Knowledge Base
Guides and cheat sheets for practical engineering work
Explore SQL, data, web, and tooling topics with concise explanations and implementation-first examples.
59
Published guides
9
Technical categories
Hands-on
Example-focused writing
RAG Architecture Guide: Building Retrieval-Augmented Generation Systems
Complete guide to RAG: embeddings, chunking, vector stores, hybrid search, and production integration.
OpenAI API Best Practices for Production
Retry logic, streaming, token budgeting, prompt caching, and cost control for the OpenAI API.
AI Agent Design Patterns: ReAct, Tool Use, Memory, and Multi-Agent Systems
Production-ready patterns for AI agents: ReAct, tool-use, memory strategies, and multi-agent orchestration.
Vector Database Comparison: Pinecone vs Weaviate vs Chroma vs pgvector
Compare vector databases for AI: performance, pricing, features, and integration patterns.
LLM Fine-Tuning Guide: LoRA, Data Prep, and Evaluation
When to fine-tune, how to prepare data, LoRA/QLoRA techniques, and evaluation strategies.
AI Cost Optimization: Reducing LLM API Costs in Production
Semantic caching, model routing, Batch API, prompt compression, and token budgeting strategies.
Structured Output from LLMs: JSON Mode, Function Calling, Zod Validation
Get reliable structured output from LLMs using JSON schema, function calling, and runtime validation.
AI Observability: Monitoring LLM Applications in Production
Trace LLM calls, track latency and costs, detect quality regressions, and set up AI dashboards.
Prompt Engineering Guide: Advanced Techniques for Production LLMs
Chain-of-thought, few-shot, self-consistency, meta-prompting, and prompt testing in CI.
LangChain Guide: Chains, Agents, Memory, and LCEL Patterns
Practical LangChain patterns: LCEL, RAG chains, tool-using agents, memory, and streaming.
AI Security: Prompt Injection, Jailbreaks, and LLM Guardrails
Defend against prompt injection, jailbreaks, indirect attacks, and data exfiltration in LLM applications.
Semantic Search: Embeddings, Cosine Similarity, and Hybrid Search
Build semantic search with embeddings, BM25 hybrid search, reranking, and query expansion.
AI Streaming Guide: SSE, ReadableStream, and Edge Deployment
Stream LLM responses token-by-token using SSE, ReadableStream, Vercel AI SDK, and edge functions.
Multimodal AI Guide: Vision, Audio, and Document Processing
Image analysis, invoice extraction, audio transcription, and PDF processing with GPT-4o and Gemini.
Context Window Management: Long Documents and Memory Strategies
Sliding window, recursive summarization, map-reduce, and RAG for managing LLM context limits.
Embeddings Deep Dive: Models, Dimensions, and Production Patterns
Embedding model comparison, batching, caching, deduplication, classification, and recommendation.
AI Testing Guide: Unit Tests, Evals, and Mocking LLMs
Mock LLM APIs, write prompt snapshot tests, build eval frameworks, and integrate into CI.
Model Context Protocol (MCP) Guide: Build AI Tool Integrations
Build MCP servers to connect AI clients to databases, files, and APIs using the open standard.
Function Calling Deep Dive: OpenAI, Anthropic, and Gemini
Parallel calls, forced calling, argument validation, and error handling across all major LLM APIs.
Anthropic Claude API Guide: Messages, Tool Use, Vision, and Cost Control
Claude messages API, extended thinking, prompt caching, streaming, and production patterns.
AI Chatbot Architecture: From Prototype to Production
Session state, context assembly, intent routing, entity memory, rate limiting, and fallback chains.
LLM Router and Gateway: Provider Switching, Fallbacks, and Cost Control
Build an LLM gateway with routing rules, multi-provider fallbacks, and semantic caching.
AI Workflow Automation: Email Triage, Document Processing, and Code Review
Automate email triage, invoice extraction, code review bots, and document classification pipelines.
Knowledge Graphs and AI: GraphRAG and Structured Reasoning
Combine Neo4j knowledge graphs with LLMs for verified facts, multi-hop reasoning, and GraphRAG.
Harness AI Delivery Pipeline: Practical Blueprint
Build a release workflow with eval gates, canary rollouts, and rollback controls.
LLM Evaluation Pipeline Guide for Product Teams
Design robust dataset, scoring, and baseline comparison for production AI quality.
Prompt Regression Testing: Prevent Quality Drift
Catch regressions from prompt changes before deploying to real traffic.
AI CI/CD with Harness: End-to-End Blueprint
Reference architecture for shipping AI systems with operational guardrails.
SQL Cheat Sheet: Complete Quick Reference
A single-page SQL reference for writing, filtering, grouping, and joining faster.
SQL JOINs Explained: Visual Guide
Learn inner, left, and right joins with practical business examples.
Top 20 SQL Interview Questions
Common interview patterns with reasoning and sample solutions.
SQL Window Functions: A Practical Guide
How to rank, compare, and aggregate while preserving row-level details.
SQL GROUP BY Explained with Examples
Build reliable aggregation queries and avoid incorrect grouped results.
SQL Format Best Practices for Teams
Formatting conventions that improve readability and code review quality.
SQL vs NoSQL: When to Use Each
Choose the right data model by workload, consistency, and scaling needs.
SQL Documentation with DDL
Turn schema files into maintainable technical documentation.
PostgreSQL Cheat Sheet
Frequently used PostgreSQL syntax for tables, queries, and functions.
Generate Test Data: CSV and JSON to SQL
Fast ways to generate insert-ready data for local and CI environments.
DDL to Markdown Data Dictionary
Document table structures quickly with a structured markdown dictionary.
JavaScript Cheat Sheet
Core JavaScript syntax and patterns for daily engineering tasks.
Python Cheat Sheet
Practical Python essentials for scripts, automation, and data work.
TypeScript Guide: Types and Best Practices
Use TypeScript types effectively to reduce runtime bugs and ambiguity.
React Hooks Cheat Sheet
A compact guide to state, effects, memoization, and custom hooks.
CSS Flexbox Guide
Design responsive one-dimensional layouts without brittle hacks.
CSS Grid Guide
Build robust two-dimensional layouts with modern grid techniques.
Regex Explained: How Regular Expressions Work
Understand regex building blocks before using copy-pasted patterns.
Regex Cheat Sheet
A quick lookup for operators, quantifiers, groups, and assertions.
Base64 Encoding Guide
When Base64 is useful, and where it should never be treated as encryption.
JSON vs YAML vs XML Comparison
Compare structure, readability, and ecosystem support across formats.
YAML Guide: Syntax and Examples
Write maintainable YAML for CI pipelines, configs, and automation.
Markdown Syntax Cheat Sheet
A fast reference for writing clean Markdown docs and READMEs.
HTTP Status Codes Reference
Interpret and choose status codes that make APIs easier to debug.
REST API Design Best Practices
Conventions for stable, predictable APIs that scale across teams.
JWT Explained: How Tokens Work
Understand JWT structure, validation, and common security pitfalls.
Git Commands Cheat Sheet
Useful Git commands for branch workflows, merges, and history checks.
Docker Commands Cheat Sheet
Key Docker commands for image management and container operations.
Linux Commands Cheat Sheet
Command-line basics every developer uses for ops and troubleshooting.
NPM Commands Cheat Sheet
Daily npm commands for dependency management and script execution.
Vim Commands Cheat Sheet
Core movement and editing shortcuts to speed up terminal editing.