Guides Google published jan 20, 2026
Learn a universal multiple-choice prompting strategy for getting better outputs from AI models while reducing unhelpful context and token usage. You’ll also learn the basics of tokens and context windows, then use the technique to produce clearer AI-generated concepts.
You’ll build a reusable multiple-choice interview prompt structure that helps an AI gather useful context before producing outputs. In the example workflow, you’ll use it to generate four distinct logo concepts.
When you interact with an AI, you use text. As a general rule, every four characters read or generated by an AI equals one token. Tokens are the chunks of text the model processes. If you send a prompt with 40 characters, you will be billed for about 10 tokens, plus however many tokens the AI uses in its response.
Input tokens are used when the AI parses what you send. Output tokens are based on the words, images, or videos generated by AI. Output is often pricier depending on the model.
Context is the relevant tokens stored in the AI’s “brain” while you’re talking to it. It is text summarizing what you have talked about so far that gets passed to the AI on each new request. The more context you have, the more tokens the AI has to process. The goal of this technique is to minimize unhelpful context so you can improve outputs and reduce token usage.
Think of a task you want AI to accomplish. The example in this guide uses AI Studio to create logo concepts for a brand. To minimize unhelpful messages stored in context, break your request into a goal, a task, and next steps.
Put your prompt together. The source example recommends writing the goal, task, and next steps conversationally.
Your job is to generate a logo for my student-run moving company, “Uni Movers.” Interview me with 5–10 multiple-choice questions about my brand and vision in order to build context for the task. Our goal is to create 4 distinct logo concepts.Send your prompt to your AI.
You should get back a list of questions with multiple-choice answers. Respond with each choice separated by commas, such as “A, B, A, C…”
Why this works: the multiple-choice constraint removes potential for miscommunication. It ensures your response uses terminology that AI will understand.
The AI should respond with four logo concepts. To save on tokens, you can ask it to generate a 4x4 grid with each logo concept in a separate grid cell. Then, ask it to generate the concepts you like as standalone images.
Generate a 4x4 grid with each logo concept in a separate grid cell.
Keep going
Members get all guides, courses, live sessions, and $1,000+ in partner perks.