---
title: "Guides"
description: "Guides for getting better results from the Prototyper agent: write clear prompts, structure them with XML tags, and debug a build that went wrong."
date: "2026-10-06"
canonical: "https://www.prototyper.co/docs/guides"
---

# Guides

These guides cover the part of Prototyper that most shapes your results: what
you say to the agent. Start with being clear and direct and writing good
prompts. Move on to structure (XML tags and the built-in prompt enhancer) when
your requests get longer. When a build goes wrong, use the debugging guides and
their copy-paste templates to find the cause.

## Prompting

<Cards>
  <Card title="Be Clear and Direct" href="/docs/guides/be-clear-and-direct">
    Learn how to write prompts that are clear, contextual, and specific.
  </Card>
  <Card title="Writing Good Prompts" href="/docs/guides/writing-good-prompts">
    Plan before you prompt, build by component, and use real content.
  </Card>
  <Card title="Use XML Tags" href="/docs/guides/use-xml-tags">
    Structure your prompts with XML tags for clarity and accuracy.
  </Card>
  <Card title="Prompt Enhancer" href="/docs/guides/prompt-enhancer">
    Use the built-in AI-powered prompt improver.
  </Card>
</Cards>

## Debugging

<Cards>
  <Card title="Debugging Prompts" href="/docs/guides/debugging-prompts">
    Investigate errors and resolve issues systematically.
  </Card>
  <Card title="Advanced Debugging" href="/docs/guides/advanced-debugging">
    Codebase audits, fragile updates, and performance optimization.
  </Card>
  <Card title="Debugging Templates" href="/docs/guides/debugging-templates">
    Ready-to-use prompt templates and sample flows.
  </Card>
</Cards>

---

## Why prompting matters

The quality of your prompts directly impacts the quality of your output. A well-crafted prompt can:

- **Save time** — Get the right result on the first try instead of iterating endlessly
- **Improve consistency** — Produce predictable, high-quality outputs across your project
- **Enable complexity** — Break down complex tasks into manageable, precise instructions
- **Reduce errors** — Prevent misunderstandings that lead to bugs and rework

## The golden rule

<Callout type="info">
Show your prompt to a colleague who has minimal context on the task, and ask them to follow the instructions. If they're confused, the AI will likely be too.
</Callout>

## Quick tips

1. **Be specific** — Say exactly what you want, not what you don't want
2. **Provide context** — Explain what the task is for and who will use the result
3. **Use examples** — Show the AI what good output looks like
4. **Break it down** — Split complex requests into smaller, focused prompts
5. **Iterate** — Refine your prompts based on the results you get