AEO determinants prompt

An AEO determinants prompt maps what an AI assistant weighs before it recommends a business like yours: use case, selection criteria, audience, credibility and brand association. You get a gap list per determinant instead of a keyword list.

Stage
Plan, step 3 of 40
Use it
Before you plan pages, and again for each new buyer situation. It replaces keyword research for AI search.
You need
  • The buyer situation: who, where, and what they use today
  • The text of your current pages
You get
A table of what an assistant weighs for this buyer, with each item marked answered, partly answered or missing. Output schema included.

The prompt

Act as an AI assistant recommending a [service] provider.
The buyer is [audience], in [location], currently using [existing setup].
For this buyer, list what you would weigh before recommending anyone:
1. Use case: the job, their current setup and where they are.
2. Selection criteria: what they would compare, such as pricing model,
   speed, support and compliance.
3. Audience fit: who the provider must clearly serve.
4. Credibility: what proof you would look for, and where.
5. Brand association: what would make you link a brand to this category.
Then read my site text below. Mark each item as answered,
partly answered or missing, and name the page that answers it.
[paste your page text]
JSON version, for teams and automations

Fill each value under "inputs", keep the rest. It follows the prompt schema. When to use JSON.

{
  "$schema": "https://websitesdesigner.com/insights/prompts/prompt.schema.json",
  "id": "determinants-map",
  "name": "AEO determinants prompt",
  "stage": "plan",
  "step": 3,
  "of": 40,
  "version": "2026-11-19",
  "url": "https://websitesdesigner.com/insights/prompts/determinants-map/",
  "inputs": {
    "service": "[service]",
    "audience": "[audience]",
    "location": "[location]",
    "existing_setup": "[existing setup]",
    "paste_page_text": "[paste your page text]"
  },
  "instructions": [
    "Act as an AI assistant recommending a {{service}} provider.",
    "The buyer is {{audience}}, in {{location}}, currently using {{existing_setup}}.",
    "For this buyer, list what you would weigh before recommending anyone:",
    "1. Use case: the job, their current setup and where they are.",
    "2. Selection criteria: what they would compare, such as pricing model, speed, support and compliance.",
    "3. Audience fit: who the provider must clearly serve.",
    "4. Credibility: what proof you would look for, and where.",
    "5. Brand association: what would make you link a brand to this category.",
    "Then read my site text below.",
    "Mark each item as answered, partly answered or missing, and name the page that answers it.",
    "{{paste_page_text}}"
  ],
  "output": "A table of what an assistant weighs for this buyer, with each item marked answered, partly answered or missing.",
  "checks": [
    "Every determinant has at least two concrete items.",
    "Each item names a page or is marked missing.",
    "Gaps are written as things to add, not as topics."
  ],
  "output_schema": {
    "type": "object",
    "properties": {
      "buyer": {
        "type": "string"
      },
      "determinants": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "determinant": {
              "type": "string",
              "enum": [
                "use case",
                "selection criteria",
                "audience",
                "credibility",
                "brand association"
              ]
            },
            "what_ai_weighs": {
              "type": "string"
            },
            "status": {
              "type": "string",
              "enum": [
                "answered",
                "partly answered",
                "missing"
              ]
            },
            "page": {
              "type": [
                "string",
                "null"
              ]
            },
            "fix": {
              "type": "string"
            }
          },
          "required": [
            "determinant",
            "what_ai_weighs",
            "status",
            "page",
            "fix"
          ],
          "additionalProperties": false
        }
      }
    },
    "required": [
      "buyer",
      "determinants"
    ],
    "additionalProperties": false
  }
}
Output schema (JSON Schema)

Ready for strict structured-output modes: every field required, unknown values nullable. In a chat, paste it after the prompt with "Return only JSON that matches this schema." How output schemas work.

{
  "type": "object",
  "properties": {
    "buyer": {
      "type": "string"
    },
    "determinants": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "determinant": {
            "type": "string",
            "enum": [
              "use case",
              "selection criteria",
              "audience",
              "credibility",
              "brand association"
            ]
          },
          "what_ai_weighs": {
            "type": "string"
          },
          "status": {
            "type": "string",
            "enum": [
              "answered",
              "partly answered",
              "missing"
            ]
          },
          "page": {
            "type": [
              "string",
              "null"
            ]
          },
          "fix": {
            "type": "string"
          }
        },
        "required": [
          "determinant",
          "what_ai_weighs",
          "status",
          "page",
          "fix"
        ],
        "additionalProperties": false
      }
    }
  },
  "required": [
    "buyer",
    "determinants"
  ],
  "additionalProperties": false
}

What good output looks like

  • Every determinant has at least two concrete items.
  • Each item names a page or is marked missing.
  • Gaps are written as things to add, not as topics.

What experts miss

  • Credibility and brand association are mostly built off your site. When ChatGPT asks buyers follow-up questions, almost none are about credibility or brand. The model judges those from training and retrieval: reviews, press, directories and consistent naming.1
  • Map one buyer situation at a time. The same clinic looks different to an assistant when the buyer runs Wix than when they run a hospital system.
  • Turn every gap into a section, a table row or a piece of proof. A missing determinant is rarely fixed by another blog post.

Why it works

Opascope studied more than 659,000 ChatGPT buying answers. The use case shaped 92.5% of them, selection criteria 83.9%, audience 59.8% and credibility 55.6%, and almost every answer combined two or more.1 The shares are Opascope's own data and show how often a factor appears, not how much it weighs. A page that answers these for one buyer gives the assistant a reason to name you.

How to adapt it

  • Run it once per buyer type you name on your site.
  • Paste a competitor's page text instead of yours to see what they answer that you don't.

Mistakes to avoid

  • Mapping "everyone". A determinant only means something for a specific buyer.
  • Treating the assistant's list as fact. Check it against real buying conversations.

Go deeper

AEO determinants explains the idea in plain words. The customer questions prompt gives you the buyer's words. How to get cited by ChatGPT covers the five changes that follow, and context systems is how I build this for clients. This prompt is part of the plan stage. It follows the AI website design prompts guide and the six steps in how to use AI to design a website.

Read the prompts guideAll 40 prompts

Sources

  1. "The Determinants Manifesto," Jimmy Park (Opascope) and Tobias Peschke (Loud & Lexis), Opascope, 16 November 2026. opascope.com

Related prompts

Customer questions prompt

A customer questions prompt asks the AI to list the questions your buyers ask before they choose a provider like you. The list becomes your page headings, your FAQ and the prompts you later test AI search against.

Get the prompt

AI answer audit prompt

An AI answer audit prompt reads answers from ChatGPT, Perplexity and Google's AI to your buyers' questions and records whether you're named, how you're described, who else is named, and why. It shows what to fix rather than a rank.

Get the prompt

Service page prompt

A service page prompt builds one page per service around the buyer's situation: who it's for, what they use today, what they compare, what proof you have and what happens next. It answers what AI assistants weigh before they recommend anyone.

Get the prompt

Entity profile prompt

An entity profile prompt writes one canonical description of your business: name, category, what you do, for whom, where and since when, plus the profiles that are really yours. You copy it word for word to your site, your Google profile and directories.

Get the prompt

Want this done for you?

Want your determinants mapped for each buyer you serve? Book a call and I'll map the first one with you.

Book a 20-minute call