Posts
Building Production LLM Orchestration from Scratch
How we built a multi-model inference pipeline with ReAct agents, type-safe tool execution, and provider-agnostic abstractions — serving real B2B customers.Read More →
Designing RAG at Scale
From embeddings to reranking — how we built a production RAG system with contextual document enrichment, multi-stage retrieval, and autonomous knowledge gap detection.Read More →
Empowering Internal Teams
Crafting an AI-Powered Slack AppRead More →