GUIDES / 02
Guides
Problem-focused AI solutions covering common scenarios, recommended tools, and complete implementation steps.
Series
Learning paths
Follow a related set of guides in sequence.
- PATH 0112 guides
AI AGENT Beginner's Guide
Start with「AI Agent Beginner Tutorial: 01 - Concepts, Examples, and Technical Background」
- PATH 025 guides
Ai Side Hustle
Start with「Systematizing Faceless YouTube: High Retention AI Workflows」
- PATH 0328 guides
WorkBuddy In Action
Start with「WorkBuddy Practical: 01 - Introduction to WorkBuddy」
Curriculum
All guides
- 01AdvancedCost: Free
Agent Tools and Interoperability with MCP: A Guide to Building Standardized and Secure Tool Integration
Based on the whitepaper by Mike Styer and Kanchana Patlolla, this guide strictly follows the original ten sections of the whitepaper, exploring how AI agents use tools to bypass static prediction limits. It covers the classification of Function, Built-in, and Agent tools, details how the Model Context Protocol (MCP) solves the N×M integration nightmare with an N+M architecture, and analyzes security vulnerabilities like the Confused Deputy and Tool Shadowing alongside enterprise defense strategies.
- 02AdvancedCost: Free
Context Engineering: An Architecture Guide to Sessions and Memory for Stateful Agents
Based on the whitepaper by Kimberly Milam and Antonio Gulli, this guide explains how Context Engineering assembles state for each model call, how Sessions hold the events and working state of one conversation, and how Memory extracts, consolidates, and retrieves durable information across sessions. It also covers long-context compaction, the division between RAG and Memory, procedural memory, privacy, production architecture, and evaluation metrics.
- 03IntermediateCost: Free
The 12 Rules of Harness Engineering: Cassie Kozyrkov's Guide to Supervising AI Agents
This guide organizes Cassie Kozyrkov's 12 rules of Harness Engineering and explains how humans can own intent, boundaries, and judgment while agents execute inside a legible, verifiable environment. It also provides a minimal implementation checklist and clarifies correction, observability, and human-escalation boundaries for high-throughput development.
- 04AdvancedAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 12 - Evaluation, Production Deployment, and the Capstone
Build a regression baseline with 20 stratified tasks, traces, and environment outcome checkers, then run the agent in idempotent queue workers with checkpoint recovery, cost budgets, version labels, canaries, and rollback. The final deliverable is a reproducible research-brief agent.
- 05AdvancedAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 11 - MCP and Multi-Agent Systems
Connect controlled external capabilities through MCP hosts, clients, servers, tools, resources, and prompts, then compare manager, agent-as-tool, and handoff patterns against a single-agent baseline. A split must produce measurable quality or maintenance gains.
- 06AdvancedAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 10 - Workflows and Development Frameworks
Use a decision tree to choose sequences, routing, parallelism, and dynamic planning, keeping deterministic steps in workflows, then migrate to the OpenAI Agents SDK under shared behavioral tests. LangGraph remains an extension for explicit graph state and checkpoints.
- 07IntermediateAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 09 - State, Memory, Human Approval, and Security
Separate run state, sessions, checkpoints, and long-term memory, then add persistent approval for writes. Finally, verify least privilege and sandbox boundaries with prompt-injection, path-traversal, and exfiltration fixtures.
- 08IntermediateAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 08 - Skill Design and Loading
Separate the roles of skills, tools, RAG, and prompts, then package task methods with SKILL.md, references, and scripts. The lesson implements a skill catalog, on-demand loading, version recording, and minimal context injection.
- 09IntermediateAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 07 - RAG, Context Engineering, and Citations
Build a local RAG baseline through source cleaning, chunking, and keyword recall, then layer system rules, task, evidence, and history in context. Structured claims and source IDs make each citation in the final brief verifiable.
- 10IntermediateAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 06 - Tool Systems
Move scattered functions into a tool registry and handle schemas, permissions, result limits, timeouts, bounded retries, stable errors, and business idempotency by side-effect level. A failure matrix verifies every recovery policy.
- 11BeginnerAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 05 - Testing and Debugging
Pause feature work to define inputs, permissions, budgets, outputs, and acceptance rules, then reproduce success, argument repair, and budget exhaustion offline with a fake model. Later capabilities share this behavioral baseline.
- 12BeginnerAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 04 - Function Calling and the Agent Loop
Connect a local search tool to the simple agent and implement tool schemas, call requests, allowlisted execution, result return, and a multi-turn loop. Success, failure, and budget-exhaustion exits give the project complete agent control flow for the first time.
- 13BeginnerAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 03 - Basic Structure and Project Setup
Connect one live model call from an empty project and define Goal, State, Action, Observation, Tool, Runtime, and Stop Policy with data classes. An offline model keeps the structure independently testable before the loop is added.
- 14BeginnerAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 02 - Use Cases and Project Design
Judge whether a requirement fits an agent through path uncertainty, tool needs, feedback loops, risk, and acceptance cost, then freeze the allowed capabilities, forbidden actions, and four-stage delivery line for the research-brief project.
- 15BeginnerAI AGENT Beginner's GuideCost: Free (API usage varies)
AI Agent Beginner Tutorial: 01 - Concepts, Examples, and Technical Background
Use research briefs, ticket routing, and rewriting to understand chat, workflows, and agents, then trace the technical progression through LLMs, structured output, function calling, tools, and agent runtimes. The result is an agent-loop map used throughout the series.
- 16IntermediateCost: FreeGPT-5.6 SolGPT-5.6 TerraGPT-5.6 Luna
GPT-5.6 vs Claude Sonnet 5 In-Depth Selection Guide: Coding Agents Need More Than Token Prices
GPT-5.6 and Claude Sonnet 5 make Coding Agent selection more complex. GPT-5.6 is split into Sol, Terra, and Luna, each with adjustable reasoning effor…
- 17BeginnerCost: Paid
Getting Started with Loops in Claude Code
At the Claude Code team, Loops are defined as: An AI Agent repeatedly executing work cycles until a preset stop condition is met. To make it easier to…
- 18IntermediateCost: Free
Comparing AI Programming Workflows: grill-me's Relentless Questioning vs Superpowers' Autonomous Reviews
grill-me and Superpowers are highly popular AI programming workflow tools that have gained significant traction in the developer community. While thei…
- 19IntermediateAi Side HustleCost: Free
New Freelance Models: High-Value Delivery via Context Engineering
On platforms like Upwork, quotes for 'Prompt Engineers' have collapsed to $25-$45 per hour. True high-value contracting has shifted to 'Context Engine…
- 20BeginnerAi Side HustleCost: Free
AI and Affiliate Marketing: Distributing and Monetizing High-Premium Digital Assets
Digital product sales have evolved from static content to functional tools in 2026. Creators now package specific solutions, such as ready-to-run AI A…