Skip to content
agentscamp

Advanced Guides

A curated collection of 11 advanced guides for building with AI coding agents.

Guide

Building an MCP Server

An accurate introduction to the Model Context Protocol: server anatomy, transports, and connecting a tool to Claude Code.

9m read· AgentsCamp
Guide

Building Multi-Step Agent Workflows

Patterns for building multi-step agent workflows in Claude Code: decompose tasks, fan-out to parallel subagents, verify every step, and orchestrate.

6m read· AgentsCamp
Guide

Building Agents with the Claude Agent SDK

A working tutorial for the Claude Agent SDK in TypeScript and Python — query(), tool permissions, custom in-process MCP tools, subagents, hooks, and auth.

4m read· AgentsCamp
Guide

Running Claude Code in CI: Headless Mode & GitHub Actions

Claude Code without the terminal — claude -p flags, JSON and structured output, safe permission scoping, and the official GitHub Action responding to @claude.

4m read· AgentsCamp
Guide

LLM API Pricing in 2026: Every Major Model Compared

Per-million-token prices for Claude, GPT, Gemini, DeepSeek, Mistral, and Grok — plus caching and batch discounts — verified against vendor pricing pages.

4m read· AgentsCamp
Guide

LLM Context Windows Compared (2026)

Context windows and max output tokens across Claude, GPT, Gemini, DeepSeek, and Grok — the million-token era, what it costs, and what fits in practice.

2m read· AgentsCamp
Guide

LLM Cost and Latency Engineering: Caching, Right-Sizing, and p95 Budgets

A practical playbook for cutting LLM cost and tail latency — caching, model right-sizing, prompt trimming, and enforced p95 budgets — without losing quality.

3m read· AgentsCamp
Guide

LLM Gateways Compared: Portkey vs Helicone vs LiteLLM for Caching & Cost Control

How Portkey, Helicone, and LiteLLM compare for caching, cost control, and observability — each one's 2026 status and which fits self-hosted vs. hosted.

4m read· AgentsCamp
Guide

Multi-Agent Orchestration

Four patterns for coordinating multiple agents — fan-out, pipeline, orchestrator-worker, and verify/critic — and when each earns its overhead.

10m read· AgentsCamp
Guide

Parallel Claude Code Sessions with Git Worktrees

Run several Claude Code sessions at once without edits colliding — the built-in claude --worktree flag, .worktreeinclude, subagent isolation, and cleanup.

3m read· AgentsCamp
Guide

Sandboxing AI-Generated Code: E2B vs Modal vs Daytona vs Vercel Sandbox

Where should agent-written code run? E2B vs Modal vs Daytona vs Vercel Sandbox compared on isolation, persistence, and cost, plus rules for safe execution.

2m read· AgentsCamp