30 min read
Model Context Protocol: The USB-C Port for AI Applications
Before MCP, every AI agent needed a custom integration for every tool it touched: the M by N problem that does not scale. MCP is the open standard...
Blog
Notes written while building: the Model Context Protocol from the wire up, retrieval and vector memory, load balancing and rate limiting. Long, specific and with the code.
4 posts
6 min read
RAG Simplified: How to Give Your LLM a Long-Term Memory
Fine-tuning a model every time your data changes is costly, slow and forgets nothing on command. RAG stores knowledge in a vector database and...
6 min read
Load Balancing at Scale: Strategies That Keep Systems Alive
A single overloaded server is a single point of failure. Load balancing distributes traffic across a fleet, enabling horizontal scaling,...
5 min read
Rate Limiting: The API Guard You Cannot Ship Without
An unprotected API endpoint is an open invitation to abuse, from scrapers and bots to cascading backend overload. Rate limiting enforces per-client...