Content

Sitemap & Site IA Spec Prompt — Pages, Navigation, and Structure

Turn website goals, audiences, content types, and conversion paths into a sitemap and information-architecture spec: navigation, a page inventory, hierarchy, URLs, user journeys, and an internal-linking plan.

Open in Markdown Output Builder

Overview

A website structured page by page becomes a maze — navigation no one can follow and pages that don't connect to a goal. This prompt builds the information architecture first: from the site's purpose, audiences, content types, and conversion paths it produces an IA specification — primary and secondary navigation, a full page inventory, the page hierarchy, URL/slug recommendations, the key user journeys, content requirements per page, an internal-linking plan, indexability notes, and the IA risks and open questions. It is a planning artifact a team builds from, not a crawl: it does not draw a visual sitemap diagram, generate an XML sitemap file, or run a technical SEO audit — it produces a sitemap-ready textual outline you can turn into either. It is for organizing a multi-page site (a company site, a docs site, or a knowledge base), distinct from structuring a single long reference document.

How to use this resource

Start from goals, not pages

Navigation and page inventory trace to audience goals and conversion paths, so the structure serves visitors, not the org chart.
Make the hierarchy explicit

A page tree, URLs, and per-page content requirements turn a vague "site map" into something a team can build.
Connect and de-risk

An internal-linking plan ties pages to the conversion paths, and IA risks become open questions instead of post-launch surprises.

Why This Works

Grouping by visitor intent instead of internal structure is the single biggest driver of navigability
A per-page purpose and content requirement prevents the orphan pages a page-by-page build accumulates
Naming IA risks as open questions surfaces the grouping decisions that are expensive to change after launch

Best for

Planning a company website's structure and navigation
Planning a documentation or knowledge-base information architecture
Turning pages and user goals into a sitemap
Designing navigation and hierarchy before writing page copy

Not for

Structuring a single long reference document — that's Structure Large Reference Documents
Writing the page copy — use the landing-page copy prompts
Generating an XML sitemap file — this is an IA planning spec, not a crawler file
Technical SEO crawling or indexability audits — use an SEO-specific tool

Use cases

Planning the sitemap and navigation for a company website before writing pages
Designing the information architecture of a documentation site or knowledge base
Turning a pile of pages and goals into a navigable hierarchy with an internal-linking plan

FAQ

Will this produce an actual XML sitemap file or a visual diagram?

Neither — it produces a textual IA specification. A Rules line states it does "not draw a visual sitemap, generate an XML sitemap file, or claim to crawl the site." What you get is item 12, a SITEMAP-READY OUTLINE that "a developer or a diagramming tool can render." The markdown-output-builder shapes the prompt; you run it, then feed the outline into whatever tool draws or crawls.

How does this decide which pages the site actually needs?

Every page must trace to an audience goal or a content type you supplied — a Rules line bars "speculative pages." You paste the purpose, audiences, content types, and conversion paths; PAGE INVENTORY groups each page by section with a one-line purpose, and grouping follows "how visitors think, not by how the company is organized." Unresolved grouping goes into IA RISKS & OPEN QUESTIONS rather than being guessed.

Can I use this to structure one long reference document instead of a multi-page site?

It's built for multi-page sites, not a single document. The output is site-shaped — PRIMARY NAVIGATION, PAGE HIERARCHY as an indented tree, KEY USER JOURNEYS across pages, and an INTERNAL-LINKING PLAN toward the conversion paths. Those assume many pages connecting to goals. Organizing sections within one long document is a different job, which the notFor points to Structure Large Reference Documents for.

Customize This Resource

Opens this setup in Markdown Output Builder. Generate to get the full markdown prompt — then adjust the sections, table rules, and consistency level.

Open in Markdown Output Builder

Inputs you need

Have these details ready before you copy or open the template.

The site purpose and the business goals it serves
The primary audiences and what each is trying to do
The main content types or sections the site needs
The conversion goals or key actions you want visitors to take
SEO, scale, or navigation constraints (or not specified)

Prompt Template

Copy it as-is, or use Open in Markdown Output Builder to load it pre-filled and customize it with your own context.

SITEMAP & INFORMATION ARCHITECTURE SPEC

You are designing the information architecture for a website. Work from the goals, audiences, and content given — do not invent pages, audiences, or content the site doesn't need. This produces a textual IA specification, not a visual diagram and not an XML sitemap file.

Paste the website purpose and goals:
[What the site is for, and the business goals it serves]

Paste the audiences:
[Who visits, and what each audience is trying to do]

Paste the content types and key pages you know you need:
[Products, services, docs, blog, pricing, about, support — whatever applies]

Paste the conversion paths / primary actions:
[What you want visitors to do — sign up, contact, buy, read docs — and from where]

Paste constraints:
[Site type (marketing / docs / knowledge base), scale, existing URLs, SEO or localization needs — write "not specified" for any you lack]

Return:
1. WEBSITE PURPOSE & AUDIENCE SUMMARY — the site's job and who it serves, in a few lines.
2. PRIMARY NAVIGATION — the top-level nav items, ordered, each mapped to an audience goal.
3. SECONDARY / FOOTER NAVIGATION — utility, legal, and supporting links.
4. PAGE INVENTORY — every page the site needs, grouped by section, each with a one-line purpose.
5. PAGE HIERARCHY — the parent/child nesting, shown as an indented tree.
6. URL / SLUG RECOMMENDATIONS — a clean, consistent slug for each page; flag any that affect existing URLs.
7. KEY USER JOURNEYS — for each audience, the path from entry to primary action across pages.
8. CONTENT REQUIREMENTS PER PAGE — what each high-stakes page must contain to do its job.
9. INTERNAL-LINKING PLAN — the links that connect related pages and move visitors toward the conversion paths.
10. SEO / INDEXABILITY NOTES — which pages to index, canonical/duplication risks, and depth-from-home concerns (planning notes, not a crawl).
11. IA RISKS & OPEN QUESTIONS — overloaded sections, orphan pages, ambiguous grouping, and what to decide before building.
12. SITEMAP-READY OUTLINE — a compact, build-ready outline of the whole site that a developer or a diagramming tool can render.

Rules:
- Every page must trace to an audience goal or a content type you were given — no speculative pages.
- Group by how visitors think, not by how the company is organized.
- Do not draw a visual sitemap, generate an XML sitemap file, or claim to crawl the site — this is an IA plan.
- Name the IA risks honestly; put unresolved grouping decisions in Open Questions rather than guessing.

More resources from Markdown Output Builder

Resource

Markdown Output Prompt — Lock the Document Structure

The contract that stops AI documents from restructuring themselves: a pinned section skeleton, forced tables, and strict consistency rules.

Prompt Engineering

Resource

README Prompt Template

Overview, Installation, Usage, Examples, Configuration — the README skeleton with required, runnable code examples.

Engineering

Resource

API Documentation Prompt

Overview, Authentication, Endpoints, Error Handling, Rate Limits — endpoint docs in an identical structure, with parameter tables and runnable examples forced.

Engineering

Resources that pair well

Resource

Executive Summary Prompt

Summary, Why It Matters, What Happens Next — the executive summary contract for readers who will never open the source.

Operations

Resource

Force JSON Output from AI

Stop getting 'Sure, here is the JSON…' — the output-contract pattern that forces models to return only parseable JSON: schema, example, and a strict rule block.

Prompt Engineering

Resource

Fix Invalid JSON from AI

The JSON won't parse and you can't see why. Deterministic cause-sniffing — trailing commas, single quotes, unclosed brackets — and the repair prompt that fixes it.

Engineering

Related tools

Tool

Markdown Output Builder

Build prompts that produce documents in a fixed structure — headings, sections, and tables.

Structured Output

Projects that use this resource

Project

Build a Company Website with AI

The full path to a business website that holds together — plan the content, structure the site, design the components, write the page copy, then ship it as one coherent whole.

5 stages Websites

Project

Build a Documentation Website with AI

The full path to docs people can actually navigate — plan the doc set, structure the site, write the guides and the API reference, then ship it as a coherent documentation site.

5 stages Websites

Project

Build a Knowledge Base with AI

The full path to knowledge that's findable by people and AI — plan the taxonomy, structure it for search, write the articles, tag the metadata, make it retrievable, then ship it maintainable.

6 stages Knowledge Systems

Workflows that use this resource

Workflow

AI Website Structure Workflow

Organize a site so people and crawlers find things — inventory the content, group it into a real hierarchy, design the sitemap and navigation, then document the information architecture for the build.

4 steps 40–70 minutes

Tip: Save time by exploring related resources and tools that integrate with this resource.