AI for Beginners
Best practices for people new to AI, Ubuntu, and the command line. Each topic shows its most recent dated snapshot; open a topic to browse every archived version. Every entry is independently verified — nothing is published until the 3-lens panel clears it.
Running Coding Agents in CI/CD — Beginner's Guide (as of 10 Aug 2026)
A plain-language walkthrough for first-timers on running Claude Code, Codex CLI, or Gemini CLI unattended in a CI/CD pipeline: what CI/CD even is, least-privilege credentials, human approval gates, the dangers of skipping sandbox/approval checks (including a CVSS 10.0 Gemini CLI bug), keeping secrets out of logs, and stopping a runaway agent from running up your bill — as of 10 Aug 2026.
Tool Use & Function-Calling Design Patterns for AI Agents — Best Practices (as of 09 Aug 2026)
A plain-language guide to how AI agents call tools/functions safely: start with the safety rules that matter no matter which AI vendor you use (sandboxing, least privilege, prompt-injection risk, cost surprises), then a short, brief look at Claude's and OpenAI's specific tool-calling mechanics.
Context Management for AI Coding Agents — Beginner Guide (as of 06 Aug 2026)
A plain-language guide to how AI coding agents (Claude Code, OpenAI Codex CLI, Google Gemini CLI) fill up, compress, and lose track of their working memory — including the cost traps that quietly drain a budget. Every fact is carried over unchanged from the 2026-08-06 technical entry.
Running AI Agents on Ubuntu — Beginner Guide (as of 03 Aug 2026)
A plain-language guide to installing and safely running AI agents (Claude Code, Codex CLI, Gemini CLI) on Ubuntu. Every fact here already exists in the fact-checked 2026-08-03 technical entry — nothing new was added or re-fetched.
Gemini CLI Authentication & Data Handling — Beginner Guide (as of 01 Aug 2026)
A beginner-friendly walkthrough of Gemini CLI's login options (API key, Google sign-in, Vertex AI), how each one affects whether Google can use your data to train models, where your login credentials are stored on your computer, and how to keep them safe — including the June 2026 retirement of personal Google sign-in.
Gemini CLI Security for Beginners: Extensions & MCP Integration (as of 01 Aug 2026)
A beginner's guide to Gemini CLI's extension and MCP (Model Context Protocol) system — what an MCP server actually is, why the default trust settings matter, and the real incidents (a CI remote-code-execution bug, a poisoned official extension, fake installer websites) that show what goes wrong, as of August 2026.
Gemini CLI Security Fundamentals — Beginner Guide (as of 01 Aug 2026)
A plain-language guide for beginners to Gemini CLI's safety settings: what each approval mode really does, why 'auto-approve everything' (--yolo) is dangerous — especially for CI bots — why sandboxing isn't on by default, and the real CVE-2026-12537 incident that shows what goes wrong when these are misused, as of 01 Aug 2026.
MCP Security in Claude Code — Best Practices (Beginner Guide) (as of 29 Jul 2026)
How to securely configure, discover, and use MCP servers when Claude Code is the client — covering permission modes, trust settings, sandboxing, tool restrictions, audit logging, the now-final 2026-07-28 protocol changes, and documented real-world incidents (CVE-2025-68143/144/145, CVE-2026-21852) — as of 29 Jul 2026. Written for people new to AI, Claude Code, and the command line.
Building Secure MCP Servers — Best Practices (as of 29 Jul 2026) (Beginner Guide)
Concrete security practices for people building their first MCP server: checking inputs, defending against prompt injection, giving tools only the permissions they need, managing secrets safely, the now-final 2026-07-28 OAuth/authorization requirements, rate limiting, transport hardening, and cleaning up tool output — as of 29 Jul 2026 (Beginner Guide).
MCP Security Fundamentals — Best Practices (Beginner Guide) (as of 29 Jul 2026)
What the Model Context Protocol actually protects (and doesn't) — explained for beginners: the newly finalized 2026-07-28 update, dangerous hidden instructions in tool results, permission scoping, DNS rebinding, supply-chain risks, and real security bugs — as of 29 Jul 2026.
MCP Supply Chain Verification for Claude Code — Beginner Guide (as of 29 Jul 2026)
Beginner-friendly guide to safely connecting Claude Code to MCP servers without exposing your computer to malicious code — refreshed now that the MCP 2026-07-28 specification is final.
Cloud Fine-Tuning APIs — Beginner Guide (as of 26 Jul 2026)
A plain-English guide to training a custom AI model using cloud services — no GPU required. Covers OpenAI, Together.ai, Vertex AI, AWS Bedrock, and OpenPipe, with cost warnings and step-by-step data preparation.
Fine-Tuning and Adapting Language Models — Beginner Guide (as of 26 Jul 2026)
A plain-English guide explaining when to fine-tune a language model versus using simpler approaches, how to prepare data safely, and what traps to avoid — written for people new to AI.
Fine-Tuning with Python PEFT — Beginner Guide (as of 26 Jul 2026)
A plain-English guide to fine-tuning open-weight language models on your own data using Hugging Face PEFT, LoRA, QLoRA, and related tools — with clear hardware requirements, cost warnings, and step-by-step install instructions.
Structured Outputs and Tool Use with Claude APIs — Best Practices (Beginner Guide as of 24 Jul 2026)
A plain-English guide to getting reliable structured output from the Anthropic Claude API using tool use, caching, streaming, and related techniques — written for people new to AI.
Structured Outputs and Tool Use with AI APIs — Best Practices (Beginner Guide as of 24 Jul 2026)
Ten plain-English best practices for getting reliable, machine-readable structured output from AI APIs — covering schema design, validation, streaming, prompt patterns, token budgets, and safe tool execution.
Structured Outputs and Tool Use with AI APIs (Python) — Beginner Guide as of 24 Jul 2026
A plain-English walkthrough of how to get reliable, structured data back from LLM APIs in Python — covering the instructor library, Pydantic v2, LangChain, testing, caching, and async patterns.
RAG Best Practices — Anthropic Claude Ecosystem (as of 22 Jul 2026)
Plain-language guide to building RAG systems with Claude: when to use long context vs. retrieval, document blocks, citations, prompt caching, model selection, and batch processing — no prior ML experience needed.
RAG Best Practices — Generic / Cross-Platform (as of 22 Jul 2026)
Plain-language RAG pipeline best practices for beginners: how to choose chunking, retrieve documents, rerank results, evaluate quality, and stay safe. No prior ML experience needed.
RAG Best Practices — Python Ecosystem (LangChain, LlamaIndex, Haystack) (as of 22 Jul 2026) — Beginner Edition
Plain-English guide to building RAG systems in Python — chunking, hybrid retrieval, vector stores, streaming, evaluation, and security. Beginner-friendly re-leveling of the 2026-07-22 technical entry. Accurate as of 22 Jul 2026.
AI Agent Orchestration — Anthropic/Claude — Beginner Guide (as of 20 Jul 2026)
Plain-language guide to running Claude agents safely: how to avoid runaway costs, keep agents from doing too much, and understand the main building blocks — written for people new to AI and the command line.
AI Agent Orchestration — Generic/Cross-Platform — Beginner Guide (as of 20 Jul 2026)
Plain-language guide to running AI agents safely: when to run steps one at a time vs. all at once, how to handle failures, when to ask a human, how to avoid surprise bills, and more.
AI Agent Orchestration — LangGraph — Beginner Guide (as of 20 Jul 2026)
A plain-language guide to building AI agent workflows with LangGraph: how to store state safely, pause for human approval, remember things across conversations, and avoid the mistakes that cost money or lose data.
AI Agent Evaluation and Testing — Anthropic / Claude Best Practices (as of 18 Jul 2026)
Plain-language guide to evaluating AI agents built on Anthropic's Claude: Console Evaluation tool, Batches API, LLM-as-judge, adaptive thinking for evals, tool-use testing, and safety testing.
AI Agent Evaluation and Testing — Best Practices (as of 18 Jul 2026)
Plain-language guide to evaluating and testing AI agents: golden datasets, LLM-as-judge, regression CI, unit mocking, red-teaming, evaluation metrics, and trajectory evaluation.
AI Agent Evaluation and Testing — Python Tools Best Practices (as of 18 Jul 2026)
Plain-language guide to evaluating AI agents in Python: Inspect AI, DeepEval, RAGAS, LangSmith, Weave, Phoenix, Promptfoo, pytest mocking, and PromptLayer A/B rollouts.
LLM Observability and Monitoring — Open-Source Tooling — Beginner Guide (as of 16 Jul 2026)
A beginner-friendly guide to watching what your AI application does — using Langfuse, Arize Phoenix, W&B Weave, OpenLLMetry/Traceloop, and Helicone — with plain-English explanations of every step and all the warnings you need before running anything.
LLM Observability and Monitoring — Generic / Architectural Patterns — Beginner Guide (as of 16 Jul 2026)
Platform-agnostic observability architecture for LLM applications, explained for beginners: OTel semantic conventions, span trees, structured logging, prompt versioning, golden datasets, LLM-as-judge, drift detection, and SLO design.
LLM Observability and Monitoring — Managed Cloud Platforms — Beginner Guide (as of 16 Jul 2026)
How to instrument and monitor LLM workloads on Datadog Agent Observability, New Relic AI Monitoring, AWS Bedrock + CloudWatch, GCP Vertex AI, and Azure AI Foundry — written for people brand new to AI and to the command line.
AI Agent Supply Chain Verification — Node.js/npm, Explained for Beginners (as of 13 Jul 2026)
A plain-English guide to keeping the packages your AI agent depends on safe — covering lockfiles, audits, behavioral scanners, provenance, typosquats, MCP server pinning, private registries, and safer package managers.
AI Agent Supply Chain Verification — Python (Beginner Guide, as of 13 Jul 2026)
Plain-English guide for beginners: how to protect the Python packages your AI agent depends on from tampering, malware, and fake package names — covering hash pinning, vulnerability scanning, cooldown windows, safe private registries, and more.
AI Agent Supply Chain Verification — What Every Beginner Needs to Know (as of 13 Jul 2026)
Plain-English guide to checking that the AI model files, containers, and code tools you download are safe and unmodified — no prior security knowledge required.
AI Agent Supply Chain Verification — Beginner Guide (as of 12 Jul 2026)
Plain-language introduction to verifying that the AI tools and models you use haven't been tampered with — covering checksums, safe model formats, RAG data trust, and agent permissions.
AI Agent Supply Chain Verification — Python — Beginner Guide (as of 12 Jul 2026)
Beginner-friendly guide to checking that the Python packages and AI models you download are safe before using them.
Vector Store Security — Open-Source Self-Hosted (as of 09 Jul 2026)
Security best practices for self-hosted open-source vector databases (Chroma, Qdrant, Weaviate, Milvus) explained for people new to AI — covering dangerous auth defaults, TLS, Docker isolation, known CVEs (ChromaToast CVSS 10.0, Milvus CVSS 9.3), and patching.
Vector Store Security — RAG Pipeline (as of 09 Jul 2026)
Cross-cutting security best practices for RAG pipelines using vector stores — explained for people new to AI. Covers embedding privacy, retrieval-time access control, data poisoning, prompt injection, audit logging, and GDPR deletion, with plain-language explanations and concrete code examples.
Vector Store Security — Cloud-Managed Services (as of 09 Jul 2026)
Security and access-control best practices for cloud-managed vector stores (Pinecone, Azure AI Search, AWS OpenSearch Serverless, Google Vertex AI) explained for people new to AI — covering dangerous defaults, authentication, encryption, and audit logging in plain language.
AI Agent Memory and State Management — Anthropic/Claude (Beginner Guide, as of 07 Jul 2026)
A plain-English guide to giving Claude-based agents a memory that survives between conversations: how to choose a storage approach, avoid surprise costs, and keep your data safe — accurate as of July 2026.
AI Agent Memory and State Management — Beginner Guide (as of 07 Jul 2026)
A plain-language introduction to how AI agents remember things: what memory types exist, how to store them safely, and what can go wrong — accurate as of July 2026.
AI Agent Memory and State Management — LangChain / LangGraph — Beginner Guide (as of 07 Jul 2026)
How to manage memory and persistent state in LangChain agents and LangGraph graphs — written for people new to AI. Covers which memory tool to start with, how to keep conversation history across sessions, which old APIs to stop using, and a critical security update — accurate as of July 2026.
LLM Cost Management — Beginner Guide (as of 06 Jul 2026)
Eight plain-language practices for keeping your AI API bills under control: what to measure, how to tag your requests, why context grows so fast, caching explained simply, hard budget limits, alerts before damage happens, picking the right model for the job, and checking quality before you go live.
LLM Cost Management — Anthropic/Claude Beginner Guide (as of 06 Jul 2026)
Plain-English guidance on keeping your Claude API bill under control: checking your dashboard, setting a spending cap, picking the right model, caching repeated content, using batch processing, and reading rate-limit signals.
LLM Cost Management — Open-Source Tools Beginner Guide (as of 06 Jul 2026)
Best practices for tracking LLM token usage and costs with Langfuse, LiteLLM proxy, OpenInference/OpenTelemetry, and W&B Weave. Covers integration, budget enforcement, security, self-hosting trade-offs, and alerting.
Prompt Injection Defense — Claude & Anthropic Platform — For Beginners (as of 04 Jul 2026)
Plain-language guide to how Anthropic protects Claude from prompt injection attacks, and what builders using Claude should do first — no programming background assumed.
Prompt Injection Defense for Web-Browsing and RAG Agents — For Beginners (as of 04 Jul 2026)
Plain-language guide to protecting AI agents that browse the web or search documents from hidden attack instructions — no prior security knowledge needed.
Prompt Injection Defense in AI Agents — For Beginners (as of 04 Jul 2026)
Plain-language guide to protecting AI agents from prompt injection attacks — what the attack is, why it matters, and practical first steps — no programming background assumed.
Cursor for Beginners — Best Practices (as of 01 Jul 2026)
Plain-language guide to getting better results from Cursor AI — covering rules files, chat modes, context tools, and the most important safety warnings. No prior AI coding experience needed.
Prompt Engineering for GitHub Copilot — Beginner Guide (as of 01 Jul 2026)
Plain-language practices for getting better results from GitHub Copilot — written for someone who just installed Copilot and has never used an AI coding tool before.
Prompt Engineering for Claude Code — Beginner Guide (as of 01 Jul 2026)
Plain-language, safety-first guide for using Claude Code effectively when you are brand new to AI coding tools. Same verified facts as the technical entry, re-written for first-timers.
Prompt Engineering for Coding Agents — Beginner Guide (as of 30 Jun 2026)
Plain-English guide to getting better results from AI coding tools — covering universal habits every beginner needs, plus a focused look at Claude Code. No software engineering background required.