Topic / 6 published entries

AI Engineering

LLM integration, RAG pipelines, agent orchestration, vector databases, and AI-powered frontends.

Track
ai-engineering

AI Agent Orchestration

Tool calling, multi-step reasoning loops, event-driven AI pipelines with Kafka/SQS, and human-in-the-loop checkpoints for production agent systems.

#agents#tool-calling#orchestration#kafka

AI Observability & Evals

Monitoring LLM applications in production — latency/cost tracking, hallucination detection, eval frameworks (LLM-as-judge, golden dataset), prompt regression testing.

#ai-observability#evals#llm#hallucination

LLM Integration in Production

Wrapping OpenAI, Anthropic, and AWS Bedrock APIs in production-grade Java/Spring and Node.js microservices — rate limiting, cost control, prompt templates, and guardrails.

#llm#openai#anthropic#bedrock

RAG Pipeline Architecture

Retrieval-Augmented Generation — embeddings, vector search, chunking strategies, context assembly, and production RAG patterns.

#rag#embeddings#vector-search#llm

Streaming AI Responses: SSE & WebSocket in React

Server-Sent Events and WebSocket patterns for token-by-token LLM streaming in Next.js — from API route to React UI with loading states and error recovery.

#sse#websocket#streaming#react

Vector Databases

Pinecone, pgvector, Weaviate, and OpenSearch — how vector similarity search works, index types, and choosing the right vector DB for production.

#vector-db#pinecone#pgvector#embeddings