#prompt

Beginner tutorial: have your AI agent search the web for an unfamiliar industry using the five forces model, then use a fresh chat to check the sources, ask peers and customers what the web cannot answer, try a small task yourself, and pick a first step based on how much you can afford to lose, with 6 copy-ready prompts.

Beginner tutorial: Build a Space in Meta Muse with one prompt, using an open-source Chinese pose gallery as the source. Only two safe categories are included. Each pose gets a stick-figure sketch and prompts for Seedance, Kling, FLUX and Midjourney. Then check the list, generate, and set a weekly auto-refresh for new poses. Includes 3 copy-ready prompts.

Edit with three-part prompts that change only what you want, and turn a selfie into a portrait that still looks like you.

An AI private tutor that works in stages: it helps you set testable goals, replaces lectures with mistakes and follow-up questions, and finally has you explain the material back to it to confirm you have really learned it.

Advanced tutorial: Walk through four weeks with a sample Markdown-to-PDF site: in Week 1, screen for small, precise demand; in Week 2, check search results to decide page format; in Week 3, write a core page and supporting pages and link them to each other; from Week 4 on, read Search Console against a symptom lookup table. Includes two prompt templates and an experiment log template.

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.

Developer advanced tutorial: to build a trustworthy agent, manage its system prompt well and recognize six common threats: tampered instructions, unauthorized access, resource abuse, knowledge base poisoning, cascading failures, and how to defend against them.

Agents get less obedient the more you use them, usually because AGENTS.md has piled up too much. Write only what the agent can't see for itself and that really affects results, prune it regularly, and include a cleanup prompt.

A prompt I have refined over a long period on ChatGPT and Gemini. It makes the model give the answer first, attach conditions to its judgments, search first for time-sensitive information, and end with a next step. Includes a simplified full text and usage instructions.

Hand the tutorial to an Agent and it works through it to the end; you only confirm key steps such as logging in and paying, so learning and putting it into practice happen in one go.