer the rest from ActiveRecord metadata.
Read more →Make your update_field action reusable across controllers with a simple concern interface.
Read more →Stop building filter options inline in your controllers. Extract them to a presenter with memoization.
Read more →Controllers shouldn't know which fields are editable or how to record changes. Extract that to a service.
Read more →Heroku's release phase creates a race condition during destructive migrations. Here's how to rename tables without errors using PostgreSQL views.
Read more →How to use AI tools to refactor code and generate blog content from the same conversation.
Read more →