3 articles
In AI Agent services, user trust depends not only on the final answer but on how progress is shown during execution. This post compares SSE and WebSocket for token streaming, step status, tool execution events, and intermediate results, with practical guidance for real product teams.
A practical guide to turning AI Agents into real services. Covers Tool Calling, Planner/Executor separation, session state management, human-in-the-loop workflows, failure handling, and cost control.
How to design production AI Agent systems. A practical guide covering the ReAct pattern, Tool Use, Memory management, Multi-Agent orchestration, and safety design.
6 articles
A practical blueprint for a RAG-based AI stock investment Agent. Covers product goals, user scenarios, system boundaries, core components, and end-to-end architecture for a research and paper-trading workflow.
A practical guide to building the RAG data layer for an AI stock investment Agent. Covers price data, news, SEC filings, earnings transcripts, normalization, chunking, metadata, and freshness-aware retrieval.
A practical design for the workflow of an AI stock investment Agent. Covers routing, query parsing, screening, retrieval analysis, quantitative analysis, risk evaluation, and final report composition.
Strong stock analysis is not enough to build a real investment Agent. This post explains position sizing, sector concentration limits, event risk, backtesting design, and paper-trading workflows.
A practical implementation blueprint for a RAG-based stock investment Agent using FastAPI, PostgreSQL, pgvector, Redis, async workers, and domain-separated service modules.
A practical operations guide for a stock investment Agent. Covers paper-trading workflow, human approval, monitoring, alerts, audit logs, failure handling, and the guardrails needed before any real execution.
2 articles
How to build a production-grade AI model inference server with FastAPI and uvicorn. Covers async processing, batch inference, GPU utilization, and Kubernetes deployment.
How to reliably operate LLM-based services in production. Covers cost management, latency optimization, incident response, and monitoring — all from real-world experience.
6 articles
A practical guide to designing RAG systems. Covers document ingestion, chunking, embeddings, vector search, reranking, prompt composition, and evaluation from a real product engineering perspective.
RAG quality starts with data, not the model. This post explains how to choose source documents, clean HTML/PDF/wiki data, attach metadata, and build a production-ready ingestion pipeline.
Chunking and embeddings define the floor of retrieval quality. This post covers chunk size, overlap, heading preservation, code block handling, embedding model selection, and indexing strategy.
Search quality largely defines RAG quality. This post explains dense retrieval, BM25, hybrid search, query rewriting, metadata filtering, and reranking from a practical engineering perspective.
Retrieval is only half of RAG. This post explains how to structure prompts, select and compress context, design citations, and make the system answer safely when evidence is weak.
To move RAG into production, you need quality evaluation, logging, latency tracking, and feedback loops. This post covers retrieval metrics, groundedness, citation accuracy, observability, and operational checklists.