Explore Convex guides and tutorials on vybecoding.ai. Each guide is a structured, multi-lesson course covering practical techniques, real-world examples, and hands-on exercises for developers at every skill level. Whether you are just getting started with Convex or looking to deepen your expertise, these guides provide the depth and clarity to move forward with confidence.
Claude Cowork + Obsidian: The Under 1-Minute Setup (and What It Unlocks) You create an Obsidian vault, point Claude Cowork at the same folder, and within sixty seconds you have an AI that reads, writes, and reorganises your notes the way a...
RAG in Production: The Minimal, Correct Implementation for LLM Apps RAG (Retrieval-Augmented Generation) powers every LLM app that works with custom data.
Production Claude: Building with the Anthropic SDK Beyond the Chat Interface Claude Code is great for development work, but production AI apps need the Anthropic SDK directly.
Build Your First MCP Server in 30 Minutes: The Practical Guide MCP (Model Context Protocol) has reached 97 million installs. It's the standard way to extend Claude with custom tools, data sources, and reusable prompts.
CLAUDE.md Mastery: Writing Project Instructions That Claude Actually Follows Every Claude Code session loads a single CLAUDE.md file into the context window.
LLMOps: Instrumenting Your Multi-Agent Stack for Production When your agent calls a tool that calls another agent that calls an LLM and something breaks, where do you look?
Google's A2A Protocol: How Agents Talk to Each Other (and Why It Matters) Google's Agent-to-Agent protocol is now governed by the Linux Foundation alongside MCP.
AI Cost Engineering: Token Budgeting, Prompt Caching, and Three-Tier Model Routing Running AI in production at scale isn't cheap — unless you engineer it.
Flat-rate AI subscriptions break when agents — not humans — are the primary users. Discover the four pricing models replacing subscriptions: per-seat, token-metered, session-based, and outcome-based cost-per-resolved-task.
On February 4, 2026 — exactly one year after coining 'vibe coding' — Andrej Karpathy declared the term passé and proposed 'agentic engineering' as the more accurate name for how professionals now build with AI. His distinction: vibe coding remains fine for demos and throwaway projects, but undersells the structured discipline that production-grade AI-assisted development requires.
Most developers jump straight into prompting and wonder why Claude Code fights them. This guide walks through 7 essential setup steps — GitHub repos, CLAUDE.md files, MCP servers, and custom sub-agents — that make every project 10x easier.
Remote Claude Code Terminal Access: Check on Your AI Agent from Anywhere Introduction You start a Claude Code session, give it a big task, and then you need to leave your desk.
Claude Cowork + Obsidian: The Under 1-Minute Setup (and What It Unlocks) You create an Obsidian vault, point Claude Cowork at the same folder, and within sixty seconds you have an AI that reads, writes, and reorganises your notes the way a...
Level: beginner · 150 min read
RAG in Production: The Minimal, Correct Implementation for LLM Apps RAG (Retrieval-Augmented Generation) powers every LLM app that works with custom data.
Level: beginner · 8 min read
Production Claude: Building with the Anthropic SDK Beyond the Chat Interface Claude Code is great for development work, but production AI apps need the Anthropic SDK directly.
Level: beginner · 22 min read
Build Your First MCP Server in 30 Minutes: The Practical Guide MCP (Model Context Protocol) has reached 97 million installs. It's the standard way to extend Claude with custom tools, data sources, and reusable prompts.
Level: beginner · 18 min read
CLAUDE.md Mastery: Writing Project Instructions That Claude Actually Follows Every Claude Code session loads a single CLAUDE.md file into the context window.
Level: beginner · 8 min read
LLMOps: Instrumenting Your Multi-Agent Stack for Production When your agent calls a tool that calls another agent that calls an LLM and something breaks, where do you look?
Level: beginner · 12 min read
Google's A2A Protocol: How Agents Talk to Each Other (and Why It Matters) Google's Agent-to-Agent protocol is now governed by the Linux Foundation alongside MCP.
Level: beginner · 9 min read
AI Cost Engineering: Token Budgeting, Prompt Caching, and Three-Tier Model Routing Running AI in production at scale isn't cheap — unless you engineer it.
Level: beginner · 13 min read
Flat-rate AI subscriptions break when agents — not humans — are the primary users. Discover the four pricing models replacing subscriptions: per-seat, token-metered, session-based, and outcome-based cost-per-resolved-task.
Level: beginner · 16 min read
On February 4, 2026 — exactly one year after coining 'vibe coding' — Andrej Karpathy declared the term passé and proposed 'agentic engineering' as the more accurate name for how professionals now build with AI. His distinction: vibe coding remains fine for demos and throwaway projects, but undersells the structured discipline that production-grade AI-assisted development requires.
Level: beginner · 22 min read
Most developers jump straight into prompting and wonder why Claude Code fights them. This guide walks through 7 essential setup steps — GitHub repos, CLAUDE.md files, MCP servers, and custom sub-agents — that make every project 10x easier.
Level: beginner · 168 min read
Remote Claude Code Terminal Access: Check on Your AI Agent from Anywhere Introduction You start a Claude Code session, give it a big task, and then you need to leave your desk.
Level: beginner · 216 min read