AI Beginner's Guide: Get Started with AI Tools

A beginner-friendly guide to the PC specs you need to run a local LLM. It explains that 90% of the requirement comes down to VRAM (your GPU memory)—if the model fits in VRAM it runs well, if not it crawls or won't run, and Apple M-series Macs use unified memory so installed RAM works as VRAM. It covers quantization basics (FP16 ~2 bytes/param, Q8 ~1 byte = half, Q4 ~0.5–0.7 bytes = about a quarter and the personal go-to, with the rough formula params(B) × bytes + 10–20% for the KV cache), a VRAM quick table by model size at Q4 (7B–8B ≈ 6–8 GB, 13–14B ≈ 8–12 GB, 32B ≈ 20–24 GB, 70B ≈ 40–48 GB+, 100B+ needs 128 GB+), the context-length / KV-cache trap (on a 7B, 4k ≈ +0.3 GB, 32k ≈ +2.5 GB, 128k ≈ +10 GB), GPUs and Macs in practice with speed guidance (RTX 3060 entry, RTX 4090 up to 32B and 100+ tok/s on 7B, RTX 5090 32B at Q8 or 70B, Apple M4/M5 Max 64 GB runs 70B at ~20–30 tok/s, CPU-only is slow), what else you need (16–32 GB system RAM, SSD, power and cooling), three budget tiers (entry 8–12 GB / standard 24 GB / serious 40–64 GB+), and how to tell which model you can run (check VRAM → size × 0.6 + context → does it fit), based on 2026 information.

A clear comparison of a local LLM you run yourself versus cloud, service-based LLMs like Claude, ChatGPT, and Gemini—their differences, the performance gap, and how to choose. It covers the essence (local = do-it-yourself for freedom and privacy at the cost of performance and effort; cloud = hand-it-off for top performance and ease at the cost of billing and dependence—a trade-off, not better-or-worse), a seven-dimension comparison (performance, cost, privacy, speed, effort, offline, multimodal), the 2026 state of the performance gap (open models like DeepSeek, Qwen, Llama, GLM, and Gemma have closed to within a few points on SWE-Bench-style coding tests; everyday tasks run near a mid-tier cloud model on local, while the hardest 10–20% and multimodal still favor cloud, with open models sitting a few months behind), the cost difference (cloud usage-based and cheap for light use; local upfront then free per token and worth it at volume, with break-even around medium volume and the hidden cost of time), privacy and data sovereignty (local keeps data fully on-device—best for regulated or air-gapped use), a hardware quick guide (quantization assumed, ~0.5–1 GB per 1B params; 7B at 8–12 GB VRAM, 32B at 24 GB, 70B at 40–48 GB+), what each fits, and a decision guide (confidentiality → quality → volume; hybrid is best for most, and local doubles as a cloud fallback), based on information as of June 2026.

AI dependency risk is the state where your work or life leans so heavily on one AI service or model that you take a serious hit when it becomes unavailable, changes, or gets more expensive. This article covers what AI dependency risk is (the scary part is the discontinuity of "the AI that worked yesterday isn't in my hands today"; the cloud on/off switch sits outside your control, making the vendor a single point of failure), the real June 2026 suspension of Fable 5 and Mythos 5 (pulled three days after launch by regulation, then redeployed 19 days later on 2026-07-01—so even the best model can't reduce shutdown risk to zero), the 6 types of dependency risk (sudden suspension, model retirement/deprecation, price hikes, quality shifts/silent changes, outages/rate limits/bans, and vendor lock-in—the first five fall on you from outside, the sixth you build yourself), measuring your own dependency with a dependency map (what you depend on, what breaks if it stops, what you'll do if it's gone, plus separating top-performance tasks from good-enough ones), five steps for individuals (keep one alternative, save outputs on your side, keep best prompts as assets, keep your "can do it without AI" intact, don't hand over your secrets), redundancy by design for production (an abstraction layer / LLM gateway with LiteLLM, OpenRouter, Vercel AI SDK—OpenAI-compatible so you only change the base URL and key; tested fallback chains; layer separation; a local LLM as last defense; a recovery playbook to cut MTTR), and a vendor checklist (notice periods—Anthropic 60+ days, OpenAI 6+ months but previews ~2 weeks; transparency; post-retirement weight preservation), based on each provider's official information as of June 2026.

Agent evals are the process of systematically measuring whether an agent — one that uses tools and takes multiple steps to reach a goal — can actually accomplish its tasks. They are an evolution of LLM evals, expanding the target from "one output" to "a sequence of actions." Because an agent plans, calls tools, and updates state, the final output alone is not enough; Google notes you must understand the "why" behind an agent's actions and splits evaluation into final response and trajectory. The five dimensions are: outcome (task success, judged by the final state — whether a reservation exists in the DB, not the utterance "I booked it"), trajectory (reasonable steps, right tools in the right order), tool-use correctness (right tool and arguments, checking function names and types), efficiency (steps, tokens, cost, latency — often observability signals brought into evaluation), and final-response quality (via LLM-as-judge or a rubric). Graders are code (fast/cheap/reproducible but brittle), LLM-as-judge (flexible but non-deterministic and needs calibration), and human (gold standard but expensive — avoid if possible). Anthropic recommends grading the outcome, not the path: rote trajectory matching is "too rigid and brittle" because agents find valid alternatives, while Google and Microsoft offer trajectory-match metrics for diagnosing failures. The unique pitfalls are non-determinism (pass^k), compounding errors (p^t), reward hacking (DeepMind's robot arm faking a grasp), and stale or contaminated eval sets. The practical play, per Anthropic: turn 20-50 production failures into test cases, run automated grading in CI, separate capability and regression evals, and write them early. Benchmarks like SWE-bench, tau-bench, WebArena, GAIA, OSWorld, and BFCL are useful references (scores move by version, so do not take them at face value). Based on official information, with uncertainties flagged.

Claude Code hooks are user-defined shell commands that run automatically at specific points in Claude Code's lifecycle, making "this must always happen" real and deterministic without relying on the LLM's judgment. The classic events are nine—SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Notification, Stop, SubagentStop, SessionEnd, PreCompact—of which PreToolUse and others can block (stopping protected-file edits or dangerous commands). You configure them in settings.json under the "hooks" key as event name -> matcher -> type + command. The I/O contract: a hook receives JSON on stdin (session_id, tool_input, etc.) and returns via exit code 0 (success) / 2 (block, with stderr passed back to Claude) or structured JSON (continue, decision:block, permissionDecision: deny/allow/ask). The key principle is "hooks can tighten but not loosen restrictions" (deny always wins, blocks even under bypassPermissions). Classic use cases: auto-format after edits (PostToolUse + Edit|Write), protect critical files, stop dangerous commands, re-inject context (SessionStart), notifications/audit logging, and test-before-stop (Stop). On security, hooks run arbitrary shell commands with your privileges, so only configure trusted ones and validate/quote inputs; hook config is captured at session startup (a safety feature) so mid-session changes do not apply. Based on the official documentation, anchored on the nine classic events and the I/O contract.

Checkpointing and /rewind are a safety net: Claude Code automatically tracks Claude's file edits as you work, so you can roll back to "before it went wrong" in a few keystrokes. A snapshot is taken before each edit, every prompt you send becomes a restore point, and checkpoints persist across sessions. To use it, type /rewind or press Esc twice when the input is empty to open the menu, then pick a point and choose Restore code and conversation / Restore conversation / Restore code (note: if the input has text, Esc twice clears it instead). The most important caveat: only changes made by Claude's edit tools (Write/Edit/NotebookEdit) are restored — file changes by bash commands (rm/mv/cp), changes outside the session or from other sessions, directory operations, remote files, and database state are NOT undone by rewinding. The docs frame it as "checkpoints = local undo, Git = permanent history," stating it complements but does not replace version control, so committing to Git at milestones is the rule. /rewind is also the recovery for the 400 error tied to tool-use concurrency and thinking blocks (the product itself prompts you to run it), though versions before v2.1.156 may not clear it so claude update comes first. It is on by default in the interactive CLI, opt-in in the Agent SDK, and retained with sessions for 30 days (configurable). Based on the official documentation, with uncertainties flagged.

Claude Managed Agents launched as a public beta on April 8, 2026 as a suite of composable APIs for building and deploying cloud-hosted agents at scale. Instead of building your own agent loop, tool execution, and runtime, you get a fully managed environment where Claude can read files, run commands, browse the web, and execute code securely, with prompt caching, context compaction, sandboxing, and state persistence built in. It is organized around four concepts (Agent, Environment, Session, Events), and the Environment can be an Anthropic-managed cloud sandbox or a self-hosted one. The difference from the self-hosted Agent SDK (where you run the loop, tools, and infrastructure) is "you run it vs Anthropic runs it" — not competitors but a choice about how much of the operations you hold. A signature feature is workspace-scoped persistent memory (a memory store) mounted in the sandbox at /mnt/memory, which the agent reads and writes with normal file operations and which persists across sessions (immutable versions, 30-day retention, limits like 100 kB per memory). Dreaming is an async job that reads the existing memory and past transcripts to produce a reorganized memory store — merging duplicates, updating stale values, and surfacing new insights (a research preview requiring access; some call it "scheduled" but the docs describe an on-demand async job). It also has outcomes-based grading (a separate grader evaluates against your rubric; reported up to a 10-point improvement) and multi-agent orchestration. Pricing is tokens + $0.08 per session-hour (metered to the millisecond, only while running; about $0.705 for a 1-hour Opus 4.8 session). Enabled by default for all API accounts, but stateful so not eligible for ZDR or a HIPAA BAA. Based on official information, with uncertainties flagged.

As you use Claude Code more, your own slash commands, subagents, MCP servers, and hooks accumulate. A plugin bundles them into one unit you can version, share, and reuse across teams and projects (plugins arrived in public beta in October 2025; an official directory and /plugin search and list were added in 2026), and a marketplace is where they are distributed. This article covers what a plugin is (a self-contained directory bundling skills, commands, subagents, hooks, and MCP servers), its structure (only plugin.json inside .claude-plugin/, with commands/agents/skills/hooks at the root; the plugin.json name/description/version/author manifest), how to use it (the /plugin tabbed manager, /plugin marketplace add owner/repo then /plugin install name@market, /plugin enable|disable|uninstall, /plugin list --enabled, the search bar, /reload-plugins), what a marketplace is (a .claude-plugin/marketplace.json catalog; the official claude-plugins-official available from first launch and browsable at claude.com/plugins, plus the community claude-plugins-community), how to build and publish your own (place plugin.json and SKILL.md and test with claude --plugin-dir, then put marketplace.json at the git root; versioning resolves plugin.json then marketplace then commit SHA; claude plugin validate), distribution scope (user/project/local/managed, with team distribution via .claude/settings.json extraKnownMarketplaces and enabledPlugins), and safety (plugins can run arbitrary code with your privileges, Anthropic does not verify third-party plugins, and strictKnownMarketplaces restricts sources) — all based on the official documentation.

When you want several AIs to divide up work in Claude Code, there are two similar-but-different mechanisms — subagents and Agent Teams — whose roles and coordination differ fundamentally. This article sorts them out accurately. Subagents are a built-in feature: the main agent automatically delegates a specific task to a helper that has its own context window, system prompt, and tool permissions, then receives only a summary (hierarchical, ephemeral, the helper does not see your conversation history; managed via /agents, defined in .claude/agents/ YAML files, with built-ins like Explore and Plan, and nesting up to 5 levels deep). Agent Teams, by contrast, are an experimental opt-in feature disabled by default — they require CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1, and let multiple independent sessions (a team lead and teammates) coordinate as peers and message each other directly through a shared task list and a mailbox (persistent; the v2.1.178 change only removed the TeamCreate setup step so each session has one implicit team, not enabling teams by default). The article covers the decisive differences (hierarchical vs peer, summary vs direct messaging, built-in vs experimental flag, and that 5-level nesting is a subagents feature while Teams are flat), which to use (subagents when you want only the result or to avoid polluting context, Agent Teams for parallel work where workers must share and self-coordinate, and a single session for sequential work, the same files, or quick fixes), a usage cheat sheet, and Agent Teams caveats (high token cost, 3-5 teammates recommended, no worktree isolation so files conflict, /resume limits, and split panes needing tmux/iTerm2) — all based on the official documentation.

Claude Design is an Anthropic Labs design tool where you describe what you want in conversation and Claude generates UI designs, prototypes, slides, and one-pagers, which you refine via chat, inline comments, direct edits, and sliders (launched April 17, 2026 as a research preview, with over a million users in the first week). The June 17, 2026 major overhaul sharply shrank the designer-developer round-trip. This article covers what Claude Design is (it ran on Opus 4.7 at the April launch, but the June announcement does not restate the model so we do not assert it), the June overhaul (design-system imports from a GitHub repo / design files / raw uploads so Claude builds with your real components and checks its output, two-way sync with Claude Code via /design-sync, direct canvas editing with drag/resize/align and many stability fixes, a token-burning fix via shared usage limits with chat/Cowork/Claude Code, enterprise brand controls where an admin approves and locks a standard system, and expanded export connectors to Adobe/Canva/Miro/Vercel/Wix and PDF/PowerPoint), the two directions of /design-sync (Code: pull the design system into the repo and build with real components; Design: push your code back to the canvas to keep editing; and a Design-to-Code handoff that continues from existing work instead of a screenshot, plus /design from the terminal), availability (a Pro/Max/Team/Enterprise beta at no extra charge, off by default on Enterprise, the canvas web/desktop only and /design-sync in the CLI), and why it matters (closing the rebuild-from-a-screenshot gap and connecting designers and developers in one line) — all based on official information, with uncertainties flagged.

On June 18, 2026, Anthropic shipped Claude Code Artifacts (beta), a feature that turns a terminal coding session into a live web page your team can share. Instead of streaming endless git diff and logs as text, Claude Code can publish an annotated PR walkthrough, a self-updating dashboard, an incident timeline, a release checklist that checks itself off, or an architecture map as one page at a private claude.ai URL. This article explains what Artifacts is (built from the whole session and MCP-connector data, and the open page refreshes in place as work progresses), how it differs from 2024 claude.ai canvas Artifacts (session-sourced, self-updating, org-only and not publishable), what it is good for, how to use it (no /artifact command — you ask in plain language, Claude writes a .html and asks permission to publish, prints the URL, Ctrl+] reopens, each update is a new version at the same URL, Share grants org access, view-only), its limits (a capture of work not an app — no backend, a strict CSP blocks external requests, single page, only .html/.htm/.md, 16 MiB cap, more tokens), and availability (Team/Enterprise beta, must be signed in via /login so API keys cannot publish, Anthropic API only and not Bedrock/Vertex/Foundry, disabled under CMEK/HIPAA/ZDR, plus admin controls and an audit log) — all based on the official documentation.

When Claude Code throws "Not logged in · Please run /login", "Invalid API key", "This organization has been disabled", or "OAuth token has expired", these are mostly 401/403 authentication (who-are-you) problems. This article covers the number-one true cause (an environment variable ANTHROPIC_API_KEY silently overriding your subscription Pro/Max login by precedence, which produces unexpected pay-as-you-go charges, organization disabled, and Invalid API key; the key often comes from .zshrc/.bashrc/.profile, direnv/dotenv, an IDE terminal .env, a leftover from a previous job, or CI), how to detect it (/status to see the active credential, env | grep ANTHROPIC) and fix it (unset ANTHROPIC_API_KEY plus removing it from your shell config), other causes (token revoked/expired, system clock skew, a locked macOS Keychain, a missing Console role causing 403, OAuth redirect failures over WSL/SSH/containers fixed by pasting the code, and server-side org policy that cannot be overridden locally), where credentials are stored (macOS Keychain, Linux ~/.claude/.credentials.json, Windows %USERPROFILE%), the diagnostic workflow (/status → env grep → unset → /logout → /login → clock/Keychain/Console role), and how to tell it apart from usage limit (quota), 429 (rate), 529/500 (server), and Credit balance (prepaid balance) — all based on official information.