#start-here

Subscription quota often beats pay-per-use API calls by several times. Give your own non-urgent, one-off back-office jobs to your AI agent, and use the API only for features that serve users live at high volume. Includes four questions to decide and the limits you must not cross.

A beginner tutorial: learn only 5 concepts (repository, commit, branch, cloud backup, revert), have the agent check Git and GitHub, and install a Git safety-net Skill. From then on, say in plain words to save, revert or upload, and it will always save first, explain changes afterwards and ask you before key actions. Finally, rehearse breaking something and recovering it. Includes 3 copy-ready prompts.

A beginner's guide: set a role and constraints first, describe the goal as the finished result, ask step by step, add a line against made-up facts, then have the AI score its own answer and revise it. All five rules come with copy-ready wording and one combined template.

A plain-language rewrite of Microsoft's open-source AI Agents for Beginners 19 lessons: 5 lessons are readable by general users, and 14 are for developers who want to build their own agents. Each lesson has key points, exercises, and a tutor prompt you can hand to an agent.

A beginner tutorial that explains in plain language what an AI agent is, what parts it is made of, the common types, and which tasks suit an agent and which do not need one.

A list of the models we currently find most useful, by use case: general, coding, complex reasoning, deep research, web search, long documents, slides, image drawing and editing, AI video, digital humans, voice and music, value for money, and open weights. Personal experience; models change fast, for reference only.

Beginner tutorial: you can write a Skill without coding. Step 1 is finding your repetitive work, step 2 is running it through manually first, step 3 is explaining the requirements to AI so it writes them into SKILL.md, step 4 is running and refining it, and step 5 is sharing it with others to use.

A practical lesson: models confidently present wrong things as right. Here is a prompt you can paste directly, which forces it to weigh evidence for and against based on authoritative literature, news and public discussion, give sources, separate facts from speculation, and state what information is still missing. Usage note: many models do not actually browse the web, so check the sources yourself.

Beginner tutorial: why AI-written text often has a distinctive tone, and how to remove it. The core principle comes from Anthropic's internal guide on removing AI flavor: if you can say it directly, say it directly. At the end is a prompt that works in both Chinese and English and suits any text model; paste it as is.

A short, repeatable way to write instructions a model follows reliably: role, input, output, rules, example. With a template you can paste.

Before an Agent touches your inbox or calendar, learn the three questions to ask about any connection, what "read-only" really means, and how to revoke access in two minutes.

Build a workflow that reads one calendar, summarizes next week, and delivers it to you every Friday. No code, one connection, under an hour.

A plain-language definition you can use in a meeting, the three parts every Agent has, and how to tell a real one from a chatbot with a nicer name.