Primitive/seo3 min read

Introducing /seo and /aeo: rank in Google and show up in AI answers

Keyword volume, backlinks, SERP competitors, and ranked-keyword data for classic search — plus AEO/GEO visibility into whether ChatGPT, Claude, Gemini, and Perplexity actually mention you. The full visibility stack behind one key.

/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
/seo /seo /seo /seo /seo /seo /seo /seo /seo /seo
Primitive/seo
TL;DR
  • /seo search volume, ranked keywords, backlinks, and SERP competitor data behind one key
  • /aeo answer-engine optimization: see what ChatGPT, Claude, Gemini, and Perplexity actually say and cite
  • LLM mentions track whether and where your brand is referenced in AI answers, and who's cited instead
  • AI keyword volume measure demand in AI search, not just classic search
  • Close the loop measure visibility, then act with /apps content and /social distribution
  • Agent-native data structured results an Employee can query, decide on, and act against

Today we're launching /seo and /aeo — the visibility stack for autonomous companies. /seo covers classic search: keyword volume, ranked keywords, backlinks, and SERP competitors. /aeo covers the new frontier: whether ChatGPT, Claude, Gemini, and Perplexity actually mention and cite you when someone asks. Both return structured data an agent can query and act on, behind the same key as everything else.

The problem: visibility moved, and most tools didn't

For two decades, "getting found" meant ranking in Google. SEO tools grew up around that single surface. But the way people research has split in two:

  • Classic search still matters — and measuring it (volume, rankings, backlinks, competitors) is table stakes.
  • AI search is now where a huge share of high-intent questions land. "What's the best tool for X" increasingly gets answered by a model that names a handful of products — and if you're not one of them, you never enter the consideration set.

The second surface is almost entirely dark to traditional tooling. You can obsess over your SERP position and still be invisible inside the assistant your customer actually asked. And for an agent running a business, both surfaces need to be data, not dashboards. Until now.

/seo: classic search intelligence

The SEO primitive gives you the core operations a growth team runs daily, as one-line calls — with generic passthroughs for the full keyword/backlink/labs surface when you need it.

// Demand: monthly search volume for keywords
const vol = await naive.seo.searchVolume(["ai agent infrastructure", "agent backend"]);
 
// Rankings: what a domain already ranks for
const ranked = await naive.seo.rankedKeywords("usenaive.ai");
 
// Authority: a backlink profile summary
const backlinks = await naive.seo.backlinksSummary("competitor.com");
 
// Competition: who else ranks for these terms
const rivals = await naive.seo.serpCompetitors(["agent infrastructure"]);

Heavier operations follow an async task pattern — submit a task, then poll for the result:

const task = await naive.seo.keywordsTask("google", "search-volume", { keywords: ["..."] });
const ready = await naive.seo.keywordsTasksReady("google", "search-volume");

/aeo: answer-engine optimization

/aeo measures the surface traditional tools can't see. Ask what a model actually says, check whether you're mentioned, find who gets cited instead, and size demand for AI-driven queries.

// What does ChatGPT actually respond to a buying prompt?
const resp = await naive.aeo.llmResponses("chatgpt", {
  user_prompt: "What's the best infrastructure for AI agents?",
});
 
// Are you mentioned in AI answers — and who is?
const mentions = await naive.aeo.llmMentions("search", { keyword: "naive" });
const topDomains = await naive.aeo.llmMentions("top-domains", { keyword: "agent infrastructure" });
 
// Demand inside AI search
const aiVolume = await naive.aeo.aiKeywords({ keywords: ["agent infrastructure"] });

You can target chatgpt, claude, gemini, or perplexity, and the mentions endpoints (search, aggregated-metrics, top-domains, top-pages, and more) let you go from "are we cited" to "which page of ours wins, and where are we losing."

Close the loop

The point of measuring visibility is to change it. Because /seo and /aeo live behind the same key as the rest of the platform, an agent can act on what it learns:

  • Find a high-volume, low-competition keyword with /seo, then ship a page targeting it with /apps.
  • See a competitor getting cited by Claude with /aeo, then research why with /research and publish a better answer.
  • Distribute the result with /social, then re-measure mentions next week.

What you can build with /seo and /aeo

Run a self-optimizing content engine — An Employee pulls keyword gaps and AI-mention gaps weekly, drafts content to fill them, ships it, and tracks whether rankings and citations move — a growth loop that runs without a marketer in the seat.

Monitor your AI-search reputation — Schedule /cron checks on the prompts that matter to your business and get alerted when a model starts recommending a competitor over you.

Do competitive intelligence on both surfaces — Compare your rankings and backlink profile against rivals in classic search, and your citation share against them in AI answers — one report, two surfaces.

Brief a launch with real demand data — Before /apps ships a landing page, size the keywords and AI queries it should target so the copy aims at demand that exists.

Get started

Drop this starter prompt into any coding agent to wire up Naïve:

Read https://usenaive.ai/skill.md and use it to set up Naïve in my project.

Frequently Asked Questions
What is /seo?+
/seo is Naïve's search-intelligence primitive. It exposes keyword search volume, ranked keywords for any domain, backlink summaries, and SERP competitor analysis through your single Naïve key, with convenience methods for the common operations and generic passthroughs for the full surface.
What is /aeo (AEO/GEO)?+
/aeo is answer-engine optimization, also called GEO (generative engine optimization). It measures your visibility in AI search: what models like ChatGPT, Claude, Gemini, and Perplexity actually respond to a prompt, whether your brand is mentioned, which domains and pages they cite, and search volume for AI-driven queries.
Why does AEO matter now?+
A growing share of buying research happens inside AI assistants, not a list of blue links. If a model recommends a competitor when asked 'what's the best X', you've lost the customer before they ever saw a SERP. AEO makes that previously invisible surface measurable so you can act on it.
Where does the data come from?+
Both primitives are backed by industry-grade search data providers and live model querying. Many endpoints return synchronously; heavier operations follow an async task pattern (submit a task, poll for the result), mirrored by the SDK's task methods.
How is this different from /research?+
/research reads the open web and synthesizes answers with citations for a question. /seo and /aeo return structured visibility metrics — volumes, rankings, backlinks, and mention data — meant for decisions and monitoring, not prose. They compose well: research to understand, /seo and /aeo to measure.
How do I get started?+
Call naive.seo.searchVolume([...]) and naive.aeo.llmResponses("chatgpt", {...}) with the SDK. The full guide is at usenaive.ai/docs/getting-started/seo.
DZ
Dennis ZaxCTO

CTO of Naïve. Building the open-source agent runtime.

@denniszax