Skip to content
~/sph.sh

llm

11 posts

llm
Model Tier or Harness? What Decides Agentic Coding Quality

When a coding agent underperforms, the reflex is a stronger model. On bounded tasks the harness moves the score at least as much; a rule for which lever to pull.

ai-agents · ai-tools · llm +3

RAG Data Preparation: The Foundation That Makes or Breaks Your AI System

Comprehensive guide to preparing data for RAG systems covering document parsing, chunking strategies, contextual enrichment, and embedding optimization

rag · llm · embeddings +2

RAG vs Fine-Tuning vs Off-the-Shelf AI: An Enterprise Decision Framework

A practical 6-level framework for enterprise AI integration: when to use ChatGPT, RAG, MCP agents, or fine-tuning, with a focus on PII and finance compliance.

ai-adoption-strategy · rag · mcp +2

AI/LLM Glossary: 82 Terms Every Developer Should Know

An implementation-focused glossary for developers navigating the AI/LLM landscape - from tokens to agents, RAG to fine-tuning, with code examples.

llm · ai-agents · rag +6

Prompt Engineering for Production Systems: A Systematic Engineering Approach

A technical guide to production-grade prompt engineering: systematic design, security, observability, and cost optimization for enterprise LLM apps.

prompt-engineering · llm · ai-tools +6

RAG Architecture Patterns: Beyond Basic Vector Search

A comprehensive guide to advanced RAG techniques including hybrid search, reranking, GraphRAG, and self-corrective patterns with production AWS implementation examples.

rag · llm · vector-databases +4

FinOps for AI Workloads: Managing LLM Costs in Production

Prompt caching, model routing, token budgets, and semantic caching: how to keep production LLM spend predictable without giving up answer quality.

aws · cost-optimization · llm +3

AI Agent Architecture Patterns: ReAct, Plan-and-Execute, Multi-Agent

The architectural evolution from rule-based chatbots to autonomous AI agents, covering ReAct, Plan-and-Execute, and multi-agent patterns in TypeScript.

ai-agents · llm · architecture +2

LangChain in Production: Patterns That Work and Anti-Patterns That Don't

Lessons from running LangChain in production: the anti-patterns that cause failures, the patterns that work, with code examples and cost optimization strategies.

langchain · llm · production +5

Building an MCP Server in TypeScript: A Production Guide

Learn how MCP standardizes AI tool integration, with TypeScript examples for building servers, managing security, and optimizing performance in production.

mcp · ai-adoption-strategy · claude +3

AI Code Review vs Human Review: What Each Catches

Where AI-assisted code review catches what humans miss, where humans still excel, and how to build effective human-AI collaboration in your review process.

code-review · ci-cd · security +7