Vadim Nicolai

A comprehensive guide to implementing Langfuse features for production-ready AI applications, covering prompt management, tracing, evaluation, and observability.

Overview​

This guide covers:

• Prompt management with caching and versioning
• Distributed tracing with OpenTelemetry
• User feedback and scoring
• Usage tracking and analytics
• A/B testing and experimentation

This article documents the complete OpenRouter integration implemented in Nomadically.work, using DeepSeek models exclusively through a unified API.

This page documents an AI-first enrichment pipeline that turns a company website into a clean, structured company profile you can safely persist into your database and expose through GraphQL.

This bulk processor extracts structured skill tags for job postings using an AI pipeline that combines:

This article documents an evaluation harness for a Remote EU job classifier—but the real focus is AI observability: how to design traces, spans, metadata, scoring, and run-level grouping so you can debug, compare, and govern LLM behavior over time.

This article documents a production-grade architecture for generating research-grounded therapeutic content. The system prioritizes verifiable artifacts (papers → structured extracts → scored outputs → claim cards) over unstructured text.

You can treat this as a “trust pipeline”: retrieve → normalize → extract → score → repair → persist → generate.

Introduction​

Introduction​