AI Beginner's Guide: Get Started with AI Tools

"Your credit balance is too low to access the Anthropic API" (shown as "Credit balance is too low" in Claude Code) means your Claude Console organization doesn't have enough prepaid credits. There are two causes: your balance really is too low, or you meant to use a plan such as Pro or Max but Claude Code is running on an API key from the ANTHROPIC_API_KEY environment variable and billing the API instead. You tell them apart with /status. Based on Anthropic's official documentation and Help Center (checked October 26, 2026), this article explains how the error appears, three questions to find the cause, how to buy credits under Billing in the Console and set up auto-reload, how to remove the API key on macOS, Linux and Windows and check it in VS Code, how this differs from the monthly API credits for Max and Team and from usage credits, and similar but different errors.

An NPU (Neural Processing Unit) is a dedicated PC chip that handles AI computations with little power. ChatGPT, Claude, and Gemini run on servers, so an NPU does not change their speed, but on-device AI such as Windows Copilot+ PC features (Recall, Live Captions translation; 40+ TOPS NPU, 16GB memory, and 256GB SSD required) can use it. Local LLMs still rely mainly on the GPU and memory, and this article explains the differences from CPUs and GPUs, TOPS performance from Intel, AMD, Qualcomm, and Apple, and how to choose a PC.

You don't need a high-end PC to run Claude Code or Codex. Both run their models on servers, so buying a new PC won't shorten the time the AI spends thinking and writing. Claude Code's CLI requires at least 4GB of RAM, an x64 or ARM64 CPU, and an internet connection, while Codex publishes no RAM or CPU figures. Your PC affects the time spent running commands locally, such as builds, tests, and searches. This article compares requirements, fast mode, per-OS sandbox conditions, and fixes for heavy workloads, and explains how to measure where your time goes and the three things to check before buying new hardware.

Claude Code's /goal lets you write down what counts as done. A separate small model checks the condition after each turn, and Claude keeps working until it is met. The article covers setup, checking, and clearing /goal from the official documentation, how the checker works and when it stops, how to write conditions, and how /goal differs from /loop and Codex's /goal. It also reports two runs aligning sentence-ending punctuation across this site's articles, including a 321-item run that finished in one turn, and notes that the checker cannot confirm finished quality that does not show up in the numbers.

Anthropic released Claude Dashboards, which builds dashboards when you ask questions about your company's data, and Claude Motion, which turns reports and charts into short explainer animations, in beta on October 8, 2026. Based on Anthropic's announcement and help documentation (checked October 22, 2026), this article covers the data sources you can connect (BigQuery, Snowflake, Salesforce, and more), the queries behind each chart, and three points to verify with queries. It also explains how Motion works (code-driven, not a video generation model, exported as MP4), plans and admin settings, how to choose between Docs, Slides, and Design, and when these tools fit or don't.

Google is replacing Gemini's Gems with skills. Gems end in November 2026 for personal Google accounts, March 2027 for work accounts, and June 2027 for school accounts, and remaining Gems are automatically rebuilt as skills, but Google Labs Gems, Opal, and GitHub files do not move. Based on Google's help pages and announcements (verified October 21, 2026), this article explains the differences between Gems and skills, three steps to move them yourself in advance, and how to create skills and use them with "/" (free to use, with up to 100 active at once). It also covers how to write names and descriptions that Gemini can use, what skills still cannot do, such as working with Canvas and Deep Research, and what to do before November.

Google's AI Gemini is free to use. Costs come from two separate paid options: app subscriptions (Google AI Plus, Pro, and Ultra), which raise usage limits and unlock higher-tier models, and the API, which is billed by usage. Based on Google's official pages (checked October 20, 2026), this guide covers plan prices and limits (reset every 5 hours, weekly caps), what is free and what isn't, Windows and Mac apps, API pricing and free tier (free-tier content is used to improve products), Antigravity for coding and the end of Gemini CLI for individuals, benchmarks separating Google's claims from third-party figures (Artificial Analysis), strengths and weaknesses, and which option to choose.

This guide walks through fixing a ChatGPT generated file that won't download, in order: requesting a new link, splitting the ZIP, and getting the file from Library. It includes an example of a roughly 12 MB ZIP that was received after splitting, and explains how to check that a handoff ZIP contains the required information.

This guide covers how to handle ChatGPT's "Message delivery timed out" error, following the official help steps. It explains how to ask for a resume without losing the partial answer, how to tell this apart from Too many requests on mobile, web, and the app, and what details to give support.

A site with an address like xxx.chatgpt.site is one that a ChatGPT user built and published with a feature called ChatGPT Sites. OpenAI provides the hosting, but it does not create the content or review or approve it, and responsibility lies with whoever built the site. This article is based on OpenAI's help articles, developer guide, terms, and release notes, which I checked in the original on October 11, 2026. ChatGPT Sites was introduced as a public beta on July 9, 2026, and is available on Plus, Pro, Business, Enterprise, and Edu, but not on Free or Go. During the beta, it is included in your subscription up to each plan's limits; the limit values and pricing after the beta have not been announced. The beta is provided "as is," OpenAI can unpublish a site for any reason, and even the example site in the developer guide returned a 404 when I checked. The article covers the constraints to know before using it in production (no guarantees, no choice of where data is stored, prohibited uses, and the creator's responsibility) and the uses it suits, how to connect a custom domain and change the URL, how to set visibility and permanently delete a site, and whether your conversations are used for training.

In the ChatGPT desktop app (Codex), right-click the floating pet and choose Hide Mini to remove it quickly. No official documentation describes a setting that disables pets in the app, so if a pet reappears, check the display shortcut first. This guide compares the steps, Mini, and the CLI, web, and IDE extension differences, using official documentation and a user-provided Windows screenshot.

On Windows, Claude Desktop refuses to start and shows "There's a problem with Claude. Reinstall the application from its original install location or contact your administrator." This is the message Windows shows when it refuses to launch a packaged (MSIX) app, and neither Anthropic's help center nor its documentation explains it or how to fix it (as of September 30, 2026). The dialog says to reinstall, but checking the state with Get-AppxPackage first tells you which route to take. If nothing is returned, the package registration is gone and a reinstall is all it takes. If Status reads Modified, NeedsRemediation, end the leftover processes and try Repair, then re-register with -DisableDevelopmentMode, then run the official installer over the top, and only as a last resort back up, remove and reinstall. A reinstall keeps your chat history and your Claude Code conversation logs (.claude\projects), but users report that the desktop app's session list was lost; claude --resume still opens those sessions. Microsoft's documentation limits Remove-AppxPackage -PreserveApplicationData to apps under development, and it has been reported to fail with 0x80073CFA. The article also sorts out the triggers seen in GitHub reports: crashes in the built-in browser, auto-updates while the app is running, and failed Cowork service registration.