•6 min read
Architecting Context-Aware LLMs: Decoupling State from Cognition
If you've spent any time building LLM-backed applications in production, you quickly run into the...
#ai#python#architecture#webdev
Writing
Notes on building production AI systems, retrieval architectures, agents and backend infrastructure.
•8 min read
Building Event-Driven Python Systems with FastAPI, RabbitMQ and Celery
How to decouple backend architecture and process asynchronous workflows reliably using message queues.
#Architecture#FastAPI#RabbitMQ#Celery#Python
•10 min read
Enterprise RAG: Hybrid Search with BM25, Vector Retrieval and Reranking
Why pure vector search fails in enterprise contexts and how to build a robust retrieval pipeline.
#RAG#Search#Information Retrieval#AI
•7 min read
Designing Multi-Agent Systems with LangGraph
Architecting reliable, graph-based workflows for complex AI agent coordination.
#LangGraph#AI Agents#Python#Architecture
•9 min read
Building Real-Time Voice AI with FastAPI and WebSockets
Architecting low-latency, full-duplex conversational voice agents.
#Voice AI#FastAPI#WebSockets#Python#Architecture