1. ai
  2. /building

Building with AI

Go beyond autocomplete — connect tools, ship API integrations, and automate multi-step dev workflows.

This section is for developers who integrate AI: MCP servers that expose your data, LLM APIs in Next.js routes, agent loops in the IDE, and RAG when @Files is not enough. Each guide includes runnable patterns; tutorials walk through full projects.

How the Pages Relate

PageWhen you need it
Building MCP ServersConnect DBs, APIs, or docs to Cursor/Claude Code
MCP SecurityAuth, secrets, and team allowlists for MCP
Agent SkillsPortable SKILL.md workflows for repeatable agent tasks
LLM APIsShip streaming chat or tool calling in your app
Structured OutputsReliable JSON from LLMs with Zod schemas
AI Code ReviewPR review workflows with human gates
AI in CI/CDReview bots and failure triage in pipelines
Anthropic APIClaude models, extended thinking, prompt caching
OpenAI APIGPT models, structured outputs, vision, embeddings
Agentic WorkflowsPlan → implement → review in the IDE or CI
RAG for CodebasesLarge repos or product features over private docs
LLM Observability and EvalsTrace calls, monitor tokens, run quality evals

Typical progression: MCP for personal coding → LLM APIs when shipping a feature → RAG when retrieval quality matters → Observability before launch.

Learning Paths

Solo developer

  1. Building MCP Servers — extend your agent locally
  2. MCP Server Tutorial — build and test end to end
  3. LLM APIs — streaming and tool schemas
  4. Anthropic API or OpenAI API — provider-specific setup
  5. Streaming Chat Tutorial — full Next.js chat app
  6. Agentic Workflows — safe multi-step automation

Team lead

  1. Building MCP Servers — approved servers and secrets policy
  2. RAG for Codebases — data residency and what not to index
  3. Security and Prompt Injection — production LLM features
  4. LLM Observability and Evals — monitoring before launch
  5. Team AI Policy — CI gates for agent automation

Start Here If…

Your goalStart with
Connect Postgres or internal API to CursorBuilding MCP Servers
First MCP server from scratchMCP Server Tutorial
Add chat to your Next.js appStreaming Chat Tutorial
Integrate Anthropic / Claude directlyAnthropic API
Integrate OpenAI / GPT directlyOpenAI API
Model misses docs in a large monorepoRAG for Codebases
Agent keeps over-scoping refactorsAgentic Workflows
Production monitoring and quality evalsLLM Observability and Evals
Compare Bedrock vs direct APIAI Platforms

Guides

Building MCP Servers

Expose databases, APIs, and docs to your agent.

Agent Skills

Author SKILL.md packages for repeatable agent workflows.

LLM APIs

OpenAI, Anthropic, Vercel AI SDK, streaming, tool calling.

Anthropic API

Claude models, extended thinking, prompt caching, vision.

OpenAI API

GPT setup, structured outputs, vision, and embeddings.

Agentic Workflows

Plan → implement → review loops and CI integration.

RAG for Codebases

Embeddings, doc indexing, pgvector, when to build vs buy.

LLM Observability and Evals

Trace calls, log tokens, run quality evals before shipping.

Tutorials

Quick References